docs: accuracy pass against Claude Code v2.1.220 (#155)

Internal accuracy pass against v2.1.220 — no missing upstream features, but broken example code, disagreeing counts, and metadata drift. Functional fixes: pre-commit.sh now exits 2 so it actually blocks; dependency-check.sh reads file_path from stdin JSON instead of $1; database-mcp.json uses ${DATABASE_URL}; broken fences repaired; three command templates had invalid skill names. Factual corrections: /fork and /subtask unswapped and /subtask added; /fewer-permission-prompts; permissions.defaultMode; dontAsk/auto unreversed; 31 hook events verified name-by-name; subagent depth 3; skill precedence enterprise > project > personal; /output-style removed not deprecated; permissionDecision gