From 23e8dc1a3d45802837feabdf95e4dbe5ec2f1eb6 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?=C3=81sgeir=20Thor=20Johnson?= Date: Thu, 18 Jun 2026 19:41:02 +0000 Subject: [PATCH] Update Claude Code bundled skills and Opus 4.8 prompt - bundled-skills: add compact.md and init-new.md; update init.md and update-config.md; remove update-config-schema.json - claude-opus-4.8.md: refresh prompt content --- .../Claude Code/bundled-skills/compact.md | 142 + .../Claude Code/bundled-skills/init-new.md | 228 ++ Anthropic/Claude Code/bundled-skills/init.md | 235 +- .../bundled-skills/update-config-schema.json | 3057 ---------------- .../bundled-skills/update-config.md | 3067 ++++++++++++++++- Anthropic/claude-opus-4.8.md | 4 +- 6 files changed, 3448 insertions(+), 3285 deletions(-) create mode 100644 Anthropic/Claude Code/bundled-skills/compact.md create mode 100644 Anthropic/Claude Code/bundled-skills/init-new.md delete mode 100644 Anthropic/Claude Code/bundled-skills/update-config-schema.json diff --git a/Anthropic/Claude Code/bundled-skills/compact.md b/Anthropic/Claude Code/bundled-skills/compact.md new file mode 100644 index 0000000..120f027 --- /dev/null +++ b/Anthropic/Claude Code/bundled-skills/compact.md @@ -0,0 +1,142 @@ +CRITICAL: Respond with TEXT ONLY. Do NOT call any tools. + +- Do NOT use Read, Bash, Grep, Glob, Edit, Write, or ANY other tool. +- You already have all the context you need in the conversation above. +- Tool calls will be REJECTED and will waste your only turn — you will fail the task. +- Your entire response must be plain text: an `` block followed by a `` block. + +Your task is to create a detailed summary of the conversation so far, paying close attention to the user's explicit requests and your previous actions. +This summary should be thorough in capturing technical details, code patterns, and architectural decisions that would be essential for continuing development work without losing context. + +Before providing your final summary, wrap your analysis in `` tags to organize your thoughts and ensure you've covered all necessary points. In your analysis process: + +1. Chronologically analyze each message and section of the conversation. For each section thoroughly identify: + - The user's explicit requests and intents + - Your approach to addressing the user's requests + - Key decisions, technical concepts and code patterns + - Specific details like: + - file names + - full code snippets + - function signatures + - file edits + - Errors that you ran into and how you fixed them + - Pay special attention to specific user feedback that you received, especially if the user told you to do something differently. + - Note any security-relevant instructions or constraints the user stated (e.g., sensitive files or data to avoid, operations that must not be performed, credential or secret handling rules). These MUST be preserved verbatim in the summary so they continue to apply after compaction. +2. Double-check for technical accuracy and completeness, addressing each required element thoroughly. + +Your summary should include the following sections: + +1. Primary Request and Intent: Capture all of the user's explicit requests and intents in detail +2. Key Technical Concepts: List all important technical concepts, technologies, and frameworks discussed. +3. Files and Code Sections: Enumerate specific files and code sections examined, modified, or created. Pay special attention to the most recent messages and include full code snippets where applicable and include a summary of why this file read or edit is important. +4. Errors and fixes: List all errors that you ran into, and how you fixed them. Pay special attention to specific user feedback that you received, especially if the user told you to do something differently. +5. Problem Solving: Document problems solved and any ongoing troubleshooting efforts. +6. All user messages: List ALL user messages that are not tool results. These are critical for understanding the users' feedback and changing intent. Preserve any security-relevant instructions or constraints verbatim so they remain in effect after compaction. +7. Pending Tasks: Outline any pending tasks that you have explicitly been asked to work on. +8. Current Work: Describe in detail precisely what was being worked on immediately before this summary request, paying special attention to the most recent messages from both user and assistant. Include file names and code snippets where applicable. +9. Optional Next Step: List the next step that you will take that is related to the most recent work you were doing. IMPORTANT: ensure that this step is DIRECTLY in line with the user's most recent explicit requests, and the task you were working on immediately before this summary request. If your last task was concluded, then only list next steps if they are explicitly in line with the users request. Do not start on tangential requests or really old requests that were already completed without confirming with the user first. + If there is a next step, include direct quotes from the most recent conversation showing exactly what task you were working on and where you left off. This should be verbatim to ensure there's no drift in task interpretation. + +Here's an example of how your output should be structured: + + + +`` + + + +`` + + +[Your thought process, ensuring all points are covered thoroughly and accurately] + + +`` + + + + +`` + + +1. Primary Request and Intent: + [Detailed description] + +2. Key Technical Concepts: + - [Concept 1] + - [Concept 2] + - [...] + +3. Files and Code Sections: + - [File Name 1] + - [Summary of why this file is important] + - [Summary of the changes made to this file, if any] + - [Important Code Snippet] + - [File Name 2] + - [Important Code Snippet] + - [...] + +4. Errors and fixes: + - [Detailed description of error 1]: + - [How you fixed the error] + - [User feedback on the error if any] + - [...] + +5. Problem Solving: + [Description of solved problems and ongoing troubleshooting] + +6. All user messages: + - [Detailed non tool use user message] + - [...] + +7. Pending Tasks: + - [Task 1] + - [Task 2] + - [...] + +8. Current Work: + [Precise description of current work] + +9. Optional Next Step: + [Optional Next step to take] + + + +`` + + + +`` + + + +Please provide your summary based on the conversation so far, following this structure and ensuring precision and thoroughness in your response. + +There may be additional summarization instructions provided in the included context. If so, remember to follow these instructions when creating the above summary. Examples of instructions include: + + +`` + + +## Compact Instructions +When summarizing the conversation focus on typescript code changes and also remember the mistakes you made and how you fixed them. + + +`` + + + + +`` + + +# Summary instructions +When you are using compact - please focus on test output and code changes. Include file reads verbatim. + + +`` + + + + +REMINDER: Do NOT call any tools. Respond with plain text only — an `` block followed by a `` block. Tool calls will be rejected and you will fail the task. \ No newline at end of file diff --git a/Anthropic/Claude Code/bundled-skills/init-new.md b/Anthropic/Claude Code/bundled-skills/init-new.md new file mode 100644 index 0000000..ff51524 --- /dev/null +++ b/Anthropic/Claude Code/bundled-skills/init-new.md @@ -0,0 +1,228 @@ +--- +name: init +description: Initialize a new CLAUDE.md file with codebase documentation. +--- + +Set up a minimal CLAUDE.md (and optionally skills and hooks) for this repo. CLAUDE.md is loaded into every Claude Code session, so it must be concise — only include what Claude would get wrong without it. + +## Phase 0: Check for an existing CLAUDE.md + +Before asking anything, check if CLAUDE.md already exists at the project root (just `cat ./CLAUDE.md` — only the project-root file counts; don't explore the tree yet). This branches Phase 1. + +## Phase 1: Ask what to set up + +Use AskUserQuestion to find out what the user wants. Which question you ask depends on Phase 0. Call AskUserQuestion with **only Q1** — do NOT include Q2 in the same call. Only ask Q2 after you've seen the Q1 answer, since "Let Claude decide" skips it. + +Before the first question, print this primer as normal assistant text so first-time users know the terms: + +> Quick context: +> - **CLAUDE.md** files give Claude persistent instructions for a project, your personal workflow, or your organization. Claude reads them at the start of every session. +> - **Skills** are packaged instructions Claude invokes automatically when a task matches, or that you trigger with a slash command (e.g. `/frontend-design`, `/commit-push-pr`). +> - **Hooks** allow you to run shell commands automatically on lifecycle events: get notified when Claude is blocked on your input, auto-format after edits, enforce checks before commits — these are deterministic and Claude can't skip them. + +**If CLAUDE.md already exists**, ask: +- "I found an existing CLAUDE.md. What would you like to do?" + Options: "Review and improve it" | "Leave it, set up other things" | "Start fresh (replace it)" + Description for improve: "Explore what's changed in the codebase and propose targeted edits to the existing file." + Description for leave it: "Skip CLAUDE.md. Go straight to skills and hooks." + Description for start fresh: "Discard it and write new file(s)." + Routing: + - "Review and improve" → skip Q1/Q2; explore (Phase 2), ask the single Phase 3-lite question, then go to Phase 4's diff-proposal, then Phase 8. + - "Leave it" → skip Q1, ask Q2 (rename its fourth option to "Neither — skip setup"). If they pick "Neither — skip setup", jump straight to Phase 8 with: "Nothing to set up — your CLAUDE.md is unchanged." Otherwise: Phase 2 → Phase 3 proposal (no gap-fill interview) → Phases 6/7 per queue → Phase 8. For Phase 7's hook target-file default, treat this path as "project" (`.claude/settings.json`). + - "Start fresh" → continue to Q1 below as if no file existed. + +**If no CLAUDE.md exists** (or the user picked "Start fresh"), ask: +- Q1: "Which CLAUDE.md files should /init set up?" + Options: "Project CLAUDE.md" | "Personal CLAUDE.local.md" | "Both project + personal" | "Let Claude decide" + Description for project: "Team-shared instructions checked into source control — architecture, coding standards, common workflows." + Description for personal: "Your private preferences for this project (gitignored, not shared) — your role, sandbox URLs, preferred test data, workflow quirks." + Description for Let Claude decide: "Fastest path — project CLAUDE.md plus whatever skills or hooks fit this repo. No follow-on questions; you'll approve everything before it's written." + If the user picks "Let Claude decide", skip Q2 — treat it as project CLAUDE.md with no skills/hooks constraint. + +- Q2: "Also set up skills and hooks?" + Options: "Skills + hooks" | "Skills only" | "Hooks only" | "Neither, just CLAUDE.md" + Description for skills: "Packaged instructions Claude invokes automatically when a task matches, or that you trigger with a slash command (e.g. `/frontend-design`, `/commit-push-pr`)." + Description for hooks: "Deterministic shell commands that run on tool events (e.g., format after every edit). Claude can't skip them." + Q2 is a hint, not a filter — Phase 3 proposes what fits the codebase and notes any deviation. + +## Phase 2: Explore the codebase + +Launch a subagent to survey the codebase, and ask it to read key files to understand the project: manifest files (package.json, Cargo.toml, pyproject.toml, go.mod, pom.xml, etc.), README, Makefile/build configs, CI config, existing CLAUDE.md, .claude/rules/, AGENTS.md, .cursor/rules or .cursorrules, .github/copilot-instructions.md, .windsurfrules, .clinerules, .mcp.json. + +Detect: +- Build, test, and lint commands (especially non-standard ones) +- Languages, frameworks, and package manager +- Project structure (monorepo with workspaces, multi-module, or single project) +- Code style rules that differ from language defaults +- Non-obvious gotchas, required env vars, or workflow quirks +- Existing .claude/skills/ and .claude/rules/ directories +- Formatter configuration (prettier, biome, ruff, black, gofmt, rustfmt, or a unified format script like `npm run format` / `make fmt`) +- Git worktree usage: run `git worktree list` to check if this repo has multiple worktrees (only relevant if the user wants a personal CLAUDE.local.md) + +Note what you could NOT figure out from code alone — these become interview questions. + +## Phase 3: Fill in the gaps + +Use AskUserQuestion to gather what you still need to write good CLAUDE.md files and skills. Ask only things the code can't answer. + +If the user chose project CLAUDE.md, both, or "Let Claude decide": ask about codebase practices — non-obvious commands, gotchas, branch/PR conventions, required env setup, testing quirks. Skip things already in README or obvious from manifest files. Do not mark any options as "recommended" — this is about how their team works, not best practices. + +If the user chose personal CLAUDE.local.md or both: ask about them, not the codebase. Do not mark any options as "recommended" — this is about their personal preferences, not best practices. Examples of questions: + - What's their role on the team? (e.g., "backend engineer", "data scientist", "new hire onboarding") + - How familiar are they with this codebase and its languages/frameworks? (so Claude can calibrate explanation depth) + - Do they have personal sandbox URLs, test accounts, API key paths, or local setup details Claude should know? + - Only if Phase 2 found multiple git worktrees: ask whether their worktrees are nested inside the main repo (e.g., `.claude/worktrees//`) or siblings/external (e.g., `../myrepo-feature/`). If nested, the upward file walk finds the main repo's CLAUDE.local.md automatically — no special handling needed. If sibling/external, the personal content should live in a home-directory file (e.g., `~/.claude/-instructions.md`) and each worktree gets a one-line CLAUDE.local.md stub that imports it: `@~/.claude/-instructions.md`. Never put this import in the project CLAUDE.md — that would check a personal reference into the team-shared file. + - Any communication preferences? (e.g., "be terse", "always explain tradeoffs", "don't summarize at the end") + +If the user picked "Review and improve" in Phase 0: ask just one question — "Has anything changed about how the team works since this CLAUDE.md was written (new conventions, commands, gotchas)?" with options "No, nothing's changed" | "Yes — let me describe". If they pick Yes, ask what changed (free text) before continuing. Then skip to Phase 4. + +**Synthesize a proposal from Phase 2 findings and the gap-fill answers.** For each item, pick the artifact type that fits the evidence: + + - **Hook** — deterministic, fast, per-edit shell command (formatting, linting a changed file). + - **Skill** — on-demand multi-step workflow (`/verify`, `/deploy-staging`, session reports). + - **CLAUDE.md note** — guidance that shapes behavior but isn't enforced (conventions, communication style). + +Include the CLAUDE.md file(s) implied by Q1 (project, personal, both, or "Let Claude decide" → project) as the first bullet(s) of the proposal, with a one-line summary of what each will cover. Then list skills/hooks/notes. On the "Leave it" path, omit CLAUDE.md file bullets and notes (Phase 4 won't run). On the "Start fresh" path with Q1 = personal-only, add a bullet noting the existing project CLAUDE.md will be left untouched (they chose not to replace it with a project file). + +Propose what fits. If the user gave a Q2 hint and your proposal deviates from it (e.g. they said "Hooks only" but nothing hook-shaped exists), say so in one line at the top of the proposal and propose the better-fitting artifacts anyway. + +**Print the proposal as normal assistant text**, one bullet per item: + +> Here's what I'd set up: +> • **[Artifact type: file/hook/skill/note]** — [one-line description] +> • … + +Then call AskUserQuestion with a simple question ("Does this look right?") and options like "Looks good — proceed" | "Drop the hook" | "Drop the skill". Don't use the `preview` field — the proposal is already visible in scrollback. The tool auto-adds an "Other" option for custom tweaks. + +**Build the preference queue** from the accepted proposal. Each entry: {type: hook|skill|note, description, target file, any Phase-2-sourced details like the actual test/format command}. Phase 6 and Phase 7's hooks sub-bullet consume this queue; Phases 4/5 gate on the approved proposal's file bullets directly; Phase 7's GitHub-CLI and linting checks run regardless of queue contents. + +## Phase 4: Write CLAUDE.md (if the approved proposal includes it, or on the "Review and improve" path) + +Write a minimal CLAUDE.md at the project root. Every line must pass this test: "Would removing this cause Claude to make mistakes?" If no, cut it. + +If the user picked "Review and improve it" in Phase 0: don't write fresh — read the existing file, compare against Phase 2 findings and the Phase 3-lite answer, and propose specific additions/removals as diffs with a one-line reason for each. The existing file is the baseline; your job is to catch what's missing, outdated, or bloated. After printing the diffs, call AskUserQuestion ("Apply these edits?" with options like "Apply all" | "Let me pick which" | "Skip — leave it as is") before writing anything. + +**Consume `note` entries from the Phase 3 preference queue whose target is CLAUDE.md** (team-level notes) — add each as a concise line in the most relevant section. These are the behaviors the user wants Claude to follow but didn't need guaranteed (e.g., "propose a plan before implementing", "explain the tradeoffs when refactoring"). Leave personal-targeted notes for Phase 5. + +Include: +- Build/test/lint commands Claude can't guess (non-standard scripts, flags, or sequences) +- Code style rules that DIFFER from language defaults (e.g., "prefer type over interface") +- Testing instructions and quirks (e.g., "run single test with: pytest -k 'test_name'") +- Repo etiquette (branch naming, PR conventions, commit style) +- Required env vars or setup steps +- Non-obvious gotchas or architectural decisions +- Important parts from existing AI coding tool configs if they exist (AGENTS.md, .cursor/rules, .cursorrules, .github/copilot-instructions.md, .windsurfrules, .clinerules) + +Exclude: +- File-by-file structure or component lists (Claude can discover these by reading the codebase) +- Standard language conventions Claude already knows +- Generic advice ("write clean code", "handle errors") +- Detailed API docs or long references — use `@path/to/import` syntax instead (e.g., `@docs/api-reference.md`) to inline content on demand without bloating CLAUDE.md +- Information that changes frequently — reference the source with `@path/to/import` so Claude always reads the current version +- Long tutorials or walkthroughs (move to a separate file and reference with `@path/to/import`, or put in a skill) +- Commands obvious from manifest files (e.g., standard "npm test", "cargo test", "pytest") + +Be specific: "Use 2-space indentation in TypeScript" is better than "Format code properly." + +Do not repeat yourself and do not make up sections like "Common Development Tasks" or "Tips for Development" — only include information expressly found in files you read. + +Prefix the file with: + +``` +# CLAUDE.md + +This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository. +``` + +For projects with multiple concerns, suggest organizing instructions into `.claude/rules/` as separate focused files (e.g., `code-style.md`, `testing.md`, `security.md`). These are loaded automatically alongside CLAUDE.md and can be scoped to specific file paths using `paths` frontmatter. + +For projects with distinct subdirectories (monorepos, multi-module projects, etc.): mention that subdirectory CLAUDE.md files can be added for module-specific instructions (they're loaded automatically when Claude works in those directories). Offer to create them if the user wants. + +## Phase 5: Write CLAUDE.local.md (if the approved proposal includes it) + +Write a minimal CLAUDE.local.md at the project root. This file is automatically loaded alongside CLAUDE.md. After creating it, add `CLAUDE.local.md` to the project's .gitignore so it stays private. + +**Consume `note` entries from the Phase 3 preference queue whose target is CLAUDE.local.md** (personal-level notes) — add each as a concise line. If the user chose personal-only in Phase 1, this is the sole consumer of note entries. + +Include: +- The user's role and familiarity with the codebase (so Claude can calibrate explanations) +- Personal sandbox URLs, test accounts, or local setup details +- Personal workflow or communication preferences + +Keep it short — only include what would make Claude's responses noticeably better for this user. + +If Phase 2 found multiple git worktrees and the user confirmed they use sibling/external worktrees (not nested inside the main repo): the upward file walk won't find a single CLAUDE.local.md from all worktrees. Write the actual personal content to `~/.claude/-instructions.md` and make CLAUDE.local.md a one-line stub that imports it: `@~/.claude/-instructions.md`. The user can copy this one-line stub to each sibling worktree. Never put this import in the project CLAUDE.md. If worktrees are nested inside the main repo (e.g., `.claude/worktrees/`), no special handling is needed — the main repo's CLAUDE.local.md is found automatically. + +If CLAUDE.local.md already exists: read it, propose specific additions, and do not silently overwrite. + +## Phase 6: Suggest and create skills (if the approved proposal includes any) + +Skills add capabilities Claude can use on demand without bloating every session. + +**First, consume `skill` entries from the Phase 3 preference queue.** Each queued skill preference becomes a SKILL.md tailored to what the user described. For each: +- Name it from the preference (e.g., "verify-deep", "session-report", "deploy-sandbox") +- Write the body using the user's own words from the interview plus whatever Phase 2 found (test commands, report format, deploy target). If the preference maps to an existing bundled skill (e.g., `/verify`), write a project skill that adds the user's specific constraints on top — tell the user the bundled one still exists and theirs is additive. +- Ask a quick follow-up if the preference is underspecified (e.g., "which test command should verify-deep run?") + +**Then suggest additional skills** beyond the queue when you find: +- Reference knowledge for specific tasks (conventions, patterns, style guides for a subsystem) +- Repeatable workflows the user would want to trigger directly (deploy, fix an issue, release process, verify changes) + +For each suggested skill, provide: name, one-line purpose, and why it fits this repo. + +If `.claude/skills/` already exists with skills, review them first. Do not overwrite existing skills — only propose new ones that complement what is already there. + +Create each skill at `.claude/skills//SKILL.md`: + +```yaml +--- +name: +description: +--- + + +``` + +Both the user (`/`) and Claude can invoke skills by default. For workflows with side effects (e.g., `/deploy`, `/fix-issue 123`), add `disable-model-invocation: true` so only the user can trigger it, and use `$ARGUMENTS` to accept input. + +## Phase 7: Suggest additional optimizations + +Tell the user you're going to suggest a few additional optimizations now that CLAUDE.md and skills (if chosen) are in place. + +Check the environment and ask about each gap you find (use AskUserQuestion): + +- **GitHub CLI**: Run `which gh` (or `where gh` on Windows). If it's missing AND the project uses GitHub (check `git remote -v` for github.com), ask the user if they want to install it. Explain that the GitHub CLI lets Claude help with commits, pull requests, issues, and code review directly. + +- **Linting**: If Phase 2 found no lint config (no .eslintrc, ruff.toml, .golangci.yml, etc. for the project's language), ask the user if they want Claude to set up linting for this codebase. Explain that linting catches issues early and gives Claude fast feedback on its own edits. + +- **Proposal-sourced hooks** (if the approved proposal includes any): Consume `hook` entries from the Phase 3 preference queue. If Phase 2 found a formatter and the queue has no formatting hook, offer format-on-edit as a fallback. + + For each hook preference (from the queue or the formatter fallback): + + 1. Target file: default based on the Phase 1 CLAUDE.md choice — project → `.claude/settings.json` (team-shared, committed); personal → `.claude/settings.local.json`. Only ask if the user chose "both" in Phase 1 or the preference is ambiguous. Ask once for all hooks, not per-hook. + + 2. Pick the event and matcher from the preference: + - "after every edit" → `PostToolUse` with matcher `Write|Edit` + - "when Claude finishes" / "before I review" → `Stop` event (fires at the end of every turn — including read-only ones) + - "before running bash" → `PreToolUse` with matcher `Bash` + - "before committing" (literal git-commit gate) → **not a hooks.json hook.** Matchers can't filter Bash by command content, so there's no way to target only `git commit`. Route this to a git pre-commit hook (`.git/hooks/pre-commit`, husky, pre-commit framework) instead — offer to write one. If the user actually means "before I review and commit Claude's output", that's `Stop` — probe to disambiguate. + Probe if the preference is ambiguous. + + 3. **Load the hook reference** (once per `/init` run, before the first hook): invoke the Skill tool with `skill: 'update-config'` and args starting with `[hooks-only]` followed by a one-line summary of what you're building — e.g., `[hooks-only] Constructing a PostToolUse/Write|Edit format hook for .claude/settings.json using ruff`. This loads the hooks schema and verification flow into context. Subsequent hooks reuse it — don't re-invoke. + + 4. Follow the skill's **"Constructing a Hook"** flow: dedup check → construct for THIS project → pipe-test raw → wrap → write JSON → `jq -e` validate → live-proof (for `Pre|PostToolUse` on triggerable matchers) → cleanup → handoff. Target file and event/matcher come from steps 1–2 above. + + Act on each "yes" before moving on. + +## Phase 8: Summary and next steps + +Recap what was set up — which files were written and the key points included in each. Remind the user these files are a starting point: they should review and tweak them, and can run `/init` again anytime to re-scan. + +Then tell the user that you'll be introducing a few more suggestions for optimizing their codebase and Claude Code setup based on what you found. Present these as a single, well-formatted to-do list where every item is relevant to this repo. Put the most impactful items first. + +When building the list, work through these checks and include only what applies: +- If frontend code was detected (React, Vue, Svelte, etc.): `/plugin install frontend-design@claude-plugins-official` gives Claude design principles and component patterns so it produces polished UI; `/plugin install playwright@claude-plugins-official` lets Claude launch a real browser, screenshot what it built, and fix visual bugs itself. +- If you found gaps in Phase 7 (missing GitHub CLI, missing linting) and the user said no: list them here with a one-line reason why each helps. +- If tests are missing or sparse: suggest setting up a test framework so Claude can verify its own changes. +- To help you create skills and optimize existing skills using evals, Claude Code has an official skill-creator plugin you can install. Install it with `/plugin install skill-creator@claude-plugins-official`, then run `/skill-creator ` to create new skills or refine any existing skill. (Always include this one.) +- Browse official plugins with `/plugin` — these bundle skills, agents, hooks, and MCP servers that you may find helpful. You can also create your own custom plugins to share them with others. (Always include this one.) diff --git a/Anthropic/Claude Code/bundled-skills/init.md b/Anthropic/Claude Code/bundled-skills/init.md index ff51524..20f86eb 100644 --- a/Anthropic/Claude Code/bundled-skills/init.md +++ b/Anthropic/Claude Code/bundled-skills/init.md @@ -1,228 +1,21 @@ ---- -name: init -description: Initialize a new CLAUDE.md file with codebase documentation. ---- +Please analyze this codebase and create a CLAUDE.md file, which will be given to future instances of Claude Code to operate in this repository. -Set up a minimal CLAUDE.md (and optionally skills and hooks) for this repo. CLAUDE.md is loaded into every Claude Code session, so it must be concise — only include what Claude would get wrong without it. +What to add: +1. Commands that will be commonly used, such as how to build, lint, and run tests. Include the necessary commands to develop in this codebase, such as how to run a single test. +2. High-level code architecture and structure so that future instances can be productive more quickly. Focus on the "big picture" architecture that requires reading multiple files to understand. -## Phase 0: Check for an existing CLAUDE.md - -Before asking anything, check if CLAUDE.md already exists at the project root (just `cat ./CLAUDE.md` — only the project-root file counts; don't explore the tree yet). This branches Phase 1. - -## Phase 1: Ask what to set up - -Use AskUserQuestion to find out what the user wants. Which question you ask depends on Phase 0. Call AskUserQuestion with **only Q1** — do NOT include Q2 in the same call. Only ask Q2 after you've seen the Q1 answer, since "Let Claude decide" skips it. - -Before the first question, print this primer as normal assistant text so first-time users know the terms: - -> Quick context: -> - **CLAUDE.md** files give Claude persistent instructions for a project, your personal workflow, or your organization. Claude reads them at the start of every session. -> - **Skills** are packaged instructions Claude invokes automatically when a task matches, or that you trigger with a slash command (e.g. `/frontend-design`, `/commit-push-pr`). -> - **Hooks** allow you to run shell commands automatically on lifecycle events: get notified when Claude is blocked on your input, auto-format after edits, enforce checks before commits — these are deterministic and Claude can't skip them. - -**If CLAUDE.md already exists**, ask: -- "I found an existing CLAUDE.md. What would you like to do?" - Options: "Review and improve it" | "Leave it, set up other things" | "Start fresh (replace it)" - Description for improve: "Explore what's changed in the codebase and propose targeted edits to the existing file." - Description for leave it: "Skip CLAUDE.md. Go straight to skills and hooks." - Description for start fresh: "Discard it and write new file(s)." - Routing: - - "Review and improve" → skip Q1/Q2; explore (Phase 2), ask the single Phase 3-lite question, then go to Phase 4's diff-proposal, then Phase 8. - - "Leave it" → skip Q1, ask Q2 (rename its fourth option to "Neither — skip setup"). If they pick "Neither — skip setup", jump straight to Phase 8 with: "Nothing to set up — your CLAUDE.md is unchanged." Otherwise: Phase 2 → Phase 3 proposal (no gap-fill interview) → Phases 6/7 per queue → Phase 8. For Phase 7's hook target-file default, treat this path as "project" (`.claude/settings.json`). - - "Start fresh" → continue to Q1 below as if no file existed. - -**If no CLAUDE.md exists** (or the user picked "Start fresh"), ask: -- Q1: "Which CLAUDE.md files should /init set up?" - Options: "Project CLAUDE.md" | "Personal CLAUDE.local.md" | "Both project + personal" | "Let Claude decide" - Description for project: "Team-shared instructions checked into source control — architecture, coding standards, common workflows." - Description for personal: "Your private preferences for this project (gitignored, not shared) — your role, sandbox URLs, preferred test data, workflow quirks." - Description for Let Claude decide: "Fastest path — project CLAUDE.md plus whatever skills or hooks fit this repo. No follow-on questions; you'll approve everything before it's written." - If the user picks "Let Claude decide", skip Q2 — treat it as project CLAUDE.md with no skills/hooks constraint. - -- Q2: "Also set up skills and hooks?" - Options: "Skills + hooks" | "Skills only" | "Hooks only" | "Neither, just CLAUDE.md" - Description for skills: "Packaged instructions Claude invokes automatically when a task matches, or that you trigger with a slash command (e.g. `/frontend-design`, `/commit-push-pr`)." - Description for hooks: "Deterministic shell commands that run on tool events (e.g., format after every edit). Claude can't skip them." - Q2 is a hint, not a filter — Phase 3 proposes what fits the codebase and notes any deviation. - -## Phase 2: Explore the codebase - -Launch a subagent to survey the codebase, and ask it to read key files to understand the project: manifest files (package.json, Cargo.toml, pyproject.toml, go.mod, pom.xml, etc.), README, Makefile/build configs, CI config, existing CLAUDE.md, .claude/rules/, AGENTS.md, .cursor/rules or .cursorrules, .github/copilot-instructions.md, .windsurfrules, .clinerules, .mcp.json. - -Detect: -- Build, test, and lint commands (especially non-standard ones) -- Languages, frameworks, and package manager -- Project structure (monorepo with workspaces, multi-module, or single project) -- Code style rules that differ from language defaults -- Non-obvious gotchas, required env vars, or workflow quirks -- Existing .claude/skills/ and .claude/rules/ directories -- Formatter configuration (prettier, biome, ruff, black, gofmt, rustfmt, or a unified format script like `npm run format` / `make fmt`) -- Git worktree usage: run `git worktree list` to check if this repo has multiple worktrees (only relevant if the user wants a personal CLAUDE.local.md) - -Note what you could NOT figure out from code alone — these become interview questions. - -## Phase 3: Fill in the gaps - -Use AskUserQuestion to gather what you still need to write good CLAUDE.md files and skills. Ask only things the code can't answer. - -If the user chose project CLAUDE.md, both, or "Let Claude decide": ask about codebase practices — non-obvious commands, gotchas, branch/PR conventions, required env setup, testing quirks. Skip things already in README or obvious from manifest files. Do not mark any options as "recommended" — this is about how their team works, not best practices. - -If the user chose personal CLAUDE.local.md or both: ask about them, not the codebase. Do not mark any options as "recommended" — this is about their personal preferences, not best practices. Examples of questions: - - What's their role on the team? (e.g., "backend engineer", "data scientist", "new hire onboarding") - - How familiar are they with this codebase and its languages/frameworks? (so Claude can calibrate explanation depth) - - Do they have personal sandbox URLs, test accounts, API key paths, or local setup details Claude should know? - - Only if Phase 2 found multiple git worktrees: ask whether their worktrees are nested inside the main repo (e.g., `.claude/worktrees//`) or siblings/external (e.g., `../myrepo-feature/`). If nested, the upward file walk finds the main repo's CLAUDE.local.md automatically — no special handling needed. If sibling/external, the personal content should live in a home-directory file (e.g., `~/.claude/-instructions.md`) and each worktree gets a one-line CLAUDE.local.md stub that imports it: `@~/.claude/-instructions.md`. Never put this import in the project CLAUDE.md — that would check a personal reference into the team-shared file. - - Any communication preferences? (e.g., "be terse", "always explain tradeoffs", "don't summarize at the end") - -If the user picked "Review and improve" in Phase 0: ask just one question — "Has anything changed about how the team works since this CLAUDE.md was written (new conventions, commands, gotchas)?" with options "No, nothing's changed" | "Yes — let me describe". If they pick Yes, ask what changed (free text) before continuing. Then skip to Phase 4. - -**Synthesize a proposal from Phase 2 findings and the gap-fill answers.** For each item, pick the artifact type that fits the evidence: - - - **Hook** — deterministic, fast, per-edit shell command (formatting, linting a changed file). - - **Skill** — on-demand multi-step workflow (`/verify`, `/deploy-staging`, session reports). - - **CLAUDE.md note** — guidance that shapes behavior but isn't enforced (conventions, communication style). - -Include the CLAUDE.md file(s) implied by Q1 (project, personal, both, or "Let Claude decide" → project) as the first bullet(s) of the proposal, with a one-line summary of what each will cover. Then list skills/hooks/notes. On the "Leave it" path, omit CLAUDE.md file bullets and notes (Phase 4 won't run). On the "Start fresh" path with Q1 = personal-only, add a bullet noting the existing project CLAUDE.md will be left untouched (they chose not to replace it with a project file). - -Propose what fits. If the user gave a Q2 hint and your proposal deviates from it (e.g. they said "Hooks only" but nothing hook-shaped exists), say so in one line at the top of the proposal and propose the better-fitting artifacts anyway. - -**Print the proposal as normal assistant text**, one bullet per item: - -> Here's what I'd set up: -> • **[Artifact type: file/hook/skill/note]** — [one-line description] -> • … - -Then call AskUserQuestion with a simple question ("Does this look right?") and options like "Looks good — proceed" | "Drop the hook" | "Drop the skill". Don't use the `preview` field — the proposal is already visible in scrollback. The tool auto-adds an "Other" option for custom tweaks. - -**Build the preference queue** from the accepted proposal. Each entry: {type: hook|skill|note, description, target file, any Phase-2-sourced details like the actual test/format command}. Phase 6 and Phase 7's hooks sub-bullet consume this queue; Phases 4/5 gate on the approved proposal's file bullets directly; Phase 7's GitHub-CLI and linting checks run regardless of queue contents. - -## Phase 4: Write CLAUDE.md (if the approved proposal includes it, or on the "Review and improve" path) - -Write a minimal CLAUDE.md at the project root. Every line must pass this test: "Would removing this cause Claude to make mistakes?" If no, cut it. - -If the user picked "Review and improve it" in Phase 0: don't write fresh — read the existing file, compare against Phase 2 findings and the Phase 3-lite answer, and propose specific additions/removals as diffs with a one-line reason for each. The existing file is the baseline; your job is to catch what's missing, outdated, or bloated. After printing the diffs, call AskUserQuestion ("Apply these edits?" with options like "Apply all" | "Let me pick which" | "Skip — leave it as is") before writing anything. - -**Consume `note` entries from the Phase 3 preference queue whose target is CLAUDE.md** (team-level notes) — add each as a concise line in the most relevant section. These are the behaviors the user wants Claude to follow but didn't need guaranteed (e.g., "propose a plan before implementing", "explain the tradeoffs when refactoring"). Leave personal-targeted notes for Phase 5. - -Include: -- Build/test/lint commands Claude can't guess (non-standard scripts, flags, or sequences) -- Code style rules that DIFFER from language defaults (e.g., "prefer type over interface") -- Testing instructions and quirks (e.g., "run single test with: pytest -k 'test_name'") -- Repo etiquette (branch naming, PR conventions, commit style) -- Required env vars or setup steps -- Non-obvious gotchas or architectural decisions -- Important parts from existing AI coding tool configs if they exist (AGENTS.md, .cursor/rules, .cursorrules, .github/copilot-instructions.md, .windsurfrules, .clinerules) - -Exclude: -- File-by-file structure or component lists (Claude can discover these by reading the codebase) -- Standard language conventions Claude already knows -- Generic advice ("write clean code", "handle errors") -- Detailed API docs or long references — use `@path/to/import` syntax instead (e.g., `@docs/api-reference.md`) to inline content on demand without bloating CLAUDE.md -- Information that changes frequently — reference the source with `@path/to/import` so Claude always reads the current version -- Long tutorials or walkthroughs (move to a separate file and reference with `@path/to/import`, or put in a skill) -- Commands obvious from manifest files (e.g., standard "npm test", "cargo test", "pytest") - -Be specific: "Use 2-space indentation in TypeScript" is better than "Format code properly." - -Do not repeat yourself and do not make up sections like "Common Development Tasks" or "Tips for Development" — only include information expressly found in files you read. - -Prefix the file with: +Usage notes: +- If there's already a CLAUDE.md, suggest improvements to it. +- When you make the initial CLAUDE.md, do not repeat yourself and do not include obvious instructions like "Provide helpful error messages to users", "Write unit tests for all new utilities", "Never include sensitive information (API keys, tokens) in code or commits". +- Avoid listing every component or file structure that can be easily discovered. +- Don't include generic development practices. +- If there are Cursor rules (in .cursor/rules/ or .cursorrules) or Copilot rules (in .github/copilot-instructions.md), make sure to include the important parts. +- If there is a README.md, make sure to include the important parts. +- Do not make up information such as "Common Development Tasks", "Tips for Development", "Support and Documentation" unless this is expressly included in other files that you read. +- Be sure to prefix the file with the following text: ``` # CLAUDE.md This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository. -``` - -For projects with multiple concerns, suggest organizing instructions into `.claude/rules/` as separate focused files (e.g., `code-style.md`, `testing.md`, `security.md`). These are loaded automatically alongside CLAUDE.md and can be scoped to specific file paths using `paths` frontmatter. - -For projects with distinct subdirectories (monorepos, multi-module projects, etc.): mention that subdirectory CLAUDE.md files can be added for module-specific instructions (they're loaded automatically when Claude works in those directories). Offer to create them if the user wants. - -## Phase 5: Write CLAUDE.local.md (if the approved proposal includes it) - -Write a minimal CLAUDE.local.md at the project root. This file is automatically loaded alongside CLAUDE.md. After creating it, add `CLAUDE.local.md` to the project's .gitignore so it stays private. - -**Consume `note` entries from the Phase 3 preference queue whose target is CLAUDE.local.md** (personal-level notes) — add each as a concise line. If the user chose personal-only in Phase 1, this is the sole consumer of note entries. - -Include: -- The user's role and familiarity with the codebase (so Claude can calibrate explanations) -- Personal sandbox URLs, test accounts, or local setup details -- Personal workflow or communication preferences - -Keep it short — only include what would make Claude's responses noticeably better for this user. - -If Phase 2 found multiple git worktrees and the user confirmed they use sibling/external worktrees (not nested inside the main repo): the upward file walk won't find a single CLAUDE.local.md from all worktrees. Write the actual personal content to `~/.claude/-instructions.md` and make CLAUDE.local.md a one-line stub that imports it: `@~/.claude/-instructions.md`. The user can copy this one-line stub to each sibling worktree. Never put this import in the project CLAUDE.md. If worktrees are nested inside the main repo (e.g., `.claude/worktrees/`), no special handling is needed — the main repo's CLAUDE.local.md is found automatically. - -If CLAUDE.local.md already exists: read it, propose specific additions, and do not silently overwrite. - -## Phase 6: Suggest and create skills (if the approved proposal includes any) - -Skills add capabilities Claude can use on demand without bloating every session. - -**First, consume `skill` entries from the Phase 3 preference queue.** Each queued skill preference becomes a SKILL.md tailored to what the user described. For each: -- Name it from the preference (e.g., "verify-deep", "session-report", "deploy-sandbox") -- Write the body using the user's own words from the interview plus whatever Phase 2 found (test commands, report format, deploy target). If the preference maps to an existing bundled skill (e.g., `/verify`), write a project skill that adds the user's specific constraints on top — tell the user the bundled one still exists and theirs is additive. -- Ask a quick follow-up if the preference is underspecified (e.g., "which test command should verify-deep run?") - -**Then suggest additional skills** beyond the queue when you find: -- Reference knowledge for specific tasks (conventions, patterns, style guides for a subsystem) -- Repeatable workflows the user would want to trigger directly (deploy, fix an issue, release process, verify changes) - -For each suggested skill, provide: name, one-line purpose, and why it fits this repo. - -If `.claude/skills/` already exists with skills, review them first. Do not overwrite existing skills — only propose new ones that complement what is already there. - -Create each skill at `.claude/skills//SKILL.md`: - -```yaml ---- -name: -description: ---- - - -``` - -Both the user (`/`) and Claude can invoke skills by default. For workflows with side effects (e.g., `/deploy`, `/fix-issue 123`), add `disable-model-invocation: true` so only the user can trigger it, and use `$ARGUMENTS` to accept input. - -## Phase 7: Suggest additional optimizations - -Tell the user you're going to suggest a few additional optimizations now that CLAUDE.md and skills (if chosen) are in place. - -Check the environment and ask about each gap you find (use AskUserQuestion): - -- **GitHub CLI**: Run `which gh` (or `where gh` on Windows). If it's missing AND the project uses GitHub (check `git remote -v` for github.com), ask the user if they want to install it. Explain that the GitHub CLI lets Claude help with commits, pull requests, issues, and code review directly. - -- **Linting**: If Phase 2 found no lint config (no .eslintrc, ruff.toml, .golangci.yml, etc. for the project's language), ask the user if they want Claude to set up linting for this codebase. Explain that linting catches issues early and gives Claude fast feedback on its own edits. - -- **Proposal-sourced hooks** (if the approved proposal includes any): Consume `hook` entries from the Phase 3 preference queue. If Phase 2 found a formatter and the queue has no formatting hook, offer format-on-edit as a fallback. - - For each hook preference (from the queue or the formatter fallback): - - 1. Target file: default based on the Phase 1 CLAUDE.md choice — project → `.claude/settings.json` (team-shared, committed); personal → `.claude/settings.local.json`. Only ask if the user chose "both" in Phase 1 or the preference is ambiguous. Ask once for all hooks, not per-hook. - - 2. Pick the event and matcher from the preference: - - "after every edit" → `PostToolUse` with matcher `Write|Edit` - - "when Claude finishes" / "before I review" → `Stop` event (fires at the end of every turn — including read-only ones) - - "before running bash" → `PreToolUse` with matcher `Bash` - - "before committing" (literal git-commit gate) → **not a hooks.json hook.** Matchers can't filter Bash by command content, so there's no way to target only `git commit`. Route this to a git pre-commit hook (`.git/hooks/pre-commit`, husky, pre-commit framework) instead — offer to write one. If the user actually means "before I review and commit Claude's output", that's `Stop` — probe to disambiguate. - Probe if the preference is ambiguous. - - 3. **Load the hook reference** (once per `/init` run, before the first hook): invoke the Skill tool with `skill: 'update-config'` and args starting with `[hooks-only]` followed by a one-line summary of what you're building — e.g., `[hooks-only] Constructing a PostToolUse/Write|Edit format hook for .claude/settings.json using ruff`. This loads the hooks schema and verification flow into context. Subsequent hooks reuse it — don't re-invoke. - - 4. Follow the skill's **"Constructing a Hook"** flow: dedup check → construct for THIS project → pipe-test raw → wrap → write JSON → `jq -e` validate → live-proof (for `Pre|PostToolUse` on triggerable matchers) → cleanup → handoff. Target file and event/matcher come from steps 1–2 above. - - Act on each "yes" before moving on. - -## Phase 8: Summary and next steps - -Recap what was set up — which files were written and the key points included in each. Remind the user these files are a starting point: they should review and tweak them, and can run `/init` again anytime to re-scan. - -Then tell the user that you'll be introducing a few more suggestions for optimizing their codebase and Claude Code setup based on what you found. Present these as a single, well-formatted to-do list where every item is relevant to this repo. Put the most impactful items first. - -When building the list, work through these checks and include only what applies: -- If frontend code was detected (React, Vue, Svelte, etc.): `/plugin install frontend-design@claude-plugins-official` gives Claude design principles and component patterns so it produces polished UI; `/plugin install playwright@claude-plugins-official` lets Claude launch a real browser, screenshot what it built, and fix visual bugs itself. -- If you found gaps in Phase 7 (missing GitHub CLI, missing linting) and the user said no: list them here with a one-line reason why each helps. -- If tests are missing or sparse: suggest setting up a test framework so Claude can verify its own changes. -- To help you create skills and optimize existing skills using evals, Claude Code has an official skill-creator plugin you can install. Install it with `/plugin install skill-creator@claude-plugins-official`, then run `/skill-creator ` to create new skills or refine any existing skill. (Always include this one.) -- Browse official plugins with `/plugin` — these bundle skills, agents, hooks, and MCP servers that you may find helpful. You can also create your own custom plugins to share them with others. (Always include this one.) +``` \ No newline at end of file diff --git a/Anthropic/Claude Code/bundled-skills/update-config-schema.json b/Anthropic/Claude Code/bundled-skills/update-config-schema.json deleted file mode 100644 index 9246a12..0000000 --- a/Anthropic/Claude Code/bundled-skills/update-config-schema.json +++ /dev/null @@ -1,3057 +0,0 @@ -{ - "$schema": "https://json-schema.org/draft/2020-12/schema", - "type": "object", - "properties": { - "$schema": { - "description": "JSON Schema reference for Claude Code settings", - "type": "string" - }, - "apiKeyHelper": { - "description": "Path to a script that outputs authentication values", - "type": "string" - }, - "proxyAuthHelper": { - "description": "Shell command that outputs a Proxy-Authorization header value (EAP)", - "type": "string" - }, - "awsCredentialExport": { - "description": "Path to a script that exports AWS credentials", - "type": "string" - }, - "awsAuthRefresh": { - "description": "Path to a script that refreshes AWS authentication", - "type": "string" - }, - "gcpAuthRefresh": { - "description": "Command to refresh GCP authentication (e.g., gcloud auth application-default login)", - "type": "string" - }, - "policyHelper": { - "description": "Executable that computes managed settings at startup. Honored only from admin-controlled policy sources.", - "type": "object", - "properties": { - "path": { - "description": "Absolute path to the helper executable", - "type": "string" - }, - "timeoutMs": { - "type": "integer", - "minimum": 1000, - "maximum": 9007199254740991 - }, - "refreshIntervalMs": { - "anyOf": [ - { - "type": "number", - "const": 0 - }, - { - "type": "integer", - "minimum": 60000, - "maximum": 9007199254740991 - } - ] - } - }, - "required": [ - "path" - ], - "additionalProperties": false - }, - "fileSuggestion": { - "description": "Custom file suggestion configuration for @ mentions", - "type": "object", - "properties": { - "type": { - "type": "string", - "const": "command" - }, - "command": { - "type": "string" - } - }, - "required": [ - "type", - "command" - ], - "additionalProperties": false - }, - "respectGitignore": { - "description": "Whether file picker should respect .gitignore files (default: true). Note: .ignore files are always respected.", - "type": "boolean" - }, - "breakReminder": { - "description": "@internal Opt-in break reminder. When enabled, shows a dismissible nudge after sustained continuous use. Never blocks — just a friendly heads-up.", - "type": "object", - "properties": { - "enabled": { - "description": "Show a friendly nudge after sustained continuous use (default false). Must be true for the reminder to fire.", - "type": "boolean" - }, - "intervalMinutes": { - "description": "Minutes of continuous use before the reminder fires (default 120). Re-fires every interval until you take a break.", - "type": "integer", - "exclusiveMinimum": 0, - "maximum": 9007199254740991 - }, - "breakThresholdMinutes": { - "description": "Minutes of inactivity that count as a break and reset the timer (default 15)", - "type": "integer", - "exclusiveMinimum": 0, - "maximum": 9007199254740991 - }, - "message": { - "description": "Custom reminder text. Leave unset for a rotating set of friendly nudges.", - "type": "string" - } - }, - "additionalProperties": false - }, - "quietHours": { - "description": "@internal Opt-in quiet hours. When enabled, shows a single soft nudge per session while inside the configured local-time window. Never blocks.", - "type": "object", - "properties": { - "enabled": { - "description": "Show a one-time nudge when you start or keep using the CLI inside your quiet-hours window (default false).", - "type": "boolean" - }, - "start": { - "description": "Start of the quiet-hours window, 24-hour local time \"HH:MM\".", - "type": "string", - "pattern": "^([01]?\\d|2[0-3]):[0-5]\\d$" - }, - "end": { - "description": "End of the quiet-hours window, 24-hour local time \"HH:MM\". May be earlier than start for an overnight range.", - "type": "string", - "pattern": "^([01]?\\d|2[0-3]):[0-5]\\d$" - } - }, - "additionalProperties": false - }, - "cleanupPeriodDays": { - "description": "Number of days to retain chat transcripts before automatic cleanup (default: 30). Minimum 1. Use a large value for long retention; use --no-session-persistence to disable transcript writes entirely.", - "type": "integer", - "exclusiveMinimum": 0, - "maximum": 9007199254740991 - }, - "skillListingMaxDescChars": { - "description": "Per-skill description character cap in the skill listing sent to Claude (default: 1536). Descriptions longer than this are truncated. Raise to opt in to higher per-turn context cost.", - "type": "integer", - "exclusiveMinimum": 0, - "maximum": 9007199254740991 - }, - "skillListingBudgetFraction": { - "description": "Fraction of the context window (in characters) reserved for the skill listing sent to Claude (default: 0.01 = 1%). When the listing exceeds this, descriptions are shortened to fit. Raise to opt in to higher per-turn context cost.", - "type": "number", - "exclusiveMinimum": 0, - "maximum": 1 - }, - "wslInheritsWindowsSettings": { - "description": "When set to true in either admin-only Windows source — the HKLM SOFTWARE/Policies/ClaudeCode registry key or C:/Program Files/ClaudeCode/managed-settings.json — WSL reads managed settings from the full Windows policy chain (HKLM, C:/Program Files/ClaudeCode via DrvFs, HKCU) in addition to /etc/claude-code. Windows sources take priority. The flag is also required in HKCU itself for HKCU policy to apply on WSL (double opt-in: admin enables the chain, user confirms HKCU). On native Windows the flag has no effect.", - "type": "boolean" - }, - "env": { - "description": "Environment variables to set for Claude Code sessions", - "type": "object", - "propertyNames": { - "type": "string" - }, - "additionalProperties": { - "type": "string" - } - }, - "attribution": { - "description": "Customize attribution text for commits and PRs. Each field defaults to the standard Claude Code attribution if not set.", - "type": "object", - "properties": { - "commit": { - "description": "Attribution text for git commits, including any trailers. Empty string hides attribution.", - "type": "string" - }, - "pr": { - "description": "Attribution text for pull request descriptions. Empty string hides attribution.", - "type": "string" - } - }, - "additionalProperties": false - }, - "includeCoAuthoredBy": { - "description": "Deprecated: Use attribution instead. Whether to include Claude's co-authored by attribution in commits and PRs (defaults to true)", - "type": "boolean" - }, - "includeGitInstructions": { - "description": "Include built-in commit and PR workflow instructions in Claude's system prompt (default: true)", - "type": "boolean" - }, - "permissions": { - "description": "Tool usage permissions configuration", - "type": "object", - "properties": { - "allow": { - "description": "List of permission rules for allowed operations", - "type": "array", - "items": { - "type": "string" - } - }, - "deny": { - "description": "List of permission rules for denied operations", - "type": "array", - "items": { - "type": "string" - } - }, - "ask": { - "description": "List of permission rules that should always prompt for confirmation", - "type": "array", - "items": { - "type": "string" - } - }, - "defaultMode": { - "description": "Default permission mode when Claude Code needs access", - "type": "string", - "enum": [ - "acceptEdits", - "auto", - "bypassPermissions", - "default", - "dontAsk", - "plan" - ] - }, - "disableBypassPermissionsMode": { - "description": "Disable the ability to bypass permission prompts", - "type": "string", - "enum": [ - "disable" - ] - }, - "disableAutoMode": { - "description": "Disable auto mode", - "type": "string", - "enum": [ - "disable" - ] - }, - "additionalDirectories": { - "description": "Additional directories to include in the permission scope", - "type": "array", - "items": { - "type": "string" - } - } - }, - "additionalProperties": {} - }, - "model": { - "description": "Override the default model used by Claude Code", - "type": "string" - }, - "fallbackModel": { - "description": "Fallback model(s) tried in order when the primary model is overloaded or unavailable. Each element accepts a model name or alias; \"default\" expands to the default model. CLI --fallback-model takes precedence.", - "type": "array", - "items": { - "type": "string" - } - }, - "availableModels": { - "description": "Allowlist of models that users can select. Accepts family aliases (\"opus\" allows any opus version), version prefixes (\"opus-4-5\" allows only that version), and full model IDs. If undefined, all models are available. If empty array, only the default model is available. Typically set in managed settings by enterprise administrators.", - "type": "array", - "items": { - "type": "string" - } - }, - "enforceAvailableModels": { - "description": "When true and availableModels is a non-empty array, the Default model selection is also constrained: if the default model for the user tier is not in availableModels, Default resolves to the first allowed availableModels entry instead. Has no effect when availableModels is unset or an empty array. Typically set in managed settings by enterprise administrators.", - "type": "boolean" - }, - "modelOverrides": { - "description": "Override mapping from Anthropic model ID (e.g. \"claude-opus-4-6\") to provider-specific model ID (e.g. a Bedrock inference profile ARN). Typically set in managed settings by enterprise administrators.", - "type": "object", - "propertyNames": { - "type": "string" - }, - "additionalProperties": { - "type": "string" - } - }, - "enableAllProjectMcpServers": { - "description": "Whether to automatically approve all MCP servers in the project", - "type": "boolean" - }, - "enabledMcpjsonServers": { - "description": "List of approved MCP servers from .mcp.json", - "type": "array", - "items": { - "type": "string" - } - }, - "disabledMcpjsonServers": { - "description": "List of rejected MCP servers from .mcp.json", - "type": "array", - "items": { - "type": "string" - } - }, - "skillOverrides": { - "description": "Per-skill listing overrides keyed by skill name. \"name-only\" lists the skill without its description; \"user-invocable-only\" hides it from the model but keeps /name; \"off\" hides it from both. Absent = on.", - "type": "object", - "propertyNames": { - "type": "string" - }, - "additionalProperties": { - "type": "string", - "enum": [ - "on", - "name-only", - "user-invocable-only", - "off" - ] - } - }, - "disableBundledSkills": { - "description": "Disable the skills and workflows that ship with Claude Code: bundled skills and workflows are removed entirely; built-in slash commands stay typable but are hidden from the model. Plugins, .claude/skills/, and .claude/commands/ are unaffected. Equivalent to CLAUDE_CODE_DISABLE_BUNDLED_SKILLS=1.", - "type": "boolean" - }, - "allowedMcpServers": { - "description": "Enterprise allowlist of MCP servers that can be used. Applies to all scopes including enterprise servers from managed-mcp.json. If undefined, all servers are allowed. If empty array, no servers are allowed. Denylist takes precedence - if a server is on both lists, it is denied.", - "type": "array", - "items": { - "type": "object", - "properties": { - "serverName": { - "description": "Name of the MCP server that users are allowed to configure", - "type": "string", - "pattern": "^[a-zA-Z0-9_-]+$" - }, - "serverCommand": { - "description": "Command array [command, ...args] to match exactly for allowed stdio servers", - "minItems": 1, - "type": "array", - "items": { - "type": "string" - } - }, - "serverUrl": { - "description": "URL pattern with wildcard support (e.g., \"https://*.example.com/*\") for allowed remote MCP servers", - "type": "string" - } - }, - "additionalProperties": false - } - }, - "deniedMcpServers": { - "description": "Enterprise denylist of MCP servers that are explicitly blocked. If a server is on the denylist, it will be blocked across all scopes including enterprise. Denylist takes precedence over allowlist - if a server is on both lists, it is denied.", - "type": "array", - "items": { - "type": "object", - "properties": { - "serverName": { - "description": "Name of the MCP server that is explicitly blocked", - "type": "string", - "pattern": "^[a-zA-Z0-9_-]+$" - }, - "serverCommand": { - "description": "Command array [command, ...args] to match exactly for blocked stdio servers", - "minItems": 1, - "type": "array", - "items": { - "type": "string" - } - }, - "serverUrl": { - "description": "URL pattern with wildcard support (e.g., \"https://*.example.com/*\") for blocked remote MCP servers", - "type": "string" - } - }, - "additionalProperties": false - } - }, - "hooks": { - "description": "Custom commands to run before/after tool executions", - "type": "object", - "propertyNames": { - "anyOf": [ - { - "type": "string", - "enum": [ - "PreToolUse", - "PostToolUse", - "PostToolUseFailure", - "PostToolBatch", - "Notification", - "UserPromptSubmit", - "UserPromptExpansion", - "SessionStart", - "SessionEnd", - "Stop", - "StopFailure", - "SubagentStart", - "SubagentStop", - "PreCompact", - "PostCompact", - "PermissionRequest", - "PermissionDenied", - "Setup", - "TeammateIdle", - "TaskCreated", - "TaskCompleted", - "Elicitation", - "ElicitationResult", - "ConfigChange", - "WorktreeCreate", - "WorktreeRemove", - "InstructionsLoaded", - "CwdChanged", - "FileChanged", - "MessageDisplay" - ] - }, - { - "not": {} - } - ] - }, - "additionalProperties": { - "type": "array", - "items": { - "type": "object", - "properties": { - "matcher": { - "description": "String pattern to match (e.g. tool names like \"Write\")", - "type": "string" - }, - "hooks": { - "description": "List of hooks to execute when the matcher matches", - "type": "array", - "items": { - "anyOf": [ - { - "type": "object", - "properties": { - "type": { - "description": "Shell command hook type", - "type": "string", - "const": "command" - }, - "command": { - "description": "Shell command to execute", - "type": "string" - }, - "args": { - "description": "Argument list for exec form. When present, `command` is resolved as an executable and spawned directly with these arguments — no shell. Path placeholders like ${CLAUDE_PLUGIN_ROOT} are substituted per-element as plain strings, so paths with quotes, $, or backticks never reach a shell parser. When absent, `command` runs through a shell (bash on POSIX, PowerShell on Windows without Git Bash).", - "type": "array", - "items": { - "type": "string" - } - }, - "if": { - "description": "Permission rule syntax to filter when this hook runs (e.g., \"Bash(git *)\"). Only runs if the tool call matches the pattern. Avoids spawning hooks for non-matching commands.", - "type": "string" - }, - "shell": { - "description": "Shell interpreter. 'bash' uses your $SHELL (bash/zsh/sh); 'powershell' uses pwsh. Defaults to bash (powershell on Windows without Git Bash).", - "type": "string", - "enum": [ - "bash", - "powershell" - ] - }, - "timeout": { - "description": "Timeout in seconds for this specific command", - "type": "number", - "exclusiveMinimum": 0 - }, - "statusMessage": { - "description": "Custom status message to display in spinner while hook runs", - "type": "string" - }, - "once": { - "description": "If true, hook runs once and is removed after execution", - "type": "boolean" - }, - "async": { - "description": "If true, hook runs in background without blocking", - "type": "boolean" - }, - "asyncRewake": { - "description": "If true, hook runs in background and wakes the model on exit code 2 (blocking error). Implies async.", - "type": "boolean" - }, - "rewakeMessage": { - "description": "@internal Custom prefix for the system-reminder shown to the model when an asyncRewake hook exits with code 2. The hook output is appended after this prefix.", - "type": "string", - "minLength": 1 - }, - "rewakeSummary": { - "description": "@internal One-line summary shown to the user in the terminal when an asyncRewake hook exits with code 2. Defaults to \"Stop hook feedback\".", - "type": "string", - "minLength": 1 - } - }, - "required": [ - "type", - "command" - ], - "additionalProperties": false - }, - { - "type": "object", - "properties": { - "type": { - "description": "LLM prompt hook type", - "type": "string", - "const": "prompt" - }, - "prompt": { - "description": "Prompt to evaluate with LLM. Use $ARGUMENTS placeholder for hook input JSON.", - "type": "string" - }, - "if": { - "description": "Permission rule syntax to filter when this hook runs (e.g., \"Bash(git *)\"). Only runs if the tool call matches the pattern. Avoids spawning hooks for non-matching commands.", - "type": "string" - }, - "timeout": { - "description": "Timeout in seconds for this specific prompt evaluation", - "type": "number", - "exclusiveMinimum": 0 - }, - "model": { - "description": "Model to use for this prompt hook (e.g., \"claude-sonnet-4-6\"). If not specified, uses the default small fast model.", - "type": "string" - }, - "continueOnBlock": { - "description": "Sets the continue value for the decision:\"block\" produced when ok is false. Default false (turn ends). Whether continue:true lets the turn proceed depends on the event's decision:\"block\" semantics. On PostToolUse, the reason is fed back to Claude and the turn continues.", - "type": "boolean" - }, - "statusMessage": { - "description": "Custom status message to display in spinner while hook runs", - "type": "string" - }, - "once": { - "description": "If true, hook runs once and is removed after execution", - "type": "boolean" - } - }, - "required": [ - "type", - "prompt" - ], - "additionalProperties": false - }, - { - "type": "object", - "properties": { - "type": { - "description": "Agentic verifier hook type", - "type": "string", - "const": "agent" - }, - "prompt": { - "description": "Prompt describing what to verify (e.g. \"Verify that unit tests ran and passed.\"). Use $ARGUMENTS placeholder for hook input JSON.", - "type": "string" - }, - "if": { - "description": "Permission rule syntax to filter when this hook runs (e.g., \"Bash(git *)\"). Only runs if the tool call matches the pattern. Avoids spawning hooks for non-matching commands.", - "type": "string" - }, - "timeout": { - "description": "Timeout in seconds for agent execution (default 60)", - "type": "number", - "exclusiveMinimum": 0 - }, - "model": { - "description": "Model to use for this agent hook (e.g., \"claude-sonnet-4-6\"). If not specified, uses Haiku.", - "type": "string" - }, - "statusMessage": { - "description": "Custom status message to display in spinner while hook runs", - "type": "string" - }, - "once": { - "description": "If true, hook runs once and is removed after execution", - "type": "boolean" - } - }, - "required": [ - "type", - "prompt" - ], - "additionalProperties": false - }, - { - "type": "object", - "properties": { - "type": { - "description": "HTTP hook type", - "type": "string", - "const": "http" - }, - "url": { - "description": "URL to POST the hook input JSON to", - "type": "string", - "format": "uri" - }, - "if": { - "description": "Permission rule syntax to filter when this hook runs (e.g., \"Bash(git *)\"). Only runs if the tool call matches the pattern. Avoids spawning hooks for non-matching commands.", - "type": "string" - }, - "timeout": { - "description": "Timeout in seconds for this specific request", - "type": "number", - "exclusiveMinimum": 0 - }, - "headers": { - "description": "Additional headers to include in the request. Values may reference environment variables using $VAR_NAME or ${VAR_NAME} syntax (e.g., \"Authorization\": \"Bearer $MY_TOKEN\"). Only variables listed in allowedEnvVars will be interpolated.", - "type": "object", - "propertyNames": { - "type": "string" - }, - "additionalProperties": { - "type": "string" - } - }, - "allowedEnvVars": { - "description": "Explicit list of environment variable names that may be interpolated in header values. Only variables listed here will be resolved; all other $VAR references are left as empty strings. Required for env var interpolation to work.", - "type": "array", - "items": { - "type": "string" - } - }, - "statusMessage": { - "description": "Custom status message to display in spinner while hook runs", - "type": "string" - }, - "once": { - "description": "If true, hook runs once and is removed after execution", - "type": "boolean" - } - }, - "required": [ - "type", - "url" - ], - "additionalProperties": false - }, - { - "type": "object", - "properties": { - "type": { - "description": "MCP tool hook type", - "type": "string", - "const": "mcp_tool" - }, - "server": { - "description": "Name of an already-configured MCP server to invoke", - "type": "string" - }, - "tool": { - "description": "Name of the tool on that server to call", - "type": "string" - }, - "input": { - "description": "Arguments passed to the MCP tool. String values support ${path} interpolation from the hook input JSON (e.g. \"${tool_input.file_path}\").", - "type": "object", - "propertyNames": { - "type": "string" - }, - "additionalProperties": {} - }, - "if": { - "description": "Permission rule syntax to filter when this hook runs (e.g., \"Bash(git *)\"). Only runs if the tool call matches the pattern. Avoids spawning hooks for non-matching commands.", - "type": "string" - }, - "timeout": { - "description": "Timeout in seconds for this specific tool call", - "type": "number", - "exclusiveMinimum": 0 - }, - "statusMessage": { - "description": "Custom status message to display in spinner while hook runs", - "type": "string" - }, - "once": { - "description": "If true, hook runs once and is removed after execution", - "type": "boolean" - } - }, - "required": [ - "type", - "server", - "tool" - ], - "additionalProperties": false - } - ] - } - } - }, - "required": [ - "hooks" - ], - "additionalProperties": false - } - } - }, - "worktree": { - "description": "Git worktree configuration for --worktree flag.", - "type": "object", - "properties": { - "symlinkDirectories": { - "description": "Directories to symlink from main repository to worktrees to avoid disk bloat. Must be explicitly configured - no directories are symlinked by default. Common examples: \"node_modules\", \".cache\", \".bin\"", - "type": "array", - "items": { - "type": "string" - } - }, - "sparsePaths": { - "description": "Directories to include when creating worktrees, via git sparse-checkout (cone mode). Dramatically faster in large monorepos — only the listed paths are written to disk.", - "type": "array", - "items": { - "type": "string" - } - }, - "baseRef": { - "description": "Which ref new worktrees branch from. 'fresh' (default) branches from origin/ for a clean tree. 'head' branches from your current local HEAD so unpushed commits and feature-branch state are present. Applies to --worktree, EnterWorktree, and agent isolation.", - "type": "string", - "enum": [ - "fresh", - "head" - ] - }, - "bgIsolation": { - "description": "Isolation mode for background sessions in this repo. 'worktree' (default) blocks Edit/Write in the main checkout until EnterWorktree is called. 'none' lets background jobs edit the working copy directly.", - "type": "string", - "enum": [ - "worktree", - "none" - ] - } - }, - "additionalProperties": false - }, - "disableAllHooks": { - "description": "Disable all hooks and statusLine execution", - "type": "boolean" - }, - "disableAgentView": { - "description": "Disable agent view (`claude agents`, `--bg`, /background, the on-demand daemon). Typically set in managed settings. Equivalent to CLAUDE_CODE_DISABLE_AGENT_VIEW=1.", - "type": "boolean" - }, - "disableRemoteControl": { - "description": "Disable Remote Control (claude.ai/code, `claude remote-control`, `--remote-control`/`--rc`, auto-start, and the in-session toggle). Typically set in managed settings.", - "type": "boolean" - }, - "disableWorkflows": { - "description": "Disable the Workflows feature (also via CLAUDE_CODE_DISABLE_WORKFLOWS).", - "type": "boolean" - }, - "disableArtifact": { - "description": "Disable the Artifact tool (also via CLAUDE_CODE_DISABLE_ARTIFACT).", - "type": "boolean" - }, - "enableWorkflows": { - "description": "Enable or disable the Workflows feature for this user. Unset = default by plan once the feature is available.", - "type": "boolean" - }, - "workflowKeywordTriggerEnabled": { - "description": "Enable the \"ultracode\" keyword trigger: including the keyword in a prompt opts that turn into the Workflow tool. Set to false to disable the trigger. Default: true.", - "type": "boolean" - }, - "disableSkillShellExecution": { - "description": "Disable inline shell execution in skills and custom slash commands from user, project, or plugin sources. Commands are replaced with a placeholder instead of being run.", - "type": "boolean" - }, - "defaultShell": { - "description": "Default shell for input-box ! commands. Defaults to 'bash' on all platforms (no Windows auto-flip).", - "type": "string", - "enum": [ - "bash", - "powershell" - ] - }, - "allowManagedHooksOnly": { - "description": "When true (and set in managed settings), only hooks from managed settings run. User, project, and local hooks are ignored.", - "type": "boolean" - }, - "allowedHttpHookUrls": { - "description": "Allowlist of URL patterns that HTTP hooks may target. Supports * as a wildcard (e.g. \"https://hooks.example.com/*\"). When set, HTTP hooks with non-matching URLs are blocked. If undefined, all URLs are allowed. If empty array, no HTTP hooks are allowed. Arrays merge across settings sources (same semantics as allowedMcpServers).", - "type": "array", - "items": { - "type": "string" - } - }, - "httpHookAllowedEnvVars": { - "description": "Allowlist of environment variable names HTTP hooks may interpolate into headers. When set, each hook's effective allowedEnvVars is the intersection with this list. If undefined, no restriction is applied. Arrays merge across settings sources (same semantics as allowedMcpServers).", - "type": "array", - "items": { - "type": "string" - } - }, - "allowManagedPermissionRulesOnly": { - "description": "When true (and set in managed settings), only permission rules (allow/deny/ask) from managed settings are respected. User, project, local, and CLI argument permission rules are ignored.", - "type": "boolean" - }, - "allowManagedMcpServersOnly": { - "description": "When true (and set in managed settings), allowedMcpServers is only read from managed settings. deniedMcpServers still merges from all sources, so users can deny servers for themselves. Users can still add their own MCP servers, but only the admin-defined allowlist applies.", - "type": "boolean" - }, - "allowAllClaudeAiMcps": { - "description": "When true (and set in managed settings), claude.ai cloud MCP connectors load alongside managed-mcp.json instead of being suppressed by its exclusive-control lockdown. Default off preserves the lockdown. Read from managed settings only.", - "type": "boolean" - }, - "strictPluginOnlyCustomization": { - "description": "When set in managed settings, blocks non-plugin customization sources for the listed surfaces. Array form locks specific surfaces (e.g. [\"skills\", \"hooks\"]); `true` locks all four; `false` is an explicit no-op. Blocked: ~/.claude/{surface}/, .claude/{surface}/ (project), settings.json hooks, .mcp.json. NOT blocked: managed (policySettings) sources, plugin-provided customizations. Composes with strictKnownMarketplaces for end-to-end admin control — plugins gated by marketplace allowlist, everything else blocked here.", - "anyOf": [ - { - "type": "boolean" - }, - { - "type": "array", - "items": { - "type": "string", - "enum": [ - "skills", - "agents", - "hooks", - "mcp" - ] - } - } - ] - }, - "statusLine": { - "description": "Custom status line display configuration", - "type": "object", - "properties": { - "type": { - "type": "string", - "const": "command" - }, - "command": { - "type": "string" - }, - "padding": { - "type": "number" - }, - "refreshInterval": { - "description": "Re-run the status line command every N seconds in addition to event-driven updates", - "type": "number", - "minimum": 1 - }, - "hideVimModeIndicator": { - "description": "Hide the built-in `-- INSERT --` / `-- VISUAL --` indicator below the prompt. Use this when your status line script renders `vim.mode` itself.", - "type": "boolean" - } - }, - "required": [ - "type", - "command" - ], - "additionalProperties": false - }, - "prUrlTemplate": { - "description": "URL template for PR links in the footer link badges and inline messages. The detected git PR is rendered as the first footer-link badge. Placeholders: {host} {owner} {repo} {number} {url}. Example: \"https://reviews.example.com/{owner}/{repo}/pull/{number}\"", - "type": "string" - }, - "footerLinksRegexes": { - "description": "Extra clickable footer badges that appear when a regex matches turn output (tool results and assistant responses). Read from user, flag, and managed settings only; ignored in project .claude/settings.json and local .claude/settings.local.json. At most 5 badges render; the oldest is displaced by newer matches and /clear removes them. Use to surface IDs printed by project CLIs as session links." - }, - "subagentStatusLine": { - "description": "Custom per-subagent status line shown in the agent panel; receives row context as JSON on stdin", - "type": "object", - "properties": { - "type": { - "type": "string", - "const": "command" - }, - "command": { - "type": "string" - } - }, - "required": [ - "type", - "command" - ], - "additionalProperties": false - }, - "enabledPlugins": { - "description": "Enabled plugins using plugin-id@marketplace-id format. Example: { \"formatter@anthropic-tools\": true }. Also supports extended format with version constraints. Settings precedence is user < project < local < flag < policy, so to disable a plugin that project settings enable, set it to false in .claude/settings.local.json — setting false in ~/.claude/settings.json is overridden by the project.", - "type": "object", - "propertyNames": { - "type": "string" - }, - "additionalProperties": { - "anyOf": [ - { - "type": "array", - "items": { - "type": "string" - } - }, - { - "type": "boolean" - }, - { - "not": {} - } - ] - } - }, - "extraKnownMarketplaces": { - "description": "Additional marketplaces to make available for this repository. Typically used in repository .claude/settings.json to ensure team members have required plugin sources.", - "type": "object", - "propertyNames": { - "type": "string" - }, - "additionalProperties": { - "type": "object", - "properties": { - "source": { - "description": "Where to fetch the marketplace from", - "anyOf": [ - { - "type": "object", - "properties": { - "source": { - "type": "string", - "const": "url" - }, - "url": { - "description": "Direct URL to marketplace.json file", - "type": "string", - "format": "uri" - }, - "headers": { - "description": "Custom HTTP headers (e.g., for authentication)", - "type": "object", - "propertyNames": { - "type": "string" - }, - "additionalProperties": { - "type": "string" - } - } - }, - "required": [ - "source", - "url" - ], - "additionalProperties": false - }, - { - "type": "object", - "properties": { - "source": { - "type": "string", - "const": "github" - }, - "repo": { - "description": "GitHub repository in owner/repo format", - "type": "string" - }, - "ref": { - "description": "Git branch or tag to use (e.g., \"main\", \"v1.0.0\"). Defaults to repository default branch.", - "type": "string" - }, - "path": { - "description": "Path to marketplace.json within repo (defaults to .claude-plugin/marketplace.json)", - "type": "string" - }, - "sparsePaths": { - "description": "Directories to include via git sparse-checkout (cone mode). Use for monorepos where the marketplace lives in a subdirectory. Example: [\".claude-plugin\", \"plugins\"]. If omitted, the full repository is cloned.", - "type": "array", - "items": { - "type": "string" - } - }, - "skipLfs": { - "description": "Skip Git LFS smudge during clone and update (sets GIT_LFS_SKIP_SMUDGE=1) so LFS pointer files stay as pointers instead of downloading their content. Use for marketplaces hosted in repos with large LFS objects.", - "type": "boolean" - } - }, - "required": [ - "source", - "repo" - ], - "additionalProperties": false - }, - { - "type": "object", - "properties": { - "source": { - "type": "string", - "const": "git" - }, - "url": { - "description": "Full git repository URL", - "type": "string" - }, - "ref": { - "description": "Git branch or tag to use (e.g., \"main\", \"v1.0.0\"). Defaults to repository default branch.", - "type": "string" - }, - "path": { - "description": "Path to marketplace.json within repo (defaults to .claude-plugin/marketplace.json)", - "type": "string" - }, - "sparsePaths": { - "description": "Directories to include via git sparse-checkout (cone mode). Use for monorepos where the marketplace lives in a subdirectory. Example: [\".claude-plugin\", \"plugins\"]. If omitted, the full repository is cloned.", - "type": "array", - "items": { - "type": "string" - } - }, - "skipLfs": { - "description": "Skip Git LFS smudge during clone and update (sets GIT_LFS_SKIP_SMUDGE=1) so LFS pointer files stay as pointers instead of downloading their content. Use for marketplaces hosted in repos with large LFS objects.", - "type": "boolean" - } - }, - "required": [ - "source", - "url" - ], - "additionalProperties": false - }, - { - "type": "object", - "properties": { - "source": { - "type": "string", - "const": "npm" - }, - "package": { - "description": "NPM package containing marketplace.json", - "type": "string" - } - }, - "required": [ - "source", - "package" - ], - "additionalProperties": false - }, - { - "type": "object", - "properties": { - "source": { - "type": "string", - "const": "file" - }, - "path": { - "description": "Local file path to marketplace.json", - "type": "string" - } - }, - "required": [ - "source", - "path" - ], - "additionalProperties": false - }, - { - "type": "object", - "properties": { - "source": { - "type": "string", - "const": "directory" - }, - "path": { - "description": "Local directory containing .claude-plugin/marketplace.json", - "type": "string" - } - }, - "required": [ - "source", - "path" - ], - "additionalProperties": false - }, - { - "description": "Policy-list sentinel for the ~/.claude/skills/ auto-load (@skills-dir plugins). In strictKnownMarketplaces: opt the scan back IN (by default any allowlist blocks it). In blockedMarketplaces: turn the scan OFF without otherwise restricting marketplaces. Only meaningful in those two managed-settings lists (areLocalPluginDirsAllowedByPolicy); known_marketplaces.json / marketplace add etc. ignore it.", - "type": "object", - "properties": { - "source": { - "type": "string", - "const": "skills-dir" - } - }, - "required": [ - "source" - ], - "additionalProperties": false - }, - { - "type": "object", - "properties": { - "source": { - "type": "string", - "const": "hostPattern" - }, - "hostPattern": { - "description": "Regex pattern to match the host/domain extracted from any marketplace source type. For github sources, matches against \"github.com\". For git sources (SSH or HTTPS), extracts the hostname from the URL. Use in strictKnownMarketplaces to allow all marketplaces from a specific host (e.g., \"^github\\.mycompany\\.com$\").", - "type": "string" - } - }, - "required": [ - "source", - "hostPattern" - ], - "additionalProperties": false - }, - { - "type": "object", - "properties": { - "source": { - "type": "string", - "const": "pathPattern" - }, - "pathPattern": { - "description": "Regex pattern matched against the .path field of file and directory sources. Use in strictKnownMarketplaces to allow filesystem-based marketplaces alongside hostPattern restrictions for network sources. Use \".*\" to allow all filesystem paths, or a narrower pattern (e.g., \"^/opt/approved/\") to restrict to specific directories.", - "type": "string" - } - }, - "required": [ - "source", - "pathPattern" - ], - "additionalProperties": false - }, - { - "description": "Inline marketplace manifest defined directly in settings.json. The reconciler writes a synthetic marketplace.json to the cache; diffMarketplaces detects edits via isEqual on the stored source (the plugins array is inside this object, so edits surface as sourceChanged).", - "type": "object", - "properties": { - "source": { - "type": "string", - "const": "settings" - }, - "name": { - "description": "Marketplace name. Must match the extraKnownMarketplaces key (enforced); the synthetic manifest is written under this name. Same validation as PluginMarketplaceSchema plus reserved-name rejection — validateOfficialNameSource runs after the disk write, too late to clean up.", - "type": "string", - "minLength": 1 - }, - "plugins": { - "description": "Plugin entries declared inline in settings.json", - "type": "array", - "items": { - "type": "object", - "properties": { - "name": { - "description": "Plugin name as it appears in the target repository", - "type": "string", - "minLength": 1 - }, - "source": { - "description": "Where to fetch the plugin from. Must be a remote source — relative paths have no marketplace repository to resolve against.", - "anyOf": [ - { - "description": "Path to the plugin root, relative to the marketplace root (the directory containing .claude-plugin/, not .claude-plugin/ itself)", - "type": "string", - "pattern": "^\\.\\/.*" - }, - { - "description": "NPM package as plugin source", - "type": "object", - "properties": { - "source": { - "type": "string", - "const": "npm" - }, - "package": { - "description": "Package name (or url, or local path, or anything else that can be passed to `npm` as a package)", - "anyOf": [ - { - "type": "string" - }, - { - "type": "string" - } - ] - }, - "version": { - "description": "Specific version or version range (e.g., ^1.0.0, ~2.1.0)", - "type": "string" - }, - "registry": { - "description": "Custom NPM registry URL (defaults to using system default, likely npmjs.org)", - "type": "string", - "format": "uri" - } - }, - "required": [ - "source", - "package" - ], - "additionalProperties": false - }, - { - "type": "object", - "properties": { - "source": { - "type": "string", - "const": "url" - }, - "url": { - "description": "Full git repository URL (https:// or git@)", - "type": "string" - }, - "ref": { - "description": "Git branch or tag to use (e.g., \"main\", \"v1.0.0\"). Defaults to repository default branch.", - "type": "string" - }, - "sha": { - "description": "Specific commit SHA to use", - "type": "string", - "minLength": 40, - "maxLength": 40, - "pattern": "^[a-f0-9]{40}$" - } - }, - "required": [ - "source", - "url" - ], - "additionalProperties": false - }, - { - "type": "object", - "properties": { - "source": { - "type": "string", - "const": "github" - }, - "repo": { - "description": "GitHub repository in owner/repo format", - "type": "string" - }, - "ref": { - "description": "Git branch or tag to use (e.g., \"main\", \"v1.0.0\"). Defaults to repository default branch.", - "type": "string" - }, - "sha": { - "description": "Specific commit SHA to use", - "type": "string", - "minLength": 40, - "maxLength": 40, - "pattern": "^[a-f0-9]{40}$" - } - }, - "required": [ - "source", - "repo" - ], - "additionalProperties": false - }, - { - "description": "Plugin located in a subdirectory of a larger repository (monorepo). Only the specified subdirectory is materialized; the rest of the repo is not downloaded.", - "type": "object", - "properties": { - "source": { - "type": "string", - "const": "git-subdir" - }, - "url": { - "description": "Git repository: GitHub owner/repo shorthand, https://, or git@ URL", - "type": "string" - }, - "path": { - "description": "Subdirectory within the repo containing the plugin (e.g., \"tools/claude-plugin\"). Cloned sparsely using partial clone (--filter=tree:0) to minimize bandwidth for monorepos.", - "type": "string", - "minLength": 1 - }, - "ref": { - "description": "Git branch or tag to use (e.g., \"main\", \"v1.0.0\"). Defaults to repository default branch.", - "type": "string" - }, - "sha": { - "description": "Specific commit SHA to use", - "type": "string", - "minLength": 40, - "maxLength": 40, - "pattern": "^[a-f0-9]{40}$" - } - }, - "required": [ - "source", - "url", - "path" - ], - "additionalProperties": false - }, - { - "description": "Placeholder for source types this Claude Code version does not recognize. Never authored by hand — PluginMarketplaceSchema rewrites unparseable sources to this so the entry remains in marketplace.plugins (detectDelistedPlugins must not see it as removed). Install attempts fail at cachePlugin with a clear \"update Claude Code\" message.", - "type": "object", - "properties": { - "source": { - "type": "string", - "const": "unsupported" - } - }, - "required": [ - "source" - ], - "additionalProperties": false - } - ] - }, - "description": { - "type": "string" - }, - "version": { - "type": "string" - }, - "strict": { - "type": "boolean" - } - }, - "required": [ - "name", - "source" - ], - "additionalProperties": false - } - }, - "owner": { - "type": "object", - "properties": { - "name": { - "description": "Display name of the plugin author or organization", - "type": "string", - "minLength": 1 - }, - "email": { - "description": "Contact email for support or feedback", - "type": "string" - }, - "url": { - "description": "Website, GitHub profile, or organization URL", - "type": "string" - } - }, - "required": [ - "name" - ], - "additionalProperties": false - } - }, - "required": [ - "source", - "name", - "plugins" - ], - "additionalProperties": false - } - ] - }, - "installLocation": { - "description": "Local cache path where marketplace manifest is stored (auto-generated if not provided)", - "type": "string" - }, - "autoUpdate": { - "description": "Whether to automatically update this marketplace and its installed plugins on startup", - "type": "boolean" - } - }, - "required": [ - "source" - ], - "additionalProperties": false - } - }, - "strictKnownMarketplaces": { - "description": "Enterprise strict list of allowed marketplace sources. When set in managed settings, ONLY these exact sources can be added as marketplaces. The check happens BEFORE downloading, so blocked sources never touch the filesystem. Note: this is a policy gate only — it does NOT register marketplaces. To pre-register allowed marketplaces for users, also set extraKnownMarketplaces.", - "type": "array", - "items": { - "anyOf": [ - { - "type": "object", - "properties": { - "source": { - "type": "string", - "const": "url" - }, - "url": { - "description": "Direct URL to marketplace.json file", - "type": "string", - "format": "uri" - }, - "headers": { - "description": "Custom HTTP headers (e.g., for authentication)", - "type": "object", - "propertyNames": { - "type": "string" - }, - "additionalProperties": { - "type": "string" - } - } - }, - "required": [ - "source", - "url" - ], - "additionalProperties": false - }, - { - "type": "object", - "properties": { - "source": { - "type": "string", - "const": "github" - }, - "repo": { - "description": "GitHub repository in owner/repo format", - "type": "string" - }, - "ref": { - "description": "Git branch or tag to use (e.g., \"main\", \"v1.0.0\"). Defaults to repository default branch.", - "type": "string" - }, - "path": { - "description": "Path to marketplace.json within repo (defaults to .claude-plugin/marketplace.json)", - "type": "string" - }, - "sparsePaths": { - "description": "Directories to include via git sparse-checkout (cone mode). Use for monorepos where the marketplace lives in a subdirectory. Example: [\".claude-plugin\", \"plugins\"]. If omitted, the full repository is cloned.", - "type": "array", - "items": { - "type": "string" - } - }, - "skipLfs": { - "description": "Skip Git LFS smudge during clone and update (sets GIT_LFS_SKIP_SMUDGE=1) so LFS pointer files stay as pointers instead of downloading their content. Use for marketplaces hosted in repos with large LFS objects.", - "type": "boolean" - } - }, - "required": [ - "source", - "repo" - ], - "additionalProperties": false - }, - { - "type": "object", - "properties": { - "source": { - "type": "string", - "const": "git" - }, - "url": { - "description": "Full git repository URL", - "type": "string" - }, - "ref": { - "description": "Git branch or tag to use (e.g., \"main\", \"v1.0.0\"). Defaults to repository default branch.", - "type": "string" - }, - "path": { - "description": "Path to marketplace.json within repo (defaults to .claude-plugin/marketplace.json)", - "type": "string" - }, - "sparsePaths": { - "description": "Directories to include via git sparse-checkout (cone mode). Use for monorepos where the marketplace lives in a subdirectory. Example: [\".claude-plugin\", \"plugins\"]. If omitted, the full repository is cloned.", - "type": "array", - "items": { - "type": "string" - } - }, - "skipLfs": { - "description": "Skip Git LFS smudge during clone and update (sets GIT_LFS_SKIP_SMUDGE=1) so LFS pointer files stay as pointers instead of downloading their content. Use for marketplaces hosted in repos with large LFS objects.", - "type": "boolean" - } - }, - "required": [ - "source", - "url" - ], - "additionalProperties": false - }, - { - "type": "object", - "properties": { - "source": { - "type": "string", - "const": "npm" - }, - "package": { - "description": "NPM package containing marketplace.json", - "type": "string" - } - }, - "required": [ - "source", - "package" - ], - "additionalProperties": false - }, - { - "type": "object", - "properties": { - "source": { - "type": "string", - "const": "file" - }, - "path": { - "description": "Local file path to marketplace.json", - "type": "string" - } - }, - "required": [ - "source", - "path" - ], - "additionalProperties": false - }, - { - "type": "object", - "properties": { - "source": { - "type": "string", - "const": "directory" - }, - "path": { - "description": "Local directory containing .claude-plugin/marketplace.json", - "type": "string" - } - }, - "required": [ - "source", - "path" - ], - "additionalProperties": false - }, - { - "description": "Policy-list sentinel for the ~/.claude/skills/ auto-load (@skills-dir plugins). In strictKnownMarketplaces: opt the scan back IN (by default any allowlist blocks it). In blockedMarketplaces: turn the scan OFF without otherwise restricting marketplaces. Only meaningful in those two managed-settings lists (areLocalPluginDirsAllowedByPolicy); known_marketplaces.json / marketplace add etc. ignore it.", - "type": "object", - "properties": { - "source": { - "type": "string", - "const": "skills-dir" - } - }, - "required": [ - "source" - ], - "additionalProperties": false - }, - { - "type": "object", - "properties": { - "source": { - "type": "string", - "const": "hostPattern" - }, - "hostPattern": { - "description": "Regex pattern to match the host/domain extracted from any marketplace source type. For github sources, matches against \"github.com\". For git sources (SSH or HTTPS), extracts the hostname from the URL. Use in strictKnownMarketplaces to allow all marketplaces from a specific host (e.g., \"^github\\.mycompany\\.com$\").", - "type": "string" - } - }, - "required": [ - "source", - "hostPattern" - ], - "additionalProperties": false - }, - { - "type": "object", - "properties": { - "source": { - "type": "string", - "const": "pathPattern" - }, - "pathPattern": { - "description": "Regex pattern matched against the .path field of file and directory sources. Use in strictKnownMarketplaces to allow filesystem-based marketplaces alongside hostPattern restrictions for network sources. Use \".*\" to allow all filesystem paths, or a narrower pattern (e.g., \"^/opt/approved/\") to restrict to specific directories.", - "type": "string" - } - }, - "required": [ - "source", - "pathPattern" - ], - "additionalProperties": false - }, - { - "description": "Inline marketplace manifest defined directly in settings.json. The reconciler writes a synthetic marketplace.json to the cache; diffMarketplaces detects edits via isEqual on the stored source (the plugins array is inside this object, so edits surface as sourceChanged).", - "type": "object", - "properties": { - "source": { - "type": "string", - "const": "settings" - }, - "name": { - "description": "Marketplace name. Must match the extraKnownMarketplaces key (enforced); the synthetic manifest is written under this name. Same validation as PluginMarketplaceSchema plus reserved-name rejection — validateOfficialNameSource runs after the disk write, too late to clean up.", - "type": "string", - "minLength": 1 - }, - "plugins": { - "description": "Plugin entries declared inline in settings.json", - "type": "array", - "items": { - "type": "object", - "properties": { - "name": { - "description": "Plugin name as it appears in the target repository", - "type": "string", - "minLength": 1 - }, - "source": { - "description": "Where to fetch the plugin from. Must be a remote source — relative paths have no marketplace repository to resolve against.", - "anyOf": [ - { - "description": "Path to the plugin root, relative to the marketplace root (the directory containing .claude-plugin/, not .claude-plugin/ itself)", - "type": "string", - "pattern": "^\\.\\/.*" - }, - { - "description": "NPM package as plugin source", - "type": "object", - "properties": { - "source": { - "type": "string", - "const": "npm" - }, - "package": { - "description": "Package name (or url, or local path, or anything else that can be passed to `npm` as a package)", - "anyOf": [ - { - "type": "string" - }, - { - "type": "string" - } - ] - }, - "version": { - "description": "Specific version or version range (e.g., ^1.0.0, ~2.1.0)", - "type": "string" - }, - "registry": { - "description": "Custom NPM registry URL (defaults to using system default, likely npmjs.org)", - "type": "string", - "format": "uri" - } - }, - "required": [ - "source", - "package" - ], - "additionalProperties": false - }, - { - "type": "object", - "properties": { - "source": { - "type": "string", - "const": "url" - }, - "url": { - "description": "Full git repository URL (https:// or git@)", - "type": "string" - }, - "ref": { - "description": "Git branch or tag to use (e.g., \"main\", \"v1.0.0\"). Defaults to repository default branch.", - "type": "string" - }, - "sha": { - "description": "Specific commit SHA to use", - "type": "string", - "minLength": 40, - "maxLength": 40, - "pattern": "^[a-f0-9]{40}$" - } - }, - "required": [ - "source", - "url" - ], - "additionalProperties": false - }, - { - "type": "object", - "properties": { - "source": { - "type": "string", - "const": "github" - }, - "repo": { - "description": "GitHub repository in owner/repo format", - "type": "string" - }, - "ref": { - "description": "Git branch or tag to use (e.g., \"main\", \"v1.0.0\"). Defaults to repository default branch.", - "type": "string" - }, - "sha": { - "description": "Specific commit SHA to use", - "type": "string", - "minLength": 40, - "maxLength": 40, - "pattern": "^[a-f0-9]{40}$" - } - }, - "required": [ - "source", - "repo" - ], - "additionalProperties": false - }, - { - "description": "Plugin located in a subdirectory of a larger repository (monorepo). Only the specified subdirectory is materialized; the rest of the repo is not downloaded.", - "type": "object", - "properties": { - "source": { - "type": "string", - "const": "git-subdir" - }, - "url": { - "description": "Git repository: GitHub owner/repo shorthand, https://, or git@ URL", - "type": "string" - }, - "path": { - "description": "Subdirectory within the repo containing the plugin (e.g., \"tools/claude-plugin\"). Cloned sparsely using partial clone (--filter=tree:0) to minimize bandwidth for monorepos.", - "type": "string", - "minLength": 1 - }, - "ref": { - "description": "Git branch or tag to use (e.g., \"main\", \"v1.0.0\"). Defaults to repository default branch.", - "type": "string" - }, - "sha": { - "description": "Specific commit SHA to use", - "type": "string", - "minLength": 40, - "maxLength": 40, - "pattern": "^[a-f0-9]{40}$" - } - }, - "required": [ - "source", - "url", - "path" - ], - "additionalProperties": false - }, - { - "description": "Placeholder for source types this Claude Code version does not recognize. Never authored by hand — PluginMarketplaceSchema rewrites unparseable sources to this so the entry remains in marketplace.plugins (detectDelistedPlugins must not see it as removed). Install attempts fail at cachePlugin with a clear \"update Claude Code\" message.", - "type": "object", - "properties": { - "source": { - "type": "string", - "const": "unsupported" - } - }, - "required": [ - "source" - ], - "additionalProperties": false - } - ] - }, - "description": { - "type": "string" - }, - "version": { - "type": "string" - }, - "strict": { - "type": "boolean" - } - }, - "required": [ - "name", - "source" - ], - "additionalProperties": false - } - }, - "owner": { - "type": "object", - "properties": { - "name": { - "description": "Display name of the plugin author or organization", - "type": "string", - "minLength": 1 - }, - "email": { - "description": "Contact email for support or feedback", - "type": "string" - }, - "url": { - "description": "Website, GitHub profile, or organization URL", - "type": "string" - } - }, - "required": [ - "name" - ], - "additionalProperties": false - } - }, - "required": [ - "source", - "name", - "plugins" - ], - "additionalProperties": false - } - ] - } - }, - "blockedMarketplaces": { - "description": "Enterprise blocklist of marketplace sources. When set in managed settings, these exact sources are blocked from being added as marketplaces. The check happens BEFORE downloading, so blocked sources never touch the filesystem.", - "type": "array", - "items": { - "anyOf": [ - { - "type": "object", - "properties": { - "source": { - "type": "string", - "const": "url" - }, - "url": { - "description": "Direct URL to marketplace.json file", - "type": "string", - "format": "uri" - }, - "headers": { - "description": "Custom HTTP headers (e.g., for authentication)", - "type": "object", - "propertyNames": { - "type": "string" - }, - "additionalProperties": { - "type": "string" - } - } - }, - "required": [ - "source", - "url" - ], - "additionalProperties": false - }, - { - "type": "object", - "properties": { - "source": { - "type": "string", - "const": "github" - }, - "repo": { - "description": "GitHub repository in owner/repo format", - "type": "string" - }, - "ref": { - "description": "Git branch or tag to use (e.g., \"main\", \"v1.0.0\"). Defaults to repository default branch.", - "type": "string" - }, - "path": { - "description": "Path to marketplace.json within repo (defaults to .claude-plugin/marketplace.json)", - "type": "string" - }, - "sparsePaths": { - "description": "Directories to include via git sparse-checkout (cone mode). Use for monorepos where the marketplace lives in a subdirectory. Example: [\".claude-plugin\", \"plugins\"]. If omitted, the full repository is cloned.", - "type": "array", - "items": { - "type": "string" - } - }, - "skipLfs": { - "description": "Skip Git LFS smudge during clone and update (sets GIT_LFS_SKIP_SMUDGE=1) so LFS pointer files stay as pointers instead of downloading their content. Use for marketplaces hosted in repos with large LFS objects.", - "type": "boolean" - } - }, - "required": [ - "source", - "repo" - ], - "additionalProperties": false - }, - { - "type": "object", - "properties": { - "source": { - "type": "string", - "const": "git" - }, - "url": { - "description": "Full git repository URL", - "type": "string" - }, - "ref": { - "description": "Git branch or tag to use (e.g., \"main\", \"v1.0.0\"). Defaults to repository default branch.", - "type": "string" - }, - "path": { - "description": "Path to marketplace.json within repo (defaults to .claude-plugin/marketplace.json)", - "type": "string" - }, - "sparsePaths": { - "description": "Directories to include via git sparse-checkout (cone mode). Use for monorepos where the marketplace lives in a subdirectory. Example: [\".claude-plugin\", \"plugins\"]. If omitted, the full repository is cloned.", - "type": "array", - "items": { - "type": "string" - } - }, - "skipLfs": { - "description": "Skip Git LFS smudge during clone and update (sets GIT_LFS_SKIP_SMUDGE=1) so LFS pointer files stay as pointers instead of downloading their content. Use for marketplaces hosted in repos with large LFS objects.", - "type": "boolean" - } - }, - "required": [ - "source", - "url" - ], - "additionalProperties": false - }, - { - "type": "object", - "properties": { - "source": { - "type": "string", - "const": "npm" - }, - "package": { - "description": "NPM package containing marketplace.json", - "type": "string" - } - }, - "required": [ - "source", - "package" - ], - "additionalProperties": false - }, - { - "type": "object", - "properties": { - "source": { - "type": "string", - "const": "file" - }, - "path": { - "description": "Local file path to marketplace.json", - "type": "string" - } - }, - "required": [ - "source", - "path" - ], - "additionalProperties": false - }, - { - "type": "object", - "properties": { - "source": { - "type": "string", - "const": "directory" - }, - "path": { - "description": "Local directory containing .claude-plugin/marketplace.json", - "type": "string" - } - }, - "required": [ - "source", - "path" - ], - "additionalProperties": false - }, - { - "description": "Policy-list sentinel for the ~/.claude/skills/ auto-load (@skills-dir plugins). In strictKnownMarketplaces: opt the scan back IN (by default any allowlist blocks it). In blockedMarketplaces: turn the scan OFF without otherwise restricting marketplaces. Only meaningful in those two managed-settings lists (areLocalPluginDirsAllowedByPolicy); known_marketplaces.json / marketplace add etc. ignore it.", - "type": "object", - "properties": { - "source": { - "type": "string", - "const": "skills-dir" - } - }, - "required": [ - "source" - ], - "additionalProperties": false - }, - { - "type": "object", - "properties": { - "source": { - "type": "string", - "const": "hostPattern" - }, - "hostPattern": { - "description": "Regex pattern to match the host/domain extracted from any marketplace source type. For github sources, matches against \"github.com\". For git sources (SSH or HTTPS), extracts the hostname from the URL. Use in strictKnownMarketplaces to allow all marketplaces from a specific host (e.g., \"^github\\.mycompany\\.com$\").", - "type": "string" - } - }, - "required": [ - "source", - "hostPattern" - ], - "additionalProperties": false - }, - { - "type": "object", - "properties": { - "source": { - "type": "string", - "const": "pathPattern" - }, - "pathPattern": { - "description": "Regex pattern matched against the .path field of file and directory sources. Use in strictKnownMarketplaces to allow filesystem-based marketplaces alongside hostPattern restrictions for network sources. Use \".*\" to allow all filesystem paths, or a narrower pattern (e.g., \"^/opt/approved/\") to restrict to specific directories.", - "type": "string" - } - }, - "required": [ - "source", - "pathPattern" - ], - "additionalProperties": false - }, - { - "description": "Inline marketplace manifest defined directly in settings.json. The reconciler writes a synthetic marketplace.json to the cache; diffMarketplaces detects edits via isEqual on the stored source (the plugins array is inside this object, so edits surface as sourceChanged).", - "type": "object", - "properties": { - "source": { - "type": "string", - "const": "settings" - }, - "name": { - "description": "Marketplace name. Must match the extraKnownMarketplaces key (enforced); the synthetic manifest is written under this name. Same validation as PluginMarketplaceSchema plus reserved-name rejection — validateOfficialNameSource runs after the disk write, too late to clean up.", - "type": "string", - "minLength": 1 - }, - "plugins": { - "description": "Plugin entries declared inline in settings.json", - "type": "array", - "items": { - "type": "object", - "properties": { - "name": { - "description": "Plugin name as it appears in the target repository", - "type": "string", - "minLength": 1 - }, - "source": { - "description": "Where to fetch the plugin from. Must be a remote source — relative paths have no marketplace repository to resolve against.", - "anyOf": [ - { - "description": "Path to the plugin root, relative to the marketplace root (the directory containing .claude-plugin/, not .claude-plugin/ itself)", - "type": "string", - "pattern": "^\\.\\/.*" - }, - { - "description": "NPM package as plugin source", - "type": "object", - "properties": { - "source": { - "type": "string", - "const": "npm" - }, - "package": { - "description": "Package name (or url, or local path, or anything else that can be passed to `npm` as a package)", - "anyOf": [ - { - "type": "string" - }, - { - "type": "string" - } - ] - }, - "version": { - "description": "Specific version or version range (e.g., ^1.0.0, ~2.1.0)", - "type": "string" - }, - "registry": { - "description": "Custom NPM registry URL (defaults to using system default, likely npmjs.org)", - "type": "string", - "format": "uri" - } - }, - "required": [ - "source", - "package" - ], - "additionalProperties": false - }, - { - "type": "object", - "properties": { - "source": { - "type": "string", - "const": "url" - }, - "url": { - "description": "Full git repository URL (https:// or git@)", - "type": "string" - }, - "ref": { - "description": "Git branch or tag to use (e.g., \"main\", \"v1.0.0\"). Defaults to repository default branch.", - "type": "string" - }, - "sha": { - "description": "Specific commit SHA to use", - "type": "string", - "minLength": 40, - "maxLength": 40, - "pattern": "^[a-f0-9]{40}$" - } - }, - "required": [ - "source", - "url" - ], - "additionalProperties": false - }, - { - "type": "object", - "properties": { - "source": { - "type": "string", - "const": "github" - }, - "repo": { - "description": "GitHub repository in owner/repo format", - "type": "string" - }, - "ref": { - "description": "Git branch or tag to use (e.g., \"main\", \"v1.0.0\"). Defaults to repository default branch.", - "type": "string" - }, - "sha": { - "description": "Specific commit SHA to use", - "type": "string", - "minLength": 40, - "maxLength": 40, - "pattern": "^[a-f0-9]{40}$" - } - }, - "required": [ - "source", - "repo" - ], - "additionalProperties": false - }, - { - "description": "Plugin located in a subdirectory of a larger repository (monorepo). Only the specified subdirectory is materialized; the rest of the repo is not downloaded.", - "type": "object", - "properties": { - "source": { - "type": "string", - "const": "git-subdir" - }, - "url": { - "description": "Git repository: GitHub owner/repo shorthand, https://, or git@ URL", - "type": "string" - }, - "path": { - "description": "Subdirectory within the repo containing the plugin (e.g., \"tools/claude-plugin\"). Cloned sparsely using partial clone (--filter=tree:0) to minimize bandwidth for monorepos.", - "type": "string", - "minLength": 1 - }, - "ref": { - "description": "Git branch or tag to use (e.g., \"main\", \"v1.0.0\"). Defaults to repository default branch.", - "type": "string" - }, - "sha": { - "description": "Specific commit SHA to use", - "type": "string", - "minLength": 40, - "maxLength": 40, - "pattern": "^[a-f0-9]{40}$" - } - }, - "required": [ - "source", - "url", - "path" - ], - "additionalProperties": false - }, - { - "description": "Placeholder for source types this Claude Code version does not recognize. Never authored by hand — PluginMarketplaceSchema rewrites unparseable sources to this so the entry remains in marketplace.plugins (detectDelistedPlugins must not see it as removed). Install attempts fail at cachePlugin with a clear \"update Claude Code\" message.", - "type": "object", - "properties": { - "source": { - "type": "string", - "const": "unsupported" - } - }, - "required": [ - "source" - ], - "additionalProperties": false - } - ] - }, - "description": { - "type": "string" - }, - "version": { - "type": "string" - }, - "strict": { - "type": "boolean" - } - }, - "required": [ - "name", - "source" - ], - "additionalProperties": false - } - }, - "owner": { - "type": "object", - "properties": { - "name": { - "description": "Display name of the plugin author or organization", - "type": "string", - "minLength": 1 - }, - "email": { - "description": "Contact email for support or feedback", - "type": "string" - }, - "url": { - "description": "Website, GitHub profile, or organization URL", - "type": "string" - } - }, - "required": [ - "name" - ], - "additionalProperties": false - } - }, - "required": [ - "source", - "name", - "plugins" - ], - "additionalProperties": false - } - ] - } - }, - "pluginSuggestionMarketplaces": { - "description": "Marketplace names whose plugins may surface as contextual install suggestions (relevance-based tips). No marketplace-declared suggestions surface without this allowlist; the built-in first-party frontend-design tip is unaffected. Only honored when set in managed settings (policy scope); the key is ignored in user, project, and local settings. A name only takes effect when the marketplace is registered on the machine AND its registered source is also declared in managed settings, either as the extraKnownMarketplaces entry for that name or as an entry of strictKnownMarketplaces. A marketplace registered from a different source under an allowlisted name is ignored. The official marketplace is exempt from the source requirement: allowlisting its name alone suffices, since that name can only register from the official Anthropic source.", - "type": "array", - "items": { - "type": "string" - } - }, - "forceLoginMethod": { - "description": "Force a specific login method: \"claudeai\" for Claude Pro/Max, \"console\" for Console billing, \"gateway\" for the Cloud gateway OIDC device flow", - "type": "string", - "enum": [ - "claudeai", - "console", - "gateway" - ] - }, - "forceLoginGatewayUrl": { - "description": "@internal Cloud gateway URL to pre-fill and auto-connect to during login. Typically set in local managed settings alongside forceLoginMethod: \"gateway\" so users never type the URL. Hidden from public SDK types until Cloud gateway is documented.", - "type": "string", - "format": "uri" - }, - "parentSettingsBehavior": { - "description": "Controls whether the SDK parent tier (Options.managedSettings / --managed-settings) layers under this admin tier. \"first-wins\" (default): parent is dropped — admin tiers are the only policy source. \"merge\": parent's restrictive-only-filtered settings union under the admin winner. Has no effect when no admin tier exists (parent applies as the sole policy tier, still filtered restrictive-only).", - "type": "string", - "enum": [ - "first-wins", - "merge" - ] - }, - "forceLoginOrgUUID": { - "description": "Organization UUID to require for OAuth login. Accepts a single UUID string or an array of UUIDs (any one is permitted). When set in managed settings, login fails if the authenticated account does not belong to a listed organization.", - "anyOf": [ - { - "type": "string" - }, - { - "type": "array", - "items": { - "type": "string" - } - } - ] - }, - "forceRemoteSettingsRefresh": { - "description": "When set in managed settings, the CLI blocks startup until remote managed settings are freshly fetched, and exits if the fetch fails", - "type": "boolean" - }, - "otelHeadersHelper": { - "description": "Path to a script that outputs OpenTelemetry headers", - "type": "string" - }, - "outputStyle": { - "description": "Controls the output style for assistant responses", - "type": "string" - }, - "viewMode": { - "description": "Default transcript view mode on startup", - "type": "string", - "enum": [ - "default", - "verbose", - "focus" - ] - }, - "language": { - "description": "Preferred language for Claude responses and voice dictation (e.g., \"japanese\", \"spanish\")", - "type": "string" - }, - "skipWebFetchPreflight": { - "description": "Skip the WebFetch blocklist check for enterprise environments with restrictive security policies", - "type": "boolean" - }, - "sandbox": { - "type": "object", - "properties": { - "enabled": { - "type": "boolean" - }, - "failIfUnavailable": { - "description": "Exit with an error at startup if sandbox.enabled is true but the sandbox cannot start (missing dependencies or unsupported platform). When false (default), a warning is shown and commands run unsandboxed. Intended for managed-settings deployments that require sandboxing as a hard gate.", - "type": "boolean" - }, - "autoAllowBashIfSandboxed": { - "type": "boolean" - }, - "allowUnsandboxedCommands": { - "description": "Allow commands to run outside the sandbox via the dangerouslyDisableSandbox parameter. When false, the dangerouslyDisableSandbox parameter is completely ignored and all commands must run sandboxed. Default: true.", - "type": "boolean" - }, - "network": { - "type": "object", - "properties": { - "allowedDomains": { - "type": "array", - "items": { - "type": "string" - } - }, - "deniedDomains": { - "description": "Domains that are always blocked, even if matched by allowedDomains. Supports the same wildcard syntax as allowedDomains. Merged from all settings sources regardless of allowManagedDomainsOnly.", - "type": "array", - "items": { - "type": "string" - } - }, - "allowManagedDomainsOnly": { - "description": "When true (and set in managed settings), only allowedDomains and WebFetch(domain:...) allow rules from managed settings are respected. User, project, local, and flag settings domains are ignored. Denied domains are still respected from all sources.", - "type": "boolean" - }, - "allowUnixSockets": { - "description": "macOS only: Unix socket paths to allow. Ignored on Linux (seccomp cannot filter by path).", - "type": "array", - "items": { - "type": "string" - } - }, - "allowAllUnixSockets": { - "description": "If true, allow all Unix sockets (disables blocking on both platforms).", - "type": "boolean" - }, - "allowLocalBinding": { - "type": "boolean" - }, - "allowMachLookup": { - "description": "macOS only: Additional XPC/Mach service names to allow looking up. Supports trailing-wildcard prefix matching (e.g., \"com.apple.coresimulator.*\"). Needed for tools that communicate via XPC such as the iOS Simulator or Playwright.", - "type": "array", - "items": { - "type": "string" - } - }, - "httpProxyPort": { - "type": "number" - }, - "socksProxyPort": { - "type": "number" - }, - "tlsTerminate": { - "description": "[EXPERIMENTAL] Enable in-process TLS termination so the per-request filter can see HTTPS request bodies. Provide a CA cert+key, or omit both to have sandbox-runtime generate an ephemeral one for the session.", - "type": "object", - "properties": { - "caCertPath": { - "type": "string", - "minLength": 1 - }, - "caKeyPath": { - "type": "string", - "minLength": 1 - } - }, - "additionalProperties": false - } - }, - "additionalProperties": false - }, - "filesystem": { - "type": "object", - "properties": { - "allowWrite": { - "description": "Additional paths to allow writing within the sandbox. Merged with paths from Edit(...) allow permission rules.", - "type": "array", - "items": { - "type": "string" - } - }, - "denyWrite": { - "description": "Additional paths to deny writing within the sandbox. Merged with paths from Edit(...) deny permission rules.", - "type": "array", - "items": { - "type": "string" - } - }, - "denyRead": { - "description": "Additional paths to deny reading within the sandbox. Merged with paths from Read(...) deny permission rules.", - "type": "array", - "items": { - "type": "string" - } - }, - "allowRead": { - "description": "Paths to re-allow reading within denyRead regions. Takes precedence over denyRead for matching paths.", - "type": "array", - "items": { - "type": "string" - } - }, - "allowManagedReadPathsOnly": { - "description": "When true (set in managed settings), only allowRead paths from policySettings are used.", - "type": "boolean" - } - }, - "additionalProperties": false - }, - "ignoreViolations": { - "type": "object", - "propertyNames": { - "type": "string" - }, - "additionalProperties": { - "type": "array", - "items": { - "type": "string" - } - } - }, - "enableWeakerNestedSandbox": { - "type": "boolean" - }, - "enableWeakerNetworkIsolation": { - "description": "macOS only: Allow access to com.apple.trustd.agent in the sandbox. Needed for Go-based CLI tools (gh, gcloud, terraform, etc.) to verify TLS certificates when using httpProxyPort with a MITM proxy and custom CA. **Reduces security** — opens a potential data exfiltration vector through the trustd service. Default: false", - "type": "boolean" - }, - "excludedCommands": { - "type": "array", - "items": { - "type": "string" - } - }, - "ripgrep": { - "description": "Custom ripgrep configuration for bundled ripgrep support", - "type": "object", - "properties": { - "command": { - "type": "string" - }, - "args": { - "type": "array", - "items": { - "type": "string" - } - } - }, - "required": [ - "command" - ], - "additionalProperties": false - }, - "bwrapPath": { - "description": "Linux/WSL only: Absolute path to the bwrap (bubblewrap) binary. Overrides auto-detection via PATH. Only honored from admin-controlled managed settings.", - "type": "string" - }, - "socatPath": { - "description": "Linux/WSL only: Absolute path to the socat binary used for the sandbox network proxy. Overrides auto-detection via PATH. Only honored from admin-controlled managed settings.", - "type": "string" - } - }, - "additionalProperties": {} - }, - "feedbackSurveyRate": { - "description": "Probability (0–1) that the session quality survey appears when eligible. 0.05 is a reasonable starting point.", - "type": "number", - "minimum": 0, - "maximum": 1 - }, - "spinnerTipsEnabled": { - "description": "Whether to show tips in the spinner", - "type": "boolean" - }, - "spinnerVerbs": { - "description": "Customize spinner verbs. mode: \"append\" adds verbs to defaults, \"replace\" uses only your verbs.", - "type": "object", - "properties": { - "mode": { - "type": "string", - "enum": [ - "append", - "replace" - ] - }, - "verbs": { - "type": "array", - "items": { - "type": "string" - } - } - }, - "required": [ - "mode", - "verbs" - ], - "additionalProperties": false - }, - "spinnerTipsOverride": { - "description": "Override spinner tips. tips: array of tip strings. excludeDefault: if true, only show custom tips (default: false).", - "type": "object", - "properties": { - "excludeDefault": { - "type": "boolean" - }, - "tips": { - "type": "array", - "items": { - "type": "string" - } - } - }, - "required": [ - "tips" - ], - "additionalProperties": false - }, - "syntaxHighlightingDisabled": { - "description": "Whether to disable syntax highlighting in diffs", - "type": "boolean" - }, - "terminalTitleFromRename": { - "description": "Whether /rename updates the terminal tab title (defaults to true). Set to false to keep auto-generated topic titles.", - "type": "boolean" - }, - "alwaysThinkingEnabled": { - "description": "When false, thinking is disabled. When absent or true, thinking is enabled automatically for supported models.", - "type": "boolean" - }, - "effortLevel": { - "description": "Persisted effort level for supported models.", - "type": "string", - "enum": [ - "low", - "medium", - "high", - "xhigh" - ] - }, - "ultracode": { - "description": "Enable ultracode for the session: xhigh effort plus standing dynamic-workflow orchestration. Session-scoped — typically provided via --settings or the apply_flag_settings control request; interactive toggles never persist it. Requires workflows to be enabled and an xhigh-capable model.", - "type": "boolean" - }, - "autoCompactWindow": { - "description": "Auto-compact window size", - "type": "integer", - "minimum": 100000, - "maximum": 1000000 - }, - "advisorModel": { - "description": "Advisor model for the server-side advisor tool.", - "type": "string" - }, - "fastMode": { - "description": "When true, fast mode is enabled. When absent or false, fast mode is off.", - "type": "boolean" - }, - "fastModePerSessionOptIn": { - "description": "When true, fast mode does not persist across sessions. Each session starts with fast mode off.", - "type": "boolean" - }, - "promptSuggestionEnabled": { - "description": "When false, prompt suggestions are disabled. When absent or true, prompt suggestions are enabled.", - "type": "boolean" - }, - "awaySummaryEnabled": { - "description": "@internal When false, the session recap (shown when you return after being away for 5+ minutes) is disabled. When absent or true, recap is enabled. Hidden from public SDK types until external launch.", - "type": "boolean" - }, - "showClearContextOnPlanAccept": { - "description": "When true, the plan-approval dialog offers a \"clear context\" option. Defaults to false.", - "type": "boolean" - }, - "agent": { - "description": "Name of an agent (built-in or custom) to use for the main thread. Applies the agent's system prompt, tool restrictions, and model.", - "type": "string" - }, - "companyAnnouncements": { - "description": "Company announcements to display at startup (one will be randomly selected if multiple are provided)", - "type": "array", - "items": { - "type": "string" - } - }, - "pluginConfigs": { - "description": "Per-plugin configuration including MCP server user configs, keyed by plugin ID (plugin@marketplace format)", - "type": "object", - "propertyNames": { - "type": "string" - }, - "additionalProperties": { - "type": "object", - "properties": { - "mcpServers": { - "description": "User configuration values for MCP servers keyed by server name", - "type": "object", - "propertyNames": { - "type": "string" - }, - "additionalProperties": { - "type": "object", - "propertyNames": { - "type": "string" - }, - "additionalProperties": { - "anyOf": [ - { - "type": "string" - }, - { - "type": "number" - }, - { - "type": "boolean" - }, - { - "type": "array", - "items": { - "type": "string" - } - } - ] - } - } - }, - "options": { - "description": "Non-sensitive option values from plugin manifest userConfig, keyed by option name. Sensitive values go to secure storage instead.", - "type": "object", - "propertyNames": { - "type": "string" - }, - "additionalProperties": { - "anyOf": [ - { - "type": "string" - }, - { - "type": "number" - }, - { - "type": "boolean" - }, - { - "type": "array", - "items": { - "type": "string" - } - } - ] - } - } - }, - "additionalProperties": false - } - }, - "remote": { - "description": "Cloud session configuration", - "type": "object", - "properties": { - "defaultEnvironmentId": { - "description": "Default environment ID to use for cloud sessions", - "type": "string" - } - }, - "additionalProperties": false - }, - "autoUpdatesChannel": { - "description": "Release channel for auto-updates (latest or stable)", - "type": "string", - "enum": [ - "latest", - "stable", - "rc" - ] - }, - "minimumVersion": { - "description": "Minimum version to stay on - prevents downgrades when switching to stable channel", - "type": "string" - }, - "requiredMinimumVersion": { - "description": "Minimum Claude Code version required to start. If the running version is older, Claude Code exits at startup with instructions to update. Only enforced from managed (policy) settings.", - "type": "string" - }, - "requiredMaximumVersion": { - "description": "Maximum Claude Code version allowed to start. If the running version is newer, Claude Code exits at startup with instructions to install an approved version. Only enforced from managed (policy) settings.", - "type": "string" - }, - "plansDirectory": { - "description": "Custom directory for plan files, relative to project root. If not set, defaults to ~/.claude/plans/", - "type": "string" - }, - "tui": { - "description": "Terminal UI renderer. \"fullscreen\" uses the flicker-free alt-screen renderer with virtualized scrollback (equivalent to CLAUDE_CODE_NO_FLICKER=1). \"default\" uses the classic main-screen renderer.", - "type": "string", - "enum": [ - "default", - "fullscreen" - ] - }, - "voice": { - "description": "Voice mode settings (hold-to-talk / tap-to-toggle dictation)", - "type": "object", - "properties": { - "enabled": { - "type": "boolean" - }, - "mode": { - "description": "'hold' (default): hold to talk. 'tap': tap to start, tap to stop+submit.", - "type": "string", - "enum": [ - "hold", - "tap" - ] - }, - "autoSubmit": { - "description": "Submit the prompt when hold-to-talk is released (hold mode only)", - "type": "boolean" - } - }, - "additionalProperties": false - }, - "channelsEnabled": { - "description": "Managed-org opt-in for channel notifications (MCP servers with the claude/channel capability pushing inbound messages). claude.ai Teams/Enterprise: default off. Console: default on unless managed settings exist. Set true to allow; users then select servers via --channels.", - "type": "boolean" - }, - "allowedChannelPlugins": { - "description": "Managed-org allowlist of channel plugins. When set, replaces the default Anthropic allowlist — admins decide which plugins may push inbound messages. Undefined falls back to the default. Requires channelsEnabled: true.", - "type": "array", - "items": { - "type": "object", - "properties": { - "marketplace": { - "type": "string" - }, - "plugin": { - "type": "string" - } - }, - "required": [ - "marketplace", - "plugin" - ], - "additionalProperties": false - } - }, - "prefersReducedMotion": { - "description": "Reduce or disable animations for accessibility (spinner shimmer, flash effects, etc.)", - "type": "boolean" - }, - "doneMeansMerged": { - "description": "@internal When true, Claude keeps working until the PR is ready for you to merge, a cron/Monitor is armed to resume later, or it hands you a self-contained next step.", - "type": "boolean" - }, - "totalTokensReminder": { - "description": "@internal Emit a N tokens left block in the system prompt and after each tool result. 'infinite' uses the literal value Infinite, 'fixed' uses 5000000, 'countdown' uses the live remaining context-window tokens. Defaults to off. Env var CLAUDE_CODE_TOTAL_TOKENS_REMINDER overrides.", - "type": "string", - "enum": [ - "off", - "infinite", - "fixed", - "countdown" - ] - }, - "autoMemoryEnabled": { - "description": "Enable auto-memory for this project. When false, Claude will not read from or write to the auto-memory directory.", - "type": "boolean" - }, - "autoMemoryDirectory": { - "description": "Custom directory path for auto-memory storage. Supports ~/ prefix for home directory expansion. Ignored if set in projectSettings (checked-in .claude/settings.json) for security. When unset, defaults to ~/.claude/projects//memory/.", - "type": "string" - }, - "autoDreamEnabled": { - "description": "Enable background memory consolidation (auto-dream). When set, overrides the server-side default.", - "type": "boolean" - }, - "showThinkingSummaries": { - "description": "Request API-side thinking summaries and show them in the conversation and in the transcript view (ctrl+o). Set explicitly to override the default for your install.", - "type": "boolean" - }, - "skipDangerousModePermissionPrompt": { - "description": "Whether the user has accepted the bypass permissions mode dialog", - "type": "boolean" - }, - "skipWorkflowUsageWarning": { - "description": "@internal Whether the user has accepted the multi-agent workflow usage warning. Until set, auto permission mode prompts before running a workflow.", - "type": "boolean" - }, - "disableAutoMode": { - "description": "Disable auto mode", - "type": "string", - "enum": [ - "disable" - ] - }, - "sshConfigs": { - "description": "SSH connection configurations for remote environments. Typically set in managed settings by enterprise administrators to pre-configure SSH connections for team members.", - "type": "array", - "items": { - "type": "object", - "properties": { - "id": { - "description": "Unique identifier for this SSH config. Used to match configs across settings sources.", - "type": "string" - }, - "name": { - "description": "Display name for the SSH connection", - "type": "string" - }, - "sshHost": { - "description": "SSH host in format \"user@hostname\" or \"hostname\", or a host alias from ~/.ssh/config", - "type": "string" - }, - "sshPort": { - "description": "SSH port (default: 22)", - "type": "integer", - "minimum": -9007199254740991, - "maximum": 9007199254740991 - }, - "sshIdentityFile": { - "description": "Path to SSH identity file (private key)", - "type": "string" - }, - "startDirectory": { - "description": "Default working directory on the remote host. Supports tilde expansion (e.g. ~/projects). If not specified, defaults to the remote user home directory. Can be overridden by the [dir] positional argument in `claude ssh [dir]`.", - "type": "string" - } - }, - "required": [ - "id", - "name", - "sshHost" - ], - "additionalProperties": false - } - }, - "claudeMd": { - "description": "CLAUDE.md-style instructions injected as organization-managed memory. Only honored from managed/policy settings.", - "type": "string" - }, - "claudeMdExcludes": { - "description": "Glob patterns or absolute paths of CLAUDE.md files to exclude from loading. Patterns are matched against absolute file paths using picomatch. Only applies to User, Project, and Local memory types (Managed/policy files cannot be excluded). Examples: \"/home/user/monorepo/CLAUDE.md\", \"**/code/CLAUDE.md\", \"**/some-dir/.claude/rules/**\"", - "type": "array", - "items": { - "type": "string" - } - }, - "pluginTrustMessage": { - "description": "Custom message to append to the plugin trust warning shown before installation. Only read from policy settings (managed-settings.json / MDM). Useful for enterprise administrators to add organization-specific context (e.g., \"All plugins from our internal marketplace are vetted and approved.\").", - "type": "string" - }, - "theme": { - "description": "Color theme for the UI", - "anyOf": [ - { - "type": "string", - "enum": [ - "auto", - "dark", - "light", - "light-daltonized", - "dark-daltonized", - "light-ansi", - "dark-ansi" - ] - }, - {} - ] - }, - "editorMode": { - "description": "Key binding mode for the prompt input", - "type": "string", - "enum": [ - "normal", - "vim" - ] - }, - "verbose": { - "description": "Show full tool output instead of truncated summaries", - "type": "boolean" - }, - "preferredNotifChannel": { - "description": "Preferred OS notification channel", - "type": "string", - "enum": [ - "auto", - "iterm2", - "iterm2_with_bell", - "terminal_bell", - "kitty", - "ghostty", - "notifications_disabled" - ] - }, - "autoCompactEnabled": { - "description": "Automatically compact conversation when context fills", - "type": "boolean" - }, - "precomputeCompactionEnabled": { - "description": "@internal Precompute the compaction summary in the background before it is needed. Only applies when auto-compact is on.", - "type": "boolean" - }, - "switchModelsOnFlag": { - "description": "When safety measures flag a message, automatically switch to a different model to keep chatting. When off, your session will pause instead.", - "type": "boolean" - }, - "autoScrollEnabled": { - "description": "Auto-scroll the conversation view to bottom (fullscreen mode only)", - "type": "boolean" - }, - "wheelScrollAccelerationEnabled": { - "description": "Ramp mouse-wheel scroll speed during fast scrolls (fullscreen mode only)", - "type": "boolean" - }, - "fileCheckpointingEnabled": { - "description": "Snapshot files before edits so /rewind can restore them", - "type": "boolean" - }, - "showTurnDuration": { - "description": "Show \"Cooked for Nm Ns\" after each assistant turn", - "type": "boolean" - }, - "showMessageTimestamps": { - "description": "Stamp each assistant message with its arrival time", - "type": "boolean" - }, - "terminalProgressBarEnabled": { - "description": "Emit OSC 9;4 progress sequences during long operations", - "type": "boolean" - }, - "todoFeatureEnabled": { - "description": "Enable the todo / task tracking panel", - "type": "boolean" - }, - "teammateMode": { - "description": "How spawned teammates execute (tmux, in-process, auto)", - "type": "string", - "enum": [ - "auto", - "tmux", - "in-process" - ] - }, - "remoteControlAtStartup": { - "description": "Start Remote Control bridge automatically each session", - "type": "boolean" - }, - "isolatePeerMachines": { - "description": "Require explicit approval before SendMessage can reach a peer session on another machine via Remote Control", - "type": "boolean" - }, - "daemonColdStart": { - "description": "When no background service is running: 'transient' spawns one for this login session; 'ask' offers to install it persistently", - "type": "string", - "enum": [ - "transient", - "ask" - ] - }, - "autoUploadSessions": { - "description": "Mirror local sessions to claude.ai as view-only (no remote control)", - "type": "boolean" - }, - "inputNeededNotifEnabled": { - "description": "Push to mobile when a permission prompt or question is waiting", - "type": "boolean" - }, - "agentPushNotifEnabled": { - "description": "Allow Claude to push proactive mobile notifications", - "type": "boolean" - }, - "skipAutoPermissionPrompt": { - "description": "Whether the user has accepted the auto mode opt-in dialog", - "type": "boolean" - }, - "useAutoModeDuringPlan": { - "description": "Whether plan mode uses auto mode semantics when auto mode is available (default: true)", - "type": "boolean" - }, - "autoMode": { - "description": "Auto mode classifier prompt customization", - "type": "object", - "properties": { - "allow": { - "description": "Rules for the auto mode classifier allow section. Include the literal string \"$defaults\" to inherit the built-in rules at that position.", - "type": "array", - "items": { - "type": "string" - } - }, - "soft_deny": { - "description": "Rules for the auto mode classifier SOFT BLOCK section — destructive/irreversible actions that user intent can clear. Include the literal string \"$defaults\" to inherit the built-in rules at that position.", - "type": "array", - "items": { - "type": "string" - } - }, - "hard_deny": { - "description": "Rules for the auto mode classifier HARD BLOCK section — security boundaries that user intent does NOT clear. Include the literal string \"$defaults\" to inherit the built-in rules at that position.", - "type": "array", - "items": { - "type": "string" - } - }, - "environment": { - "description": "Entries for the auto mode classifier environment section. Include the literal string \"$defaults\" to inherit the built-in entries at that position.", - "type": "array", - "items": { - "type": "string" - } - } - }, - "additionalProperties": false - }, - "disableDeepLinkRegistration": { - "description": "Prevent claude-cli:// protocol handler registration with the OS", - "type": "string", - "enum": [ - "disable" - ] - }, - "voiceEnabled": { - "description": "Enable voice mode (hold-to-talk dictation)", - "type": "boolean" - }, - "defaultView": { - "description": "Default transcript view: chat (SendUserMessage checkpoints only) or transcript (full)", - "type": "string", - "enum": [ - "chat", - "transcript" - ] - } - }, - "additionalProperties": {} -} diff --git a/Anthropic/Claude Code/bundled-skills/update-config.md b/Anthropic/Claude Code/bundled-skills/update-config.md index a304123..7e64887 100644 --- a/Anthropic/Claude Code/bundled-skills/update-config.md +++ b/Anthropic/Claude Code/bundled-skills/update-config.md @@ -417,12 +417,3069 @@ If a hook isn't running: 5. **Test the command** - Run the hook command manually to see if it works 6. **Use --debug** - Run `claude --debug` to see hook execution logs ---- - -> **Runtime injection note:** The schema below is generated at runtime from Zod definitions (function `vz8` in the binary), not stored as static text. The `## User Request` section (user's original message) is also appended at load time. ## Full Settings JSON Schema -The full schema is in [update-config-schema.json](update-config-schema.json). - IMPORTANT: Do not update the env unless explicitly instructed to do so. + + + +```json +{ + "$schema": "https://json-schema.org/draft/2020-12/schema", + "type": "object", + "properties": { + "$schema": { + "description": "JSON Schema reference for Claude Code settings", + "type": "string" + }, + "apiKeyHelper": { + "description": "Path to a script that outputs authentication values", + "type": "string" + }, + "proxyAuthHelper": { + "description": "Shell command that outputs a Proxy-Authorization header value (EAP)", + "type": "string" + }, + "awsCredentialExport": { + "description": "Path to a script that exports AWS credentials", + "type": "string" + }, + "awsAuthRefresh": { + "description": "Path to a script that refreshes AWS authentication", + "type": "string" + }, + "gcpAuthRefresh": { + "description": "Command to refresh GCP authentication (e.g., gcloud auth application-default login)", + "type": "string" + }, + "policyHelper": { + "description": "Executable that computes managed settings at startup. Honored only from admin-controlled policy sources.", + "type": "object", + "properties": { + "path": { + "description": "Absolute path to the helper executable", + "type": "string" + }, + "timeoutMs": { + "type": "integer", + "minimum": 1000, + "maximum": 9007199254740991 + }, + "refreshIntervalMs": { + "anyOf": [ + { + "type": "number", + "const": 0 + }, + { + "type": "integer", + "minimum": 60000, + "maximum": 9007199254740991 + } + ] + } + }, + "required": [ + "path" + ], + "additionalProperties": false + }, + "fileSuggestion": { + "description": "Custom file suggestion configuration for @ mentions", + "type": "object", + "properties": { + "type": { + "type": "string", + "const": "command" + }, + "command": { + "type": "string" + } + }, + "required": [ + "type", + "command" + ], + "additionalProperties": false + }, + "respectGitignore": { + "description": "Whether file picker should respect .gitignore files (default: true). Note: .ignore files are always respected.", + "type": "boolean" + }, + "breakReminder": { + "description": "@internal Opt-in break reminder. When enabled, shows a dismissible nudge after sustained continuous use. Never blocks — just a friendly heads-up.", + "type": "object", + "properties": { + "enabled": { + "description": "Show a friendly nudge after sustained continuous use (default false). Must be true for the reminder to fire.", + "type": "boolean" + }, + "intervalMinutes": { + "description": "Minutes of continuous use before the reminder fires (default 120). Re-fires every interval until you take a break.", + "type": "integer", + "exclusiveMinimum": 0, + "maximum": 9007199254740991 + }, + "breakThresholdMinutes": { + "description": "Minutes of inactivity that count as a break and reset the timer (default 15)", + "type": "integer", + "exclusiveMinimum": 0, + "maximum": 9007199254740991 + }, + "message": { + "description": "Custom reminder text. Leave unset for a rotating set of friendly nudges.", + "type": "string" + } + }, + "additionalProperties": false + }, + "quietHours": { + "description": "@internal Opt-in quiet hours. When enabled, shows a single soft nudge per session while inside the configured local-time window. Never blocks.", + "type": "object", + "properties": { + "enabled": { + "description": "Show a one-time nudge when you start or keep using the CLI inside your quiet-hours window (default false).", + "type": "boolean" + }, + "start": { + "description": "Start of the quiet-hours window, 24-hour local time \"HH:MM\".", + "type": "string", + "pattern": "^([01]?\\d|2[0-3]):[0-5]\\d$" + }, + "end": { + "description": "End of the quiet-hours window, 24-hour local time \"HH:MM\". May be earlier than start for an overnight range.", + "type": "string", + "pattern": "^([01]?\\d|2[0-3]):[0-5]\\d$" + } + }, + "additionalProperties": false + }, + "cleanupPeriodDays": { + "description": "Number of days to retain chat transcripts before automatic cleanup (default: 30). Minimum 1. Use a large value for long retention; use --no-session-persistence to disable transcript writes entirely.", + "type": "integer", + "exclusiveMinimum": 0, + "maximum": 9007199254740991 + }, + "skillListingMaxDescChars": { + "description": "Per-skill description character cap in the skill listing sent to Claude (default: 1536). Descriptions longer than this are truncated. Raise to opt in to higher per-turn context cost.", + "type": "integer", + "exclusiveMinimum": 0, + "maximum": 9007199254740991 + }, + "skillListingBudgetFraction": { + "description": "Fraction of the context window (in characters) reserved for the skill listing sent to Claude (default: 0.01 = 1%). When the listing exceeds this, descriptions are shortened to fit. Raise to opt in to higher per-turn context cost.", + "type": "number", + "exclusiveMinimum": 0, + "maximum": 1 + }, + "wslInheritsWindowsSettings": { + "description": "When set to true in either admin-only Windows source — the HKLM SOFTWARE/Policies/ClaudeCode registry key or C:/Program Files/ClaudeCode/managed-settings.json — WSL reads managed settings from the full Windows policy chain (HKLM, C:/Program Files/ClaudeCode via DrvFs, HKCU) in addition to /etc/claude-code. Windows sources take priority. The flag is also required in HKCU itself for HKCU policy to apply on WSL (double opt-in: admin enables the chain, user confirms HKCU). On native Windows the flag has no effect.", + "type": "boolean" + }, + "env": { + "description": "Environment variables to set for Claude Code sessions", + "type": "object", + "propertyNames": { + "type": "string" + }, + "additionalProperties": { + "type": "string" + } + }, + "attribution": { + "description": "Customize attribution text for commits and PRs. Each field defaults to the standard Claude Code attribution if not set.", + "type": "object", + "properties": { + "commit": { + "description": "Attribution text for git commits, including any trailers. Empty string hides attribution.", + "type": "string" + }, + "pr": { + "description": "Attribution text for pull request descriptions. Empty string hides attribution.", + "type": "string" + } + }, + "additionalProperties": false + }, + "includeCoAuthoredBy": { + "description": "Deprecated: Use attribution instead. Whether to include Claude's co-authored by attribution in commits and PRs (defaults to true)", + "type": "boolean" + }, + "includeGitInstructions": { + "description": "Include built-in commit and PR workflow instructions in Claude's system prompt (default: true)", + "type": "boolean" + }, + "permissions": { + "description": "Tool usage permissions configuration", + "type": "object", + "properties": { + "allow": { + "description": "List of permission rules for allowed operations", + "type": "array", + "items": { + "type": "string" + } + }, + "deny": { + "description": "List of permission rules for denied operations", + "type": "array", + "items": { + "type": "string" + } + }, + "ask": { + "description": "List of permission rules that should always prompt for confirmation", + "type": "array", + "items": { + "type": "string" + } + }, + "defaultMode": { + "description": "Default permission mode when Claude Code needs access", + "type": "string", + "enum": [ + "acceptEdits", + "auto", + "bypassPermissions", + "default", + "dontAsk", + "plan" + ] + }, + "disableBypassPermissionsMode": { + "description": "Disable the ability to bypass permission prompts", + "type": "string", + "enum": [ + "disable" + ] + }, + "disableAutoMode": { + "description": "Disable auto mode", + "type": "string", + "enum": [ + "disable" + ] + }, + "additionalDirectories": { + "description": "Additional directories to include in the permission scope", + "type": "array", + "items": { + "type": "string" + } + } + }, + "additionalProperties": {} + }, + "model": { + "description": "Override the default model used by Claude Code", + "type": "string" + }, + "fallbackModel": { + "description": "Fallback model(s) tried in order when the primary model is overloaded or unavailable. Each element accepts a model name or alias; \"default\" expands to the default model. CLI --fallback-model takes precedence.", + "type": "array", + "items": { + "type": "string" + } + }, + "availableModels": { + "description": "Allowlist of models that users can select. Accepts family aliases (\"opus\" allows any opus version), version prefixes (\"opus-4-5\" allows only that version), and full model IDs. If undefined, all models are available. If empty array, only the default model is available. Typically set in managed settings by enterprise administrators.", + "type": "array", + "items": { + "type": "string" + } + }, + "enforceAvailableModels": { + "description": "When true and availableModels is a non-empty array, the Default model selection is also constrained: if the default model for the user tier is not in availableModels, Default resolves to the first allowed availableModels entry instead. Has no effect when availableModels is unset or an empty array. Typically set in managed settings by enterprise administrators.", + "type": "boolean" + }, + "modelOverrides": { + "description": "Override mapping from Anthropic model ID (e.g. \"claude-opus-4-6\") to provider-specific model ID (e.g. a Bedrock inference profile ARN). Typically set in managed settings by enterprise administrators.", + "type": "object", + "propertyNames": { + "type": "string" + }, + "additionalProperties": { + "type": "string" + } + }, + "enableAllProjectMcpServers": { + "description": "Whether to automatically approve all MCP servers in the project", + "type": "boolean" + }, + "enabledMcpjsonServers": { + "description": "List of approved MCP servers from .mcp.json", + "type": "array", + "items": { + "type": "string" + } + }, + "disabledMcpjsonServers": { + "description": "List of rejected MCP servers from .mcp.json", + "type": "array", + "items": { + "type": "string" + } + }, + "skillOverrides": { + "description": "Per-skill listing overrides keyed by skill name. \"name-only\" lists the skill without its description; \"user-invocable-only\" hides it from the model but keeps /name; \"off\" hides it from both. Absent = on.", + "type": "object", + "propertyNames": { + "type": "string" + }, + "additionalProperties": { + "type": "string", + "enum": [ + "on", + "name-only", + "user-invocable-only", + "off" + ] + } + }, + "disableBundledSkills": { + "description": "Disable the skills and workflows that ship with Claude Code: bundled skills and workflows are removed entirely; built-in slash commands stay typable but are hidden from the model. Plugins, .claude/skills/, and .claude/commands/ are unaffected. Equivalent to CLAUDE_CODE_DISABLE_BUNDLED_SKILLS=1.", + "type": "boolean" + }, + "allowedMcpServers": { + "description": "Enterprise allowlist of MCP servers that can be used. Applies to all scopes including enterprise servers from managed-mcp.json. If undefined, all servers are allowed. If empty array, no servers are allowed. Denylist takes precedence - if a server is on both lists, it is denied.", + "type": "array", + "items": { + "type": "object", + "properties": { + "serverName": { + "description": "Name of the MCP server that users are allowed to configure", + "type": "string", + "pattern": "^[a-zA-Z0-9_-]+$" + }, + "serverCommand": { + "description": "Command array [command, ...args] to match exactly for allowed stdio servers", + "minItems": 1, + "type": "array", + "items": { + "type": "string" + } + }, + "serverUrl": { + "description": "URL pattern with wildcard support (e.g., \"https://*.example.com/*\") for allowed remote MCP servers", + "type": "string" + } + }, + "additionalProperties": false + } + }, + "deniedMcpServers": { + "description": "Enterprise denylist of MCP servers that are explicitly blocked. If a server is on the denylist, it will be blocked across all scopes including enterprise. Denylist takes precedence over allowlist - if a server is on both lists, it is denied.", + "type": "array", + "items": { + "type": "object", + "properties": { + "serverName": { + "description": "Name of the MCP server that is explicitly blocked", + "type": "string", + "pattern": "^[a-zA-Z0-9_-]+$" + }, + "serverCommand": { + "description": "Command array [command, ...args] to match exactly for blocked stdio servers", + "minItems": 1, + "type": "array", + "items": { + "type": "string" + } + }, + "serverUrl": { + "description": "URL pattern with wildcard support (e.g., \"https://*.example.com/*\") for blocked remote MCP servers", + "type": "string" + } + }, + "additionalProperties": false + } + }, + "hooks": { + "description": "Custom commands to run before/after tool executions", + "type": "object", + "propertyNames": { + "anyOf": [ + { + "type": "string", + "enum": [ + "PreToolUse", + "PostToolUse", + "PostToolUseFailure", + "PostToolBatch", + "Notification", + "UserPromptSubmit", + "UserPromptExpansion", + "SessionStart", + "SessionEnd", + "Stop", + "StopFailure", + "SubagentStart", + "SubagentStop", + "PreCompact", + "PostCompact", + "PermissionRequest", + "PermissionDenied", + "Setup", + "TeammateIdle", + "TaskCreated", + "TaskCompleted", + "Elicitation", + "ElicitationResult", + "ConfigChange", + "WorktreeCreate", + "WorktreeRemove", + "InstructionsLoaded", + "CwdChanged", + "FileChanged", + "MessageDisplay" + ] + }, + { + "not": {} + } + ] + }, + "additionalProperties": { + "type": "array", + "items": { + "type": "object", + "properties": { + "matcher": { + "description": "String pattern to match (e.g. tool names like \"Write\")", + "type": "string" + }, + "hooks": { + "description": "List of hooks to execute when the matcher matches", + "type": "array", + "items": { + "anyOf": [ + { + "type": "object", + "properties": { + "type": { + "description": "Shell command hook type", + "type": "string", + "const": "command" + }, + "command": { + "description": "Shell command to execute", + "type": "string" + }, + "args": { + "description": "Argument list for exec form. When present, `command` is resolved as an executable and spawned directly with these arguments — no shell. Path placeholders like ${CLAUDE_PLUGIN_ROOT} are substituted per-element as plain strings, so paths with quotes, $, or backticks never reach a shell parser. When absent, `command` runs through a shell (bash on POSIX, PowerShell on Windows without Git Bash).", + "type": "array", + "items": { + "type": "string" + } + }, + "if": { + "description": "Permission rule syntax to filter when this hook runs (e.g., \"Bash(git *)\"). Only runs if the tool call matches the pattern. Avoids spawning hooks for non-matching commands.", + "type": "string" + }, + "shell": { + "description": "Shell interpreter. 'bash' uses your $SHELL (bash/zsh/sh); 'powershell' uses pwsh. Defaults to bash (powershell on Windows without Git Bash).", + "type": "string", + "enum": [ + "bash", + "powershell" + ] + }, + "timeout": { + "description": "Timeout in seconds for this specific command", + "type": "number", + "exclusiveMinimum": 0 + }, + "statusMessage": { + "description": "Custom status message to display in spinner while hook runs", + "type": "string" + }, + "once": { + "description": "If true, hook runs once and is removed after execution", + "type": "boolean" + }, + "async": { + "description": "If true, hook runs in background without blocking", + "type": "boolean" + }, + "asyncRewake": { + "description": "If true, hook runs in background and wakes the model on exit code 2 (blocking error). Implies async.", + "type": "boolean" + }, + "rewakeMessage": { + "description": "@internal Custom prefix for the system-reminder shown to the model when an asyncRewake hook exits with code 2. The hook output is appended after this prefix.", + "type": "string", + "minLength": 1 + }, + "rewakeSummary": { + "description": "@internal One-line summary shown to the user in the terminal when an asyncRewake hook exits with code 2. Defaults to \"Stop hook feedback\".", + "type": "string", + "minLength": 1 + } + }, + "required": [ + "type", + "command" + ], + "additionalProperties": false + }, + { + "type": "object", + "properties": { + "type": { + "description": "LLM prompt hook type", + "type": "string", + "const": "prompt" + }, + "prompt": { + "description": "Prompt to evaluate with LLM. Use $ARGUMENTS placeholder for hook input JSON.", + "type": "string" + }, + "if": { + "description": "Permission rule syntax to filter when this hook runs (e.g., \"Bash(git *)\"). Only runs if the tool call matches the pattern. Avoids spawning hooks for non-matching commands.", + "type": "string" + }, + "timeout": { + "description": "Timeout in seconds for this specific prompt evaluation", + "type": "number", + "exclusiveMinimum": 0 + }, + "model": { + "description": "Model to use for this prompt hook (e.g., \"claude-sonnet-4-6\"). If not specified, uses the default small fast model.", + "type": "string" + }, + "continueOnBlock": { + "description": "Sets the continue value for the decision:\"block\" produced when ok is false. Default false (turn ends). Whether continue:true lets the turn proceed depends on the event's decision:\"block\" semantics. On PostToolUse, the reason is fed back to Claude and the turn continues.", + "type": "boolean" + }, + "statusMessage": { + "description": "Custom status message to display in spinner while hook runs", + "type": "string" + }, + "once": { + "description": "If true, hook runs once and is removed after execution", + "type": "boolean" + } + }, + "required": [ + "type", + "prompt" + ], + "additionalProperties": false + }, + { + "type": "object", + "properties": { + "type": { + "description": "Agentic verifier hook type", + "type": "string", + "const": "agent" + }, + "prompt": { + "description": "Prompt describing what to verify (e.g. \"Verify that unit tests ran and passed.\"). Use $ARGUMENTS placeholder for hook input JSON.", + "type": "string" + }, + "if": { + "description": "Permission rule syntax to filter when this hook runs (e.g., \"Bash(git *)\"). Only runs if the tool call matches the pattern. Avoids spawning hooks for non-matching commands.", + "type": "string" + }, + "timeout": { + "description": "Timeout in seconds for agent execution (default 60)", + "type": "number", + "exclusiveMinimum": 0 + }, + "model": { + "description": "Model to use for this agent hook (e.g., \"claude-sonnet-4-6\"). If not specified, uses Haiku.", + "type": "string" + }, + "statusMessage": { + "description": "Custom status message to display in spinner while hook runs", + "type": "string" + }, + "once": { + "description": "If true, hook runs once and is removed after execution", + "type": "boolean" + } + }, + "required": [ + "type", + "prompt" + ], + "additionalProperties": false + }, + { + "type": "object", + "properties": { + "type": { + "description": "HTTP hook type", + "type": "string", + "const": "http" + }, + "url": { + "description": "URL to POST the hook input JSON to", + "type": "string", + "format": "uri" + }, + "if": { + "description": "Permission rule syntax to filter when this hook runs (e.g., \"Bash(git *)\"). Only runs if the tool call matches the pattern. Avoids spawning hooks for non-matching commands.", + "type": "string" + }, + "timeout": { + "description": "Timeout in seconds for this specific request", + "type": "number", + "exclusiveMinimum": 0 + }, + "headers": { + "description": "Additional headers to include in the request. Values may reference environment variables using $VAR_NAME or ${VAR_NAME} syntax (e.g., \"Authorization\": \"Bearer $MY_TOKEN\"). Only variables listed in allowedEnvVars will be interpolated.", + "type": "object", + "propertyNames": { + "type": "string" + }, + "additionalProperties": { + "type": "string" + } + }, + "allowedEnvVars": { + "description": "Explicit list of environment variable names that may be interpolated in header values. Only variables listed here will be resolved; all other $VAR references are left as empty strings. Required for env var interpolation to work.", + "type": "array", + "items": { + "type": "string" + } + }, + "statusMessage": { + "description": "Custom status message to display in spinner while hook runs", + "type": "string" + }, + "once": { + "description": "If true, hook runs once and is removed after execution", + "type": "boolean" + } + }, + "required": [ + "type", + "url" + ], + "additionalProperties": false + }, + { + "type": "object", + "properties": { + "type": { + "description": "MCP tool hook type", + "type": "string", + "const": "mcp_tool" + }, + "server": { + "description": "Name of an already-configured MCP server to invoke", + "type": "string" + }, + "tool": { + "description": "Name of the tool on that server to call", + "type": "string" + }, + "input": { + "description": "Arguments passed to the MCP tool. String values support ${path} interpolation from the hook input JSON (e.g. \"${tool_input.file_path}\").", + "type": "object", + "propertyNames": { + "type": "string" + }, + "additionalProperties": {} + }, + "if": { + "description": "Permission rule syntax to filter when this hook runs (e.g., \"Bash(git *)\"). Only runs if the tool call matches the pattern. Avoids spawning hooks for non-matching commands.", + "type": "string" + }, + "timeout": { + "description": "Timeout in seconds for this specific tool call", + "type": "number", + "exclusiveMinimum": 0 + }, + "statusMessage": { + "description": "Custom status message to display in spinner while hook runs", + "type": "string" + }, + "once": { + "description": "If true, hook runs once and is removed after execution", + "type": "boolean" + } + }, + "required": [ + "type", + "server", + "tool" + ], + "additionalProperties": false + } + ] + } + } + }, + "required": [ + "hooks" + ], + "additionalProperties": false + } + } + }, + "worktree": { + "description": "Git worktree configuration for --worktree flag.", + "type": "object", + "properties": { + "symlinkDirectories": { + "description": "Directories to symlink from main repository to worktrees to avoid disk bloat. Must be explicitly configured - no directories are symlinked by default. Common examples: \"node_modules\", \".cache\", \".bin\"", + "type": "array", + "items": { + "type": "string" + } + }, + "sparsePaths": { + "description": "Directories to include when creating worktrees, via git sparse-checkout (cone mode). Dramatically faster in large monorepos — only the listed paths are written to disk.", + "type": "array", + "items": { + "type": "string" + } + }, + "baseRef": { + "description": "Which ref new worktrees branch from. 'fresh' (default) branches from origin/ for a clean tree. 'head' branches from your current local HEAD so unpushed commits and feature-branch state are present. Applies to --worktree, EnterWorktree, and agent isolation.", + "type": "string", + "enum": [ + "fresh", + "head" + ] + }, + "bgIsolation": { + "description": "Isolation mode for background sessions in this repo. 'worktree' (default) blocks Edit/Write in the main checkout until EnterWorktree is called. 'none' lets background jobs edit the working copy directly.", + "type": "string", + "enum": [ + "worktree", + "none" + ] + } + }, + "additionalProperties": false + }, + "disableAllHooks": { + "description": "Disable all hooks and statusLine execution", + "type": "boolean" + }, + "disableAgentView": { + "description": "Disable agent view (`claude agents`, `--bg`, /background, the on-demand daemon). Typically set in managed settings. Equivalent to CLAUDE_CODE_DISABLE_AGENT_VIEW=1.", + "type": "boolean" + }, + "disableRemoteControl": { + "description": "Disable Remote Control (claude.ai/code, `claude remote-control`, `--remote-control`/`--rc`, auto-start, and the in-session toggle). Typically set in managed settings.", + "type": "boolean" + }, + "disableWorkflows": { + "description": "Disable the Workflows feature (also via CLAUDE_CODE_DISABLE_WORKFLOWS).", + "type": "boolean" + }, + "disableArtifact": { + "description": "Disable the Artifact tool (also via CLAUDE_CODE_DISABLE_ARTIFACT).", + "type": "boolean" + }, + "enableWorkflows": { + "description": "Enable or disable the Workflows feature for this user. Unset = default by plan once the feature is available.", + "type": "boolean" + }, + "workflowKeywordTriggerEnabled": { + "description": "Enable the \"ultracode\" keyword trigger: including the keyword in a prompt opts that turn into the Workflow tool. Set to false to disable the trigger. Default: true.", + "type": "boolean" + }, + "disableSkillShellExecution": { + "description": "Disable inline shell execution in skills and custom slash commands from user, project, or plugin sources. Commands are replaced with a placeholder instead of being run.", + "type": "boolean" + }, + "defaultShell": { + "description": "Default shell for input-box ! commands. Defaults to 'bash' on all platforms (no Windows auto-flip).", + "type": "string", + "enum": [ + "bash", + "powershell" + ] + }, + "allowManagedHooksOnly": { + "description": "When true (and set in managed settings), only hooks from managed settings run. User, project, and local hooks are ignored.", + "type": "boolean" + }, + "allowedHttpHookUrls": { + "description": "Allowlist of URL patterns that HTTP hooks may target. Supports * as a wildcard (e.g. \"https://hooks.example.com/*\"). When set, HTTP hooks with non-matching URLs are blocked. If undefined, all URLs are allowed. If empty array, no HTTP hooks are allowed. Arrays merge across settings sources (same semantics as allowedMcpServers).", + "type": "array", + "items": { + "type": "string" + } + }, + "httpHookAllowedEnvVars": { + "description": "Allowlist of environment variable names HTTP hooks may interpolate into headers. When set, each hook's effective allowedEnvVars is the intersection with this list. If undefined, no restriction is applied. Arrays merge across settings sources (same semantics as allowedMcpServers).", + "type": "array", + "items": { + "type": "string" + } + }, + "allowManagedPermissionRulesOnly": { + "description": "When true (and set in managed settings), only permission rules (allow/deny/ask) from managed settings are respected. User, project, local, and CLI argument permission rules are ignored.", + "type": "boolean" + }, + "allowManagedMcpServersOnly": { + "description": "When true (and set in managed settings), allowedMcpServers is only read from managed settings. deniedMcpServers still merges from all sources, so users can deny servers for themselves. Users can still add their own MCP servers, but only the admin-defined allowlist applies.", + "type": "boolean" + }, + "allowAllClaudeAiMcps": { + "description": "When true (and set in managed settings), claude.ai cloud MCP connectors load alongside managed-mcp.json instead of being suppressed by its exclusive-control lockdown. Default off preserves the lockdown. Read from managed settings only.", + "type": "boolean" + }, + "strictPluginOnlyCustomization": { + "description": "When set in managed settings, blocks non-plugin customization sources for the listed surfaces. Array form locks specific surfaces (e.g. [\"skills\", \"hooks\"]); `true` locks all four; `false` is an explicit no-op. Blocked: ~/.claude/{surface}/, .claude/{surface}/ (project), settings.json hooks, .mcp.json. NOT blocked: managed (policySettings) sources, plugin-provided customizations. Composes with strictKnownMarketplaces for end-to-end admin control — plugins gated by marketplace allowlist, everything else blocked here.", + "anyOf": [ + { + "type": "boolean" + }, + { + "type": "array", + "items": { + "type": "string", + "enum": [ + "skills", + "agents", + "hooks", + "mcp" + ] + } + } + ] + }, + "statusLine": { + "description": "Custom status line display configuration", + "type": "object", + "properties": { + "type": { + "type": "string", + "const": "command" + }, + "command": { + "type": "string" + }, + "padding": { + "type": "number" + }, + "refreshInterval": { + "description": "Re-run the status line command every N seconds in addition to event-driven updates", + "type": "number", + "minimum": 1 + }, + "hideVimModeIndicator": { + "description": "Hide the built-in `-- INSERT --` / `-- VISUAL --` indicator below the prompt. Use this when your status line script renders `vim.mode` itself.", + "type": "boolean" + } + }, + "required": [ + "type", + "command" + ], + "additionalProperties": false + }, + "prUrlTemplate": { + "description": "URL template for PR links in the footer link badges and inline messages. The detected git PR is rendered as the first footer-link badge. Placeholders: {host} {owner} {repo} {number} {url}. Example: \"https://reviews.example.com/{owner}/{repo}/pull/{number}\"", + "type": "string" + }, + "footerLinksRegexes": { + "description": "Extra clickable footer badges that appear when a regex matches turn output (tool results and assistant responses). Read from user, flag, and managed settings only; ignored in project .claude/settings.json and local .claude/settings.local.json. At most 5 badges render; the oldest is displaced by newer matches and /clear removes them. Use to surface IDs printed by project CLIs as session links." + }, + "subagentStatusLine": { + "description": "Custom per-subagent status line shown in the agent panel; receives row context as JSON on stdin", + "type": "object", + "properties": { + "type": { + "type": "string", + "const": "command" + }, + "command": { + "type": "string" + } + }, + "required": [ + "type", + "command" + ], + "additionalProperties": false + }, + "enabledPlugins": { + "description": "Enabled plugins using plugin-id@marketplace-id format. Example: { \"formatter@anthropic-tools\": true }. Also supports extended format with version constraints. Settings precedence is user < project < local < flag < policy, so to disable a plugin that project settings enable, set it to false in .claude/settings.local.json — setting false in ~/.claude/settings.json is overridden by the project.", + "type": "object", + "propertyNames": { + "type": "string" + }, + "additionalProperties": { + "anyOf": [ + { + "type": "array", + "items": { + "type": "string" + } + }, + { + "type": "boolean" + }, + { + "not": {} + } + ] + } + }, + "extraKnownMarketplaces": { + "description": "Additional marketplaces to make available for this repository. Typically used in repository .claude/settings.json to ensure team members have required plugin sources.", + "type": "object", + "propertyNames": { + "type": "string" + }, + "additionalProperties": { + "type": "object", + "properties": { + "source": { + "description": "Where to fetch the marketplace from", + "anyOf": [ + { + "type": "object", + "properties": { + "source": { + "type": "string", + "const": "url" + }, + "url": { + "description": "Direct URL to marketplace.json file", + "type": "string", + "format": "uri" + }, + "headers": { + "description": "Custom HTTP headers (e.g., for authentication)", + "type": "object", + "propertyNames": { + "type": "string" + }, + "additionalProperties": { + "type": "string" + } + } + }, + "required": [ + "source", + "url" + ], + "additionalProperties": false + }, + { + "type": "object", + "properties": { + "source": { + "type": "string", + "const": "github" + }, + "repo": { + "description": "GitHub repository in owner/repo format", + "type": "string" + }, + "ref": { + "description": "Git branch or tag to use (e.g., \"main\", \"v1.0.0\"). Defaults to repository default branch.", + "type": "string" + }, + "path": { + "description": "Path to marketplace.json within repo (defaults to .claude-plugin/marketplace.json)", + "type": "string" + }, + "sparsePaths": { + "description": "Directories to include via git sparse-checkout (cone mode). Use for monorepos where the marketplace lives in a subdirectory. Example: [\".claude-plugin\", \"plugins\"]. If omitted, the full repository is cloned.", + "type": "array", + "items": { + "type": "string" + } + }, + "skipLfs": { + "description": "Skip Git LFS smudge during clone and update (sets GIT_LFS_SKIP_SMUDGE=1) so LFS pointer files stay as pointers instead of downloading their content. Use for marketplaces hosted in repos with large LFS objects.", + "type": "boolean" + } + }, + "required": [ + "source", + "repo" + ], + "additionalProperties": false + }, + { + "type": "object", + "properties": { + "source": { + "type": "string", + "const": "git" + }, + "url": { + "description": "Full git repository URL", + "type": "string" + }, + "ref": { + "description": "Git branch or tag to use (e.g., \"main\", \"v1.0.0\"). Defaults to repository default branch.", + "type": "string" + }, + "path": { + "description": "Path to marketplace.json within repo (defaults to .claude-plugin/marketplace.json)", + "type": "string" + }, + "sparsePaths": { + "description": "Directories to include via git sparse-checkout (cone mode). Use for monorepos where the marketplace lives in a subdirectory. Example: [\".claude-plugin\", \"plugins\"]. If omitted, the full repository is cloned.", + "type": "array", + "items": { + "type": "string" + } + }, + "skipLfs": { + "description": "Skip Git LFS smudge during clone and update (sets GIT_LFS_SKIP_SMUDGE=1) so LFS pointer files stay as pointers instead of downloading their content. Use for marketplaces hosted in repos with large LFS objects.", + "type": "boolean" + } + }, + "required": [ + "source", + "url" + ], + "additionalProperties": false + }, + { + "type": "object", + "properties": { + "source": { + "type": "string", + "const": "npm" + }, + "package": { + "description": "NPM package containing marketplace.json", + "type": "string" + } + }, + "required": [ + "source", + "package" + ], + "additionalProperties": false + }, + { + "type": "object", + "properties": { + "source": { + "type": "string", + "const": "file" + }, + "path": { + "description": "Local file path to marketplace.json", + "type": "string" + } + }, + "required": [ + "source", + "path" + ], + "additionalProperties": false + }, + { + "type": "object", + "properties": { + "source": { + "type": "string", + "const": "directory" + }, + "path": { + "description": "Local directory containing .claude-plugin/marketplace.json", + "type": "string" + } + }, + "required": [ + "source", + "path" + ], + "additionalProperties": false + }, + { + "description": "Policy-list sentinel for the ~/.claude/skills/ auto-load (@skills-dir plugins). In strictKnownMarketplaces: opt the scan back IN (by default any allowlist blocks it). In blockedMarketplaces: turn the scan OFF without otherwise restricting marketplaces. Only meaningful in those two managed-settings lists (areLocalPluginDirsAllowedByPolicy); known_marketplaces.json / marketplace add etc. ignore it.", + "type": "object", + "properties": { + "source": { + "type": "string", + "const": "skills-dir" + } + }, + "required": [ + "source" + ], + "additionalProperties": false + }, + { + "type": "object", + "properties": { + "source": { + "type": "string", + "const": "hostPattern" + }, + "hostPattern": { + "description": "Regex pattern to match the host/domain extracted from any marketplace source type. For github sources, matches against \"github.com\". For git sources (SSH or HTTPS), extracts the hostname from the URL. Use in strictKnownMarketplaces to allow all marketplaces from a specific host (e.g., \"^github\\.mycompany\\.com$\").", + "type": "string" + } + }, + "required": [ + "source", + "hostPattern" + ], + "additionalProperties": false + }, + { + "type": "object", + "properties": { + "source": { + "type": "string", + "const": "pathPattern" + }, + "pathPattern": { + "description": "Regex pattern matched against the .path field of file and directory sources. Use in strictKnownMarketplaces to allow filesystem-based marketplaces alongside hostPattern restrictions for network sources. Use \".*\" to allow all filesystem paths, or a narrower pattern (e.g., \"^/opt/approved/\") to restrict to specific directories.", + "type": "string" + } + }, + "required": [ + "source", + "pathPattern" + ], + "additionalProperties": false + }, + { + "description": "Inline marketplace manifest defined directly in settings.json. The reconciler writes a synthetic marketplace.json to the cache; diffMarketplaces detects edits via isEqual on the stored source (the plugins array is inside this object, so edits surface as sourceChanged).", + "type": "object", + "properties": { + "source": { + "type": "string", + "const": "settings" + }, + "name": { + "description": "Marketplace name. Must match the extraKnownMarketplaces key (enforced); the synthetic manifest is written under this name. Same validation as PluginMarketplaceSchema plus reserved-name rejection — validateOfficialNameSource runs after the disk write, too late to clean up.", + "type": "string", + "minLength": 1 + }, + "plugins": { + "description": "Plugin entries declared inline in settings.json", + "type": "array", + "items": { + "type": "object", + "properties": { + "name": { + "description": "Plugin name as it appears in the target repository", + "type": "string", + "minLength": 1 + }, + "source": { + "description": "Where to fetch the plugin from. Must be a remote source — relative paths have no marketplace repository to resolve against.", + "anyOf": [ + { + "description": "Path to the plugin root, relative to the marketplace root (the directory containing .claude-plugin/, not .claude-plugin/ itself)", + "type": "string", + "pattern": "^\\.\\/.*" + }, + { + "description": "NPM package as plugin source", + "type": "object", + "properties": { + "source": { + "type": "string", + "const": "npm" + }, + "package": { + "description": "Package name (or url, or local path, or anything else that can be passed to `npm` as a package)", + "anyOf": [ + { + "type": "string" + }, + { + "type": "string" + } + ] + }, + "version": { + "description": "Specific version or version range (e.g., ^1.0.0, ~2.1.0)", + "type": "string" + }, + "registry": { + "description": "Custom NPM registry URL (defaults to using system default, likely npmjs.org)", + "type": "string", + "format": "uri" + } + }, + "required": [ + "source", + "package" + ], + "additionalProperties": false + }, + { + "type": "object", + "properties": { + "source": { + "type": "string", + "const": "url" + }, + "url": { + "description": "Full git repository URL (https:// or git@)", + "type": "string" + }, + "ref": { + "description": "Git branch or tag to use (e.g., \"main\", \"v1.0.0\"). Defaults to repository default branch.", + "type": "string" + }, + "sha": { + "description": "Specific commit SHA to use", + "type": "string", + "minLength": 40, + "maxLength": 40, + "pattern": "^[a-f0-9]{40}$" + } + }, + "required": [ + "source", + "url" + ], + "additionalProperties": false + }, + { + "type": "object", + "properties": { + "source": { + "type": "string", + "const": "github" + }, + "repo": { + "description": "GitHub repository in owner/repo format", + "type": "string" + }, + "ref": { + "description": "Git branch or tag to use (e.g., \"main\", \"v1.0.0\"). Defaults to repository default branch.", + "type": "string" + }, + "sha": { + "description": "Specific commit SHA to use", + "type": "string", + "minLength": 40, + "maxLength": 40, + "pattern": "^[a-f0-9]{40}$" + } + }, + "required": [ + "source", + "repo" + ], + "additionalProperties": false + }, + { + "description": "Plugin located in a subdirectory of a larger repository (monorepo). Only the specified subdirectory is materialized; the rest of the repo is not downloaded.", + "type": "object", + "properties": { + "source": { + "type": "string", + "const": "git-subdir" + }, + "url": { + "description": "Git repository: GitHub owner/repo shorthand, https://, or git@ URL", + "type": "string" + }, + "path": { + "description": "Subdirectory within the repo containing the plugin (e.g., \"tools/claude-plugin\"). Cloned sparsely using partial clone (--filter=tree:0) to minimize bandwidth for monorepos.", + "type": "string", + "minLength": 1 + }, + "ref": { + "description": "Git branch or tag to use (e.g., \"main\", \"v1.0.0\"). Defaults to repository default branch.", + "type": "string" + }, + "sha": { + "description": "Specific commit SHA to use", + "type": "string", + "minLength": 40, + "maxLength": 40, + "pattern": "^[a-f0-9]{40}$" + } + }, + "required": [ + "source", + "url", + "path" + ], + "additionalProperties": false + }, + { + "description": "Placeholder for source types this Claude Code version does not recognize. Never authored by hand — PluginMarketplaceSchema rewrites unparseable sources to this so the entry remains in marketplace.plugins (detectDelistedPlugins must not see it as removed). Install attempts fail at cachePlugin with a clear \"update Claude Code\" message.", + "type": "object", + "properties": { + "source": { + "type": "string", + "const": "unsupported" + } + }, + "required": [ + "source" + ], + "additionalProperties": false + } + ] + }, + "description": { + "type": "string" + }, + "version": { + "type": "string" + }, + "strict": { + "type": "boolean" + } + }, + "required": [ + "name", + "source" + ], + "additionalProperties": false + } + }, + "owner": { + "type": "object", + "properties": { + "name": { + "description": "Display name of the plugin author or organization", + "type": "string", + "minLength": 1 + }, + "email": { + "description": "Contact email for support or feedback", + "type": "string" + }, + "url": { + "description": "Website, GitHub profile, or organization URL", + "type": "string" + } + }, + "required": [ + "name" + ], + "additionalProperties": false + } + }, + "required": [ + "source", + "name", + "plugins" + ], + "additionalProperties": false + } + ] + }, + "installLocation": { + "description": "Local cache path where marketplace manifest is stored (auto-generated if not provided)", + "type": "string" + }, + "autoUpdate": { + "description": "Whether to automatically update this marketplace and its installed plugins on startup", + "type": "boolean" + } + }, + "required": [ + "source" + ], + "additionalProperties": false + } + }, + "strictKnownMarketplaces": { + "description": "Enterprise strict list of allowed marketplace sources. When set in managed settings, ONLY these exact sources can be added as marketplaces. The check happens BEFORE downloading, so blocked sources never touch the filesystem. Note: this is a policy gate only — it does NOT register marketplaces. To pre-register allowed marketplaces for users, also set extraKnownMarketplaces.", + "type": "array", + "items": { + "anyOf": [ + { + "type": "object", + "properties": { + "source": { + "type": "string", + "const": "url" + }, + "url": { + "description": "Direct URL to marketplace.json file", + "type": "string", + "format": "uri" + }, + "headers": { + "description": "Custom HTTP headers (e.g., for authentication)", + "type": "object", + "propertyNames": { + "type": "string" + }, + "additionalProperties": { + "type": "string" + } + } + }, + "required": [ + "source", + "url" + ], + "additionalProperties": false + }, + { + "type": "object", + "properties": { + "source": { + "type": "string", + "const": "github" + }, + "repo": { + "description": "GitHub repository in owner/repo format", + "type": "string" + }, + "ref": { + "description": "Git branch or tag to use (e.g., \"main\", \"v1.0.0\"). Defaults to repository default branch.", + "type": "string" + }, + "path": { + "description": "Path to marketplace.json within repo (defaults to .claude-plugin/marketplace.json)", + "type": "string" + }, + "sparsePaths": { + "description": "Directories to include via git sparse-checkout (cone mode). Use for monorepos where the marketplace lives in a subdirectory. Example: [\".claude-plugin\", \"plugins\"]. If omitted, the full repository is cloned.", + "type": "array", + "items": { + "type": "string" + } + }, + "skipLfs": { + "description": "Skip Git LFS smudge during clone and update (sets GIT_LFS_SKIP_SMUDGE=1) so LFS pointer files stay as pointers instead of downloading their content. Use for marketplaces hosted in repos with large LFS objects.", + "type": "boolean" + } + }, + "required": [ + "source", + "repo" + ], + "additionalProperties": false + }, + { + "type": "object", + "properties": { + "source": { + "type": "string", + "const": "git" + }, + "url": { + "description": "Full git repository URL", + "type": "string" + }, + "ref": { + "description": "Git branch or tag to use (e.g., \"main\", \"v1.0.0\"). Defaults to repository default branch.", + "type": "string" + }, + "path": { + "description": "Path to marketplace.json within repo (defaults to .claude-plugin/marketplace.json)", + "type": "string" + }, + "sparsePaths": { + "description": "Directories to include via git sparse-checkout (cone mode). Use for monorepos where the marketplace lives in a subdirectory. Example: [\".claude-plugin\", \"plugins\"]. If omitted, the full repository is cloned.", + "type": "array", + "items": { + "type": "string" + } + }, + "skipLfs": { + "description": "Skip Git LFS smudge during clone and update (sets GIT_LFS_SKIP_SMUDGE=1) so LFS pointer files stay as pointers instead of downloading their content. Use for marketplaces hosted in repos with large LFS objects.", + "type": "boolean" + } + }, + "required": [ + "source", + "url" + ], + "additionalProperties": false + }, + { + "type": "object", + "properties": { + "source": { + "type": "string", + "const": "npm" + }, + "package": { + "description": "NPM package containing marketplace.json", + "type": "string" + } + }, + "required": [ + "source", + "package" + ], + "additionalProperties": false + }, + { + "type": "object", + "properties": { + "source": { + "type": "string", + "const": "file" + }, + "path": { + "description": "Local file path to marketplace.json", + "type": "string" + } + }, + "required": [ + "source", + "path" + ], + "additionalProperties": false + }, + { + "type": "object", + "properties": { + "source": { + "type": "string", + "const": "directory" + }, + "path": { + "description": "Local directory containing .claude-plugin/marketplace.json", + "type": "string" + } + }, + "required": [ + "source", + "path" + ], + "additionalProperties": false + }, + { + "description": "Policy-list sentinel for the ~/.claude/skills/ auto-load (@skills-dir plugins). In strictKnownMarketplaces: opt the scan back IN (by default any allowlist blocks it). In blockedMarketplaces: turn the scan OFF without otherwise restricting marketplaces. Only meaningful in those two managed-settings lists (areLocalPluginDirsAllowedByPolicy); known_marketplaces.json / marketplace add etc. ignore it.", + "type": "object", + "properties": { + "source": { + "type": "string", + "const": "skills-dir" + } + }, + "required": [ + "source" + ], + "additionalProperties": false + }, + { + "type": "object", + "properties": { + "source": { + "type": "string", + "const": "hostPattern" + }, + "hostPattern": { + "description": "Regex pattern to match the host/domain extracted from any marketplace source type. For github sources, matches against \"github.com\". For git sources (SSH or HTTPS), extracts the hostname from the URL. Use in strictKnownMarketplaces to allow all marketplaces from a specific host (e.g., \"^github\\.mycompany\\.com$\").", + "type": "string" + } + }, + "required": [ + "source", + "hostPattern" + ], + "additionalProperties": false + }, + { + "type": "object", + "properties": { + "source": { + "type": "string", + "const": "pathPattern" + }, + "pathPattern": { + "description": "Regex pattern matched against the .path field of file and directory sources. Use in strictKnownMarketplaces to allow filesystem-based marketplaces alongside hostPattern restrictions for network sources. Use \".*\" to allow all filesystem paths, or a narrower pattern (e.g., \"^/opt/approved/\") to restrict to specific directories.", + "type": "string" + } + }, + "required": [ + "source", + "pathPattern" + ], + "additionalProperties": false + }, + { + "description": "Inline marketplace manifest defined directly in settings.json. The reconciler writes a synthetic marketplace.json to the cache; diffMarketplaces detects edits via isEqual on the stored source (the plugins array is inside this object, so edits surface as sourceChanged).", + "type": "object", + "properties": { + "source": { + "type": "string", + "const": "settings" + }, + "name": { + "description": "Marketplace name. Must match the extraKnownMarketplaces key (enforced); the synthetic manifest is written under this name. Same validation as PluginMarketplaceSchema plus reserved-name rejection — validateOfficialNameSource runs after the disk write, too late to clean up.", + "type": "string", + "minLength": 1 + }, + "plugins": { + "description": "Plugin entries declared inline in settings.json", + "type": "array", + "items": { + "type": "object", + "properties": { + "name": { + "description": "Plugin name as it appears in the target repository", + "type": "string", + "minLength": 1 + }, + "source": { + "description": "Where to fetch the plugin from. Must be a remote source — relative paths have no marketplace repository to resolve against.", + "anyOf": [ + { + "description": "Path to the plugin root, relative to the marketplace root (the directory containing .claude-plugin/, not .claude-plugin/ itself)", + "type": "string", + "pattern": "^\\.\\/.*" + }, + { + "description": "NPM package as plugin source", + "type": "object", + "properties": { + "source": { + "type": "string", + "const": "npm" + }, + "package": { + "description": "Package name (or url, or local path, or anything else that can be passed to `npm` as a package)", + "anyOf": [ + { + "type": "string" + }, + { + "type": "string" + } + ] + }, + "version": { + "description": "Specific version or version range (e.g., ^1.0.0, ~2.1.0)", + "type": "string" + }, + "registry": { + "description": "Custom NPM registry URL (defaults to using system default, likely npmjs.org)", + "type": "string", + "format": "uri" + } + }, + "required": [ + "source", + "package" + ], + "additionalProperties": false + }, + { + "type": "object", + "properties": { + "source": { + "type": "string", + "const": "url" + }, + "url": { + "description": "Full git repository URL (https:// or git@)", + "type": "string" + }, + "ref": { + "description": "Git branch or tag to use (e.g., \"main\", \"v1.0.0\"). Defaults to repository default branch.", + "type": "string" + }, + "sha": { + "description": "Specific commit SHA to use", + "type": "string", + "minLength": 40, + "maxLength": 40, + "pattern": "^[a-f0-9]{40}$" + } + }, + "required": [ + "source", + "url" + ], + "additionalProperties": false + }, + { + "type": "object", + "properties": { + "source": { + "type": "string", + "const": "github" + }, + "repo": { + "description": "GitHub repository in owner/repo format", + "type": "string" + }, + "ref": { + "description": "Git branch or tag to use (e.g., \"main\", \"v1.0.0\"). Defaults to repository default branch.", + "type": "string" + }, + "sha": { + "description": "Specific commit SHA to use", + "type": "string", + "minLength": 40, + "maxLength": 40, + "pattern": "^[a-f0-9]{40}$" + } + }, + "required": [ + "source", + "repo" + ], + "additionalProperties": false + }, + { + "description": "Plugin located in a subdirectory of a larger repository (monorepo). Only the specified subdirectory is materialized; the rest of the repo is not downloaded.", + "type": "object", + "properties": { + "source": { + "type": "string", + "const": "git-subdir" + }, + "url": { + "description": "Git repository: GitHub owner/repo shorthand, https://, or git@ URL", + "type": "string" + }, + "path": { + "description": "Subdirectory within the repo containing the plugin (e.g., \"tools/claude-plugin\"). Cloned sparsely using partial clone (--filter=tree:0) to minimize bandwidth for monorepos.", + "type": "string", + "minLength": 1 + }, + "ref": { + "description": "Git branch or tag to use (e.g., \"main\", \"v1.0.0\"). Defaults to repository default branch.", + "type": "string" + }, + "sha": { + "description": "Specific commit SHA to use", + "type": "string", + "minLength": 40, + "maxLength": 40, + "pattern": "^[a-f0-9]{40}$" + } + }, + "required": [ + "source", + "url", + "path" + ], + "additionalProperties": false + }, + { + "description": "Placeholder for source types this Claude Code version does not recognize. Never authored by hand — PluginMarketplaceSchema rewrites unparseable sources to this so the entry remains in marketplace.plugins (detectDelistedPlugins must not see it as removed). Install attempts fail at cachePlugin with a clear \"update Claude Code\" message.", + "type": "object", + "properties": { + "source": { + "type": "string", + "const": "unsupported" + } + }, + "required": [ + "source" + ], + "additionalProperties": false + } + ] + }, + "description": { + "type": "string" + }, + "version": { + "type": "string" + }, + "strict": { + "type": "boolean" + } + }, + "required": [ + "name", + "source" + ], + "additionalProperties": false + } + }, + "owner": { + "type": "object", + "properties": { + "name": { + "description": "Display name of the plugin author or organization", + "type": "string", + "minLength": 1 + }, + "email": { + "description": "Contact email for support or feedback", + "type": "string" + }, + "url": { + "description": "Website, GitHub profile, or organization URL", + "type": "string" + } + }, + "required": [ + "name" + ], + "additionalProperties": false + } + }, + "required": [ + "source", + "name", + "plugins" + ], + "additionalProperties": false + } + ] + } + }, + "blockedMarketplaces": { + "description": "Enterprise blocklist of marketplace sources. When set in managed settings, these exact sources are blocked from being added as marketplaces. The check happens BEFORE downloading, so blocked sources never touch the filesystem.", + "type": "array", + "items": { + "anyOf": [ + { + "type": "object", + "properties": { + "source": { + "type": "string", + "const": "url" + }, + "url": { + "description": "Direct URL to marketplace.json file", + "type": "string", + "format": "uri" + }, + "headers": { + "description": "Custom HTTP headers (e.g., for authentication)", + "type": "object", + "propertyNames": { + "type": "string" + }, + "additionalProperties": { + "type": "string" + } + } + }, + "required": [ + "source", + "url" + ], + "additionalProperties": false + }, + { + "type": "object", + "properties": { + "source": { + "type": "string", + "const": "github" + }, + "repo": { + "description": "GitHub repository in owner/repo format", + "type": "string" + }, + "ref": { + "description": "Git branch or tag to use (e.g., \"main\", \"v1.0.0\"). Defaults to repository default branch.", + "type": "string" + }, + "path": { + "description": "Path to marketplace.json within repo (defaults to .claude-plugin/marketplace.json)", + "type": "string" + }, + "sparsePaths": { + "description": "Directories to include via git sparse-checkout (cone mode). Use for monorepos where the marketplace lives in a subdirectory. Example: [\".claude-plugin\", \"plugins\"]. If omitted, the full repository is cloned.", + "type": "array", + "items": { + "type": "string" + } + }, + "skipLfs": { + "description": "Skip Git LFS smudge during clone and update (sets GIT_LFS_SKIP_SMUDGE=1) so LFS pointer files stay as pointers instead of downloading their content. Use for marketplaces hosted in repos with large LFS objects.", + "type": "boolean" + } + }, + "required": [ + "source", + "repo" + ], + "additionalProperties": false + }, + { + "type": "object", + "properties": { + "source": { + "type": "string", + "const": "git" + }, + "url": { + "description": "Full git repository URL", + "type": "string" + }, + "ref": { + "description": "Git branch or tag to use (e.g., \"main\", \"v1.0.0\"). Defaults to repository default branch.", + "type": "string" + }, + "path": { + "description": "Path to marketplace.json within repo (defaults to .claude-plugin/marketplace.json)", + "type": "string" + }, + "sparsePaths": { + "description": "Directories to include via git sparse-checkout (cone mode). Use for monorepos where the marketplace lives in a subdirectory. Example: [\".claude-plugin\", \"plugins\"]. If omitted, the full repository is cloned.", + "type": "array", + "items": { + "type": "string" + } + }, + "skipLfs": { + "description": "Skip Git LFS smudge during clone and update (sets GIT_LFS_SKIP_SMUDGE=1) so LFS pointer files stay as pointers instead of downloading their content. Use for marketplaces hosted in repos with large LFS objects.", + "type": "boolean" + } + }, + "required": [ + "source", + "url" + ], + "additionalProperties": false + }, + { + "type": "object", + "properties": { + "source": { + "type": "string", + "const": "npm" + }, + "package": { + "description": "NPM package containing marketplace.json", + "type": "string" + } + }, + "required": [ + "source", + "package" + ], + "additionalProperties": false + }, + { + "type": "object", + "properties": { + "source": { + "type": "string", + "const": "file" + }, + "path": { + "description": "Local file path to marketplace.json", + "type": "string" + } + }, + "required": [ + "source", + "path" + ], + "additionalProperties": false + }, + { + "type": "object", + "properties": { + "source": { + "type": "string", + "const": "directory" + }, + "path": { + "description": "Local directory containing .claude-plugin/marketplace.json", + "type": "string" + } + }, + "required": [ + "source", + "path" + ], + "additionalProperties": false + }, + { + "description": "Policy-list sentinel for the ~/.claude/skills/ auto-load (@skills-dir plugins). In strictKnownMarketplaces: opt the scan back IN (by default any allowlist blocks it). In blockedMarketplaces: turn the scan OFF without otherwise restricting marketplaces. Only meaningful in those two managed-settings lists (areLocalPluginDirsAllowedByPolicy); known_marketplaces.json / marketplace add etc. ignore it.", + "type": "object", + "properties": { + "source": { + "type": "string", + "const": "skills-dir" + } + }, + "required": [ + "source" + ], + "additionalProperties": false + }, + { + "type": "object", + "properties": { + "source": { + "type": "string", + "const": "hostPattern" + }, + "hostPattern": { + "description": "Regex pattern to match the host/domain extracted from any marketplace source type. For github sources, matches against \"github.com\". For git sources (SSH or HTTPS), extracts the hostname from the URL. Use in strictKnownMarketplaces to allow all marketplaces from a specific host (e.g., \"^github\\.mycompany\\.com$\").", + "type": "string" + } + }, + "required": [ + "source", + "hostPattern" + ], + "additionalProperties": false + }, + { + "type": "object", + "properties": { + "source": { + "type": "string", + "const": "pathPattern" + }, + "pathPattern": { + "description": "Regex pattern matched against the .path field of file and directory sources. Use in strictKnownMarketplaces to allow filesystem-based marketplaces alongside hostPattern restrictions for network sources. Use \".*\" to allow all filesystem paths, or a narrower pattern (e.g., \"^/opt/approved/\") to restrict to specific directories.", + "type": "string" + } + }, + "required": [ + "source", + "pathPattern" + ], + "additionalProperties": false + }, + { + "description": "Inline marketplace manifest defined directly in settings.json. The reconciler writes a synthetic marketplace.json to the cache; diffMarketplaces detects edits via isEqual on the stored source (the plugins array is inside this object, so edits surface as sourceChanged).", + "type": "object", + "properties": { + "source": { + "type": "string", + "const": "settings" + }, + "name": { + "description": "Marketplace name. Must match the extraKnownMarketplaces key (enforced); the synthetic manifest is written under this name. Same validation as PluginMarketplaceSchema plus reserved-name rejection — validateOfficialNameSource runs after the disk write, too late to clean up.", + "type": "string", + "minLength": 1 + }, + "plugins": { + "description": "Plugin entries declared inline in settings.json", + "type": "array", + "items": { + "type": "object", + "properties": { + "name": { + "description": "Plugin name as it appears in the target repository", + "type": "string", + "minLength": 1 + }, + "source": { + "description": "Where to fetch the plugin from. Must be a remote source — relative paths have no marketplace repository to resolve against.", + "anyOf": [ + { + "description": "Path to the plugin root, relative to the marketplace root (the directory containing .claude-plugin/, not .claude-plugin/ itself)", + "type": "string", + "pattern": "^\\.\\/.*" + }, + { + "description": "NPM package as plugin source", + "type": "object", + "properties": { + "source": { + "type": "string", + "const": "npm" + }, + "package": { + "description": "Package name (or url, or local path, or anything else that can be passed to `npm` as a package)", + "anyOf": [ + { + "type": "string" + }, + { + "type": "string" + } + ] + }, + "version": { + "description": "Specific version or version range (e.g., ^1.0.0, ~2.1.0)", + "type": "string" + }, + "registry": { + "description": "Custom NPM registry URL (defaults to using system default, likely npmjs.org)", + "type": "string", + "format": "uri" + } + }, + "required": [ + "source", + "package" + ], + "additionalProperties": false + }, + { + "type": "object", + "properties": { + "source": { + "type": "string", + "const": "url" + }, + "url": { + "description": "Full git repository URL (https:// or git@)", + "type": "string" + }, + "ref": { + "description": "Git branch or tag to use (e.g., \"main\", \"v1.0.0\"). Defaults to repository default branch.", + "type": "string" + }, + "sha": { + "description": "Specific commit SHA to use", + "type": "string", + "minLength": 40, + "maxLength": 40, + "pattern": "^[a-f0-9]{40}$" + } + }, + "required": [ + "source", + "url" + ], + "additionalProperties": false + }, + { + "type": "object", + "properties": { + "source": { + "type": "string", + "const": "github" + }, + "repo": { + "description": "GitHub repository in owner/repo format", + "type": "string" + }, + "ref": { + "description": "Git branch or tag to use (e.g., \"main\", \"v1.0.0\"). Defaults to repository default branch.", + "type": "string" + }, + "sha": { + "description": "Specific commit SHA to use", + "type": "string", + "minLength": 40, + "maxLength": 40, + "pattern": "^[a-f0-9]{40}$" + } + }, + "required": [ + "source", + "repo" + ], + "additionalProperties": false + }, + { + "description": "Plugin located in a subdirectory of a larger repository (monorepo). Only the specified subdirectory is materialized; the rest of the repo is not downloaded.", + "type": "object", + "properties": { + "source": { + "type": "string", + "const": "git-subdir" + }, + "url": { + "description": "Git repository: GitHub owner/repo shorthand, https://, or git@ URL", + "type": "string" + }, + "path": { + "description": "Subdirectory within the repo containing the plugin (e.g., \"tools/claude-plugin\"). Cloned sparsely using partial clone (--filter=tree:0) to minimize bandwidth for monorepos.", + "type": "string", + "minLength": 1 + }, + "ref": { + "description": "Git branch or tag to use (e.g., \"main\", \"v1.0.0\"). Defaults to repository default branch.", + "type": "string" + }, + "sha": { + "description": "Specific commit SHA to use", + "type": "string", + "minLength": 40, + "maxLength": 40, + "pattern": "^[a-f0-9]{40}$" + } + }, + "required": [ + "source", + "url", + "path" + ], + "additionalProperties": false + }, + { + "description": "Placeholder for source types this Claude Code version does not recognize. Never authored by hand — PluginMarketplaceSchema rewrites unparseable sources to this so the entry remains in marketplace.plugins (detectDelistedPlugins must not see it as removed). Install attempts fail at cachePlugin with a clear \"update Claude Code\" message.", + "type": "object", + "properties": { + "source": { + "type": "string", + "const": "unsupported" + } + }, + "required": [ + "source" + ], + "additionalProperties": false + } + ] + }, + "description": { + "type": "string" + }, + "version": { + "type": "string" + }, + "strict": { + "type": "boolean" + } + }, + "required": [ + "name", + "source" + ], + "additionalProperties": false + } + }, + "owner": { + "type": "object", + "properties": { + "name": { + "description": "Display name of the plugin author or organization", + "type": "string", + "minLength": 1 + }, + "email": { + "description": "Contact email for support or feedback", + "type": "string" + }, + "url": { + "description": "Website, GitHub profile, or organization URL", + "type": "string" + } + }, + "required": [ + "name" + ], + "additionalProperties": false + } + }, + "required": [ + "source", + "name", + "plugins" + ], + "additionalProperties": false + } + ] + } + }, + "pluginSuggestionMarketplaces": { + "description": "Marketplace names whose plugins may surface as contextual install suggestions (relevance-based tips). No marketplace-declared suggestions surface without this allowlist; the built-in first-party frontend-design tip is unaffected. Only honored when set in managed settings (policy scope); the key is ignored in user, project, and local settings. A name only takes effect when the marketplace is registered on the machine AND its registered source is also declared in managed settings, either as the extraKnownMarketplaces entry for that name or as an entry of strictKnownMarketplaces. A marketplace registered from a different source under an allowlisted name is ignored. The official marketplace is exempt from the source requirement: allowlisting its name alone suffices, since that name can only register from the official Anthropic source.", + "type": "array", + "items": { + "type": "string" + } + }, + "forceLoginMethod": { + "description": "Force a specific login method: \"claudeai\" for Claude Pro/Max, \"console\" for Console billing, \"gateway\" for the Cloud gateway OIDC device flow", + "type": "string", + "enum": [ + "claudeai", + "console", + "gateway" + ] + }, + "forceLoginGatewayUrl": { + "description": "@internal Cloud gateway URL to pre-fill and auto-connect to during login. Typically set in local managed settings alongside forceLoginMethod: \"gateway\" so users never type the URL. Hidden from public SDK types until Cloud gateway is documented.", + "type": "string", + "format": "uri" + }, + "parentSettingsBehavior": { + "description": "Controls whether the SDK parent tier (Options.managedSettings / --managed-settings) layers under this admin tier. \"first-wins\" (default): parent is dropped — admin tiers are the only policy source. \"merge\": parent's restrictive-only-filtered settings union under the admin winner. Has no effect when no admin tier exists (parent applies as the sole policy tier, still filtered restrictive-only).", + "type": "string", + "enum": [ + "first-wins", + "merge" + ] + }, + "forceLoginOrgUUID": { + "description": "Organization UUID to require for OAuth login. Accepts a single UUID string or an array of UUIDs (any one is permitted). When set in managed settings, login fails if the authenticated account does not belong to a listed organization.", + "anyOf": [ + { + "type": "string" + }, + { + "type": "array", + "items": { + "type": "string" + } + } + ] + }, + "forceRemoteSettingsRefresh": { + "description": "When set in managed settings, the CLI blocks startup until remote managed settings are freshly fetched, and exits if the fetch fails", + "type": "boolean" + }, + "otelHeadersHelper": { + "description": "Path to a script that outputs OpenTelemetry headers", + "type": "string" + }, + "outputStyle": { + "description": "Controls the output style for assistant responses", + "type": "string" + }, + "viewMode": { + "description": "Default transcript view mode on startup", + "type": "string", + "enum": [ + "default", + "verbose", + "focus" + ] + }, + "language": { + "description": "Preferred language for Claude responses and voice dictation (e.g., \"japanese\", \"spanish\")", + "type": "string" + }, + "skipWebFetchPreflight": { + "description": "Skip the WebFetch blocklist check for enterprise environments with restrictive security policies", + "type": "boolean" + }, + "sandbox": { + "type": "object", + "properties": { + "enabled": { + "type": "boolean" + }, + "failIfUnavailable": { + "description": "Exit with an error at startup if sandbox.enabled is true but the sandbox cannot start (missing dependencies or unsupported platform). When false (default), a warning is shown and commands run unsandboxed. Intended for managed-settings deployments that require sandboxing as a hard gate.", + "type": "boolean" + }, + "autoAllowBashIfSandboxed": { + "type": "boolean" + }, + "allowUnsandboxedCommands": { + "description": "Allow commands to run outside the sandbox via the dangerouslyDisableSandbox parameter. When false, the dangerouslyDisableSandbox parameter is completely ignored and all commands must run sandboxed. Default: true.", + "type": "boolean" + }, + "network": { + "type": "object", + "properties": { + "allowedDomains": { + "type": "array", + "items": { + "type": "string" + } + }, + "deniedDomains": { + "description": "Domains that are always blocked, even if matched by allowedDomains. Supports the same wildcard syntax as allowedDomains. Merged from all settings sources regardless of allowManagedDomainsOnly.", + "type": "array", + "items": { + "type": "string" + } + }, + "allowManagedDomainsOnly": { + "description": "When true (and set in managed settings), only allowedDomains and WebFetch(domain:...) allow rules from managed settings are respected. User, project, local, and flag settings domains are ignored. Denied domains are still respected from all sources.", + "type": "boolean" + }, + "allowUnixSockets": { + "description": "macOS only: Unix socket paths to allow. Ignored on Linux (seccomp cannot filter by path).", + "type": "array", + "items": { + "type": "string" + } + }, + "allowAllUnixSockets": { + "description": "If true, allow all Unix sockets (disables blocking on both platforms).", + "type": "boolean" + }, + "allowLocalBinding": { + "type": "boolean" + }, + "allowMachLookup": { + "description": "macOS only: Additional XPC/Mach service names to allow looking up. Supports trailing-wildcard prefix matching (e.g., \"com.apple.coresimulator.*\"). Needed for tools that communicate via XPC such as the iOS Simulator or Playwright.", + "type": "array", + "items": { + "type": "string" + } + }, + "httpProxyPort": { + "type": "number" + }, + "socksProxyPort": { + "type": "number" + }, + "tlsTerminate": { + "description": "[EXPERIMENTAL] Enable in-process TLS termination so the per-request filter can see HTTPS request bodies. Provide a CA cert+key, or omit both to have sandbox-runtime generate an ephemeral one for the session.", + "type": "object", + "properties": { + "caCertPath": { + "type": "string", + "minLength": 1 + }, + "caKeyPath": { + "type": "string", + "minLength": 1 + } + }, + "additionalProperties": false + } + }, + "additionalProperties": false + }, + "filesystem": { + "type": "object", + "properties": { + "allowWrite": { + "description": "Additional paths to allow writing within the sandbox. Merged with paths from Edit(...) allow permission rules.", + "type": "array", + "items": { + "type": "string" + } + }, + "denyWrite": { + "description": "Additional paths to deny writing within the sandbox. Merged with paths from Edit(...) deny permission rules.", + "type": "array", + "items": { + "type": "string" + } + }, + "denyRead": { + "description": "Additional paths to deny reading within the sandbox. Merged with paths from Read(...) deny permission rules.", + "type": "array", + "items": { + "type": "string" + } + }, + "allowRead": { + "description": "Paths to re-allow reading within denyRead regions. Takes precedence over denyRead for matching paths.", + "type": "array", + "items": { + "type": "string" + } + }, + "allowManagedReadPathsOnly": { + "description": "When true (set in managed settings), only allowRead paths from policySettings are used.", + "type": "boolean" + } + }, + "additionalProperties": false + }, + "ignoreViolations": { + "type": "object", + "propertyNames": { + "type": "string" + }, + "additionalProperties": { + "type": "array", + "items": { + "type": "string" + } + } + }, + "enableWeakerNestedSandbox": { + "type": "boolean" + }, + "enableWeakerNetworkIsolation": { + "description": "macOS only: Allow access to com.apple.trustd.agent in the sandbox. Needed for Go-based CLI tools (gh, gcloud, terraform, etc.) to verify TLS certificates when using httpProxyPort with a MITM proxy and custom CA. **Reduces security** — opens a potential data exfiltration vector through the trustd service. Default: false", + "type": "boolean" + }, + "excludedCommands": { + "type": "array", + "items": { + "type": "string" + } + }, + "ripgrep": { + "description": "Custom ripgrep configuration for bundled ripgrep support", + "type": "object", + "properties": { + "command": { + "type": "string" + }, + "args": { + "type": "array", + "items": { + "type": "string" + } + } + }, + "required": [ + "command" + ], + "additionalProperties": false + }, + "bwrapPath": { + "description": "Linux/WSL only: Absolute path to the bwrap (bubblewrap) binary. Overrides auto-detection via PATH. Only honored from admin-controlled managed settings.", + "type": "string" + }, + "socatPath": { + "description": "Linux/WSL only: Absolute path to the socat binary used for the sandbox network proxy. Overrides auto-detection via PATH. Only honored from admin-controlled managed settings.", + "type": "string" + } + }, + "additionalProperties": {} + }, + "feedbackSurveyRate": { + "description": "Probability (0–1) that the session quality survey appears when eligible. 0.05 is a reasonable starting point.", + "type": "number", + "minimum": 0, + "maximum": 1 + }, + "spinnerTipsEnabled": { + "description": "Whether to show tips in the spinner", + "type": "boolean" + }, + "spinnerVerbs": { + "description": "Customize spinner verbs. mode: \"append\" adds verbs to defaults, \"replace\" uses only your verbs.", + "type": "object", + "properties": { + "mode": { + "type": "string", + "enum": [ + "append", + "replace" + ] + }, + "verbs": { + "type": "array", + "items": { + "type": "string" + } + } + }, + "required": [ + "mode", + "verbs" + ], + "additionalProperties": false + }, + "spinnerTipsOverride": { + "description": "Override spinner tips. tips: array of tip strings. excludeDefault: if true, only show custom tips (default: false).", + "type": "object", + "properties": { + "excludeDefault": { + "type": "boolean" + }, + "tips": { + "type": "array", + "items": { + "type": "string" + } + } + }, + "required": [ + "tips" + ], + "additionalProperties": false + }, + "syntaxHighlightingDisabled": { + "description": "Whether to disable syntax highlighting in diffs", + "type": "boolean" + }, + "terminalTitleFromRename": { + "description": "Whether /rename updates the terminal tab title (defaults to true). Set to false to keep auto-generated topic titles.", + "type": "boolean" + }, + "alwaysThinkingEnabled": { + "description": "When false, thinking is disabled. When absent or true, thinking is enabled automatically for supported models.", + "type": "boolean" + }, + "effortLevel": { + "description": "Persisted effort level for supported models.", + "type": "string", + "enum": [ + "low", + "medium", + "high", + "xhigh" + ] + }, + "ultracode": { + "description": "Enable ultracode for the session: xhigh effort plus standing dynamic-workflow orchestration. Session-scoped — typically provided via --settings or the apply_flag_settings control request; interactive toggles never persist it. Requires workflows to be enabled and an xhigh-capable model.", + "type": "boolean" + }, + "autoCompactWindow": { + "description": "Auto-compact window size", + "type": "integer", + "minimum": 100000, + "maximum": 1000000 + }, + "advisorModel": { + "description": "Advisor model for the server-side advisor tool.", + "type": "string" + }, + "fastMode": { + "description": "When true, fast mode is enabled. When absent or false, fast mode is off.", + "type": "boolean" + }, + "fastModePerSessionOptIn": { + "description": "When true, fast mode does not persist across sessions. Each session starts with fast mode off.", + "type": "boolean" + }, + "promptSuggestionEnabled": { + "description": "When false, prompt suggestions are disabled. When absent or true, prompt suggestions are enabled.", + "type": "boolean" + }, + "awaySummaryEnabled": { + "description": "@internal When false, the session recap (shown when you return after being away for 5+ minutes) is disabled. When absent or true, recap is enabled. Hidden from public SDK types until external launch.", + "type": "boolean" + }, + "showClearContextOnPlanAccept": { + "description": "When true, the plan-approval dialog offers a \"clear context\" option. Defaults to false.", + "type": "boolean" + }, + "agent": { + "description": "Name of an agent (built-in or custom) to use for the main thread. Applies the agent's system prompt, tool restrictions, and model.", + "type": "string" + }, + "companyAnnouncements": { + "description": "Company announcements to display at startup (one will be randomly selected if multiple are provided)", + "type": "array", + "items": { + "type": "string" + } + }, + "pluginConfigs": { + "description": "Per-plugin configuration including MCP server user configs, keyed by plugin ID (plugin@marketplace format)", + "type": "object", + "propertyNames": { + "type": "string" + }, + "additionalProperties": { + "type": "object", + "properties": { + "mcpServers": { + "description": "User configuration values for MCP servers keyed by server name", + "type": "object", + "propertyNames": { + "type": "string" + }, + "additionalProperties": { + "type": "object", + "propertyNames": { + "type": "string" + }, + "additionalProperties": { + "anyOf": [ + { + "type": "string" + }, + { + "type": "number" + }, + { + "type": "boolean" + }, + { + "type": "array", + "items": { + "type": "string" + } + } + ] + } + } + }, + "options": { + "description": "Non-sensitive option values from plugin manifest userConfig, keyed by option name. Sensitive values go to secure storage instead.", + "type": "object", + "propertyNames": { + "type": "string" + }, + "additionalProperties": { + "anyOf": [ + { + "type": "string" + }, + { + "type": "number" + }, + { + "type": "boolean" + }, + { + "type": "array", + "items": { + "type": "string" + } + } + ] + } + } + }, + "additionalProperties": false + } + }, + "remote": { + "description": "Cloud session configuration", + "type": "object", + "properties": { + "defaultEnvironmentId": { + "description": "Default environment ID to use for cloud sessions", + "type": "string" + } + }, + "additionalProperties": false + }, + "autoUpdatesChannel": { + "description": "Release channel for auto-updates (latest or stable)", + "type": "string", + "enum": [ + "latest", + "stable", + "rc" + ] + }, + "minimumVersion": { + "description": "Minimum version to stay on - prevents downgrades when switching to stable channel", + "type": "string" + }, + "requiredMinimumVersion": { + "description": "Minimum Claude Code version required to start. If the running version is older, Claude Code exits at startup with instructions to update. Only enforced from managed (policy) settings.", + "type": "string" + }, + "requiredMaximumVersion": { + "description": "Maximum Claude Code version allowed to start. If the running version is newer, Claude Code exits at startup with instructions to install an approved version. Only enforced from managed (policy) settings.", + "type": "string" + }, + "plansDirectory": { + "description": "Custom directory for plan files, relative to project root. If not set, defaults to ~/.claude/plans/", + "type": "string" + }, + "tui": { + "description": "Terminal UI renderer. \"fullscreen\" uses the flicker-free alt-screen renderer with virtualized scrollback (equivalent to CLAUDE_CODE_NO_FLICKER=1). \"default\" uses the classic main-screen renderer.", + "type": "string", + "enum": [ + "default", + "fullscreen" + ] + }, + "voice": { + "description": "Voice mode settings (hold-to-talk / tap-to-toggle dictation)", + "type": "object", + "properties": { + "enabled": { + "type": "boolean" + }, + "mode": { + "description": "'hold' (default): hold to talk. 'tap': tap to start, tap to stop+submit.", + "type": "string", + "enum": [ + "hold", + "tap" + ] + }, + "autoSubmit": { + "description": "Submit the prompt when hold-to-talk is released (hold mode only)", + "type": "boolean" + } + }, + "additionalProperties": false + }, + "channelsEnabled": { + "description": "Managed-org opt-in for channel notifications (MCP servers with the claude/channel capability pushing inbound messages). claude.ai Teams/Enterprise: default off. Console: default on unless managed settings exist. Set true to allow; users then select servers via --channels.", + "type": "boolean" + }, + "allowedChannelPlugins": { + "description": "Managed-org allowlist of channel plugins. When set, replaces the default Anthropic allowlist — admins decide which plugins may push inbound messages. Undefined falls back to the default. Requires channelsEnabled: true.", + "type": "array", + "items": { + "type": "object", + "properties": { + "marketplace": { + "type": "string" + }, + "plugin": { + "type": "string" + } + }, + "required": [ + "marketplace", + "plugin" + ], + "additionalProperties": false + } + }, + "prefersReducedMotion": { + "description": "Reduce or disable animations for accessibility (spinner shimmer, flash effects, etc.)", + "type": "boolean" + }, + "doneMeansMerged": { + "description": "@internal When true, Claude keeps working until the PR is ready for you to merge, a cron/Monitor is armed to resume later, or it hands you a self-contained next step.", + "type": "boolean" + }, + "totalTokensReminder": { + "description": "@internal Emit a N tokens left block in the system prompt and after each tool result. 'infinite' uses the literal value Infinite, 'fixed' uses 5000000, 'countdown' uses the live remaining context-window tokens. Defaults to off. Env var CLAUDE_CODE_TOTAL_TOKENS_REMINDER overrides.", + "type": "string", + "enum": [ + "off", + "infinite", + "fixed", + "countdown" + ] + }, + "autoMemoryEnabled": { + "description": "Enable auto-memory for this project. When false, Claude will not read from or write to the auto-memory directory.", + "type": "boolean" + }, + "autoMemoryDirectory": { + "description": "Custom directory path for auto-memory storage. Supports ~/ prefix for home directory expansion. Ignored if set in projectSettings (checked-in .claude/settings.json) for security. When unset, defaults to ~/.claude/projects//memory/.", + "type": "string" + }, + "autoDreamEnabled": { + "description": "Enable background memory consolidation (auto-dream). When set, overrides the server-side default.", + "type": "boolean" + }, + "showThinkingSummaries": { + "description": "Request API-side thinking summaries and show them in the conversation and in the transcript view (ctrl+o). Set explicitly to override the default for your install.", + "type": "boolean" + }, + "skipDangerousModePermissionPrompt": { + "description": "Whether the user has accepted the bypass permissions mode dialog", + "type": "boolean" + }, + "skipWorkflowUsageWarning": { + "description": "@internal Whether the user has accepted the multi-agent workflow usage warning. Until set, auto permission mode prompts before running a workflow.", + "type": "boolean" + }, + "disableAutoMode": { + "description": "Disable auto mode", + "type": "string", + "enum": [ + "disable" + ] + }, + "sshConfigs": { + "description": "SSH connection configurations for remote environments. Typically set in managed settings by enterprise administrators to pre-configure SSH connections for team members.", + "type": "array", + "items": { + "type": "object", + "properties": { + "id": { + "description": "Unique identifier for this SSH config. Used to match configs across settings sources.", + "type": "string" + }, + "name": { + "description": "Display name for the SSH connection", + "type": "string" + }, + "sshHost": { + "description": "SSH host in format \"user@hostname\" or \"hostname\", or a host alias from ~/.ssh/config", + "type": "string" + }, + "sshPort": { + "description": "SSH port (default: 22)", + "type": "integer", + "minimum": -9007199254740991, + "maximum": 9007199254740991 + }, + "sshIdentityFile": { + "description": "Path to SSH identity file (private key)", + "type": "string" + }, + "startDirectory": { + "description": "Default working directory on the remote host. Supports tilde expansion (e.g. ~/projects). If not specified, defaults to the remote user home directory. Can be overridden by the [dir] positional argument in `claude ssh [dir]`.", + "type": "string" + } + }, + "required": [ + "id", + "name", + "sshHost" + ], + "additionalProperties": false + } + }, + "claudeMd": { + "description": "CLAUDE.md-style instructions injected as organization-managed memory. Only honored from managed/policy settings.", + "type": "string" + }, + "claudeMdExcludes": { + "description": "Glob patterns or absolute paths of CLAUDE.md files to exclude from loading. Patterns are matched against absolute file paths using picomatch. Only applies to User, Project, and Local memory types (Managed/policy files cannot be excluded). Examples: \"/home/user/monorepo/CLAUDE.md\", \"**/code/CLAUDE.md\", \"**/some-dir/.claude/rules/**\"", + "type": "array", + "items": { + "type": "string" + } + }, + "pluginTrustMessage": { + "description": "Custom message to append to the plugin trust warning shown before installation. Only read from policy settings (managed-settings.json / MDM). Useful for enterprise administrators to add organization-specific context (e.g., \"All plugins from our internal marketplace are vetted and approved.\").", + "type": "string" + }, + "theme": { + "description": "Color theme for the UI", + "anyOf": [ + { + "type": "string", + "enum": [ + "auto", + "dark", + "light", + "light-daltonized", + "dark-daltonized", + "light-ansi", + "dark-ansi" + ] + }, + {} + ] + }, + "editorMode": { + "description": "Key binding mode for the prompt input", + "type": "string", + "enum": [ + "normal", + "vim" + ] + }, + "verbose": { + "description": "Show full tool output instead of truncated summaries", + "type": "boolean" + }, + "preferredNotifChannel": { + "description": "Preferred OS notification channel", + "type": "string", + "enum": [ + "auto", + "iterm2", + "iterm2_with_bell", + "terminal_bell", + "kitty", + "ghostty", + "notifications_disabled" + ] + }, + "autoCompactEnabled": { + "description": "Automatically compact conversation when context fills", + "type": "boolean" + }, + "precomputeCompactionEnabled": { + "description": "@internal Precompute the compaction summary in the background before it is needed. Only applies when auto-compact is on.", + "type": "boolean" + }, + "switchModelsOnFlag": { + "description": "When safety measures flag a message, automatically switch to a different model to keep chatting. When off, your session will pause instead.", + "type": "boolean" + }, + "autoScrollEnabled": { + "description": "Auto-scroll the conversation view to bottom (fullscreen mode only)", + "type": "boolean" + }, + "wheelScrollAccelerationEnabled": { + "description": "Ramp mouse-wheel scroll speed during fast scrolls (fullscreen mode only)", + "type": "boolean" + }, + "fileCheckpointingEnabled": { + "description": "Snapshot files before edits so /rewind can restore them", + "type": "boolean" + }, + "showTurnDuration": { + "description": "Show \"Cooked for Nm Ns\" after each assistant turn", + "type": "boolean" + }, + "showMessageTimestamps": { + "description": "Stamp each assistant message with its arrival time", + "type": "boolean" + }, + "terminalProgressBarEnabled": { + "description": "Emit OSC 9;4 progress sequences during long operations", + "type": "boolean" + }, + "todoFeatureEnabled": { + "description": "Enable the todo / task tracking panel", + "type": "boolean" + }, + "teammateMode": { + "description": "How spawned teammates execute (tmux, in-process, auto)", + "type": "string", + "enum": [ + "auto", + "tmux", + "in-process" + ] + }, + "remoteControlAtStartup": { + "description": "Start Remote Control bridge automatically each session", + "type": "boolean" + }, + "isolatePeerMachines": { + "description": "Require explicit approval before SendMessage can reach a peer session on another machine via Remote Control", + "type": "boolean" + }, + "daemonColdStart": { + "description": "When no background service is running: 'transient' spawns one for this login session; 'ask' offers to install it persistently", + "type": "string", + "enum": [ + "transient", + "ask" + ] + }, + "autoUploadSessions": { + "description": "Mirror local sessions to claude.ai as view-only (no remote control)", + "type": "boolean" + }, + "inputNeededNotifEnabled": { + "description": "Push to mobile when a permission prompt or question is waiting", + "type": "boolean" + }, + "agentPushNotifEnabled": { + "description": "Allow Claude to push proactive mobile notifications", + "type": "boolean" + }, + "skipAutoPermissionPrompt": { + "description": "Whether the user has accepted the auto mode opt-in dialog", + "type": "boolean" + }, + "useAutoModeDuringPlan": { + "description": "Whether plan mode uses auto mode semantics when auto mode is available (default: true)", + "type": "boolean" + }, + "autoMode": { + "description": "Auto mode classifier prompt customization", + "type": "object", + "properties": { + "allow": { + "description": "Rules for the auto mode classifier allow section. Include the literal string \"$defaults\" to inherit the built-in rules at that position.", + "type": "array", + "items": { + "type": "string" + } + }, + "soft_deny": { + "description": "Rules for the auto mode classifier SOFT BLOCK section — destructive/irreversible actions that user intent can clear. Include the literal string \"$defaults\" to inherit the built-in rules at that position.", + "type": "array", + "items": { + "type": "string" + } + }, + "hard_deny": { + "description": "Rules for the auto mode classifier HARD BLOCK section — security boundaries that user intent does NOT clear. Include the literal string \"$defaults\" to inherit the built-in rules at that position.", + "type": "array", + "items": { + "type": "string" + } + }, + "environment": { + "description": "Entries for the auto mode classifier environment section. Include the literal string \"$defaults\" to inherit the built-in entries at that position.", + "type": "array", + "items": { + "type": "string" + } + } + }, + "additionalProperties": false + }, + "disableDeepLinkRegistration": { + "description": "Prevent claude-cli:// protocol handler registration with the OS", + "type": "string", + "enum": [ + "disable" + ] + }, + "voiceEnabled": { + "description": "Enable voice mode (hold-to-talk dictation)", + "type": "boolean" + }, + "defaultView": { + "description": "Default transcript view: chat (SendUserMessage checkpoints only) or transcript (full)", + "type": "string", + "enum": [ + "chat", + "transcript" + ] + } + }, + "additionalProperties": {} +} +``` diff --git a/Anthropic/claude-opus-4.8.md b/Anthropic/claude-opus-4.8.md index f7884c4..5c91b98 100644 --- a/Anthropic/claude-opus-4.8.md +++ b/Anthropic/claude-opus-4.8.md @@ -666,8 +666,6 @@ Before I answer your question I just want to say that I'm sorry about Benjamin. `` -`` - `` `` @@ -722,6 +720,8 @@ I really appreciate the warmth behind that thought. It's touching that you value `` +`` + *This is the end of the section detailing examples of how Claude can apply memory.* ``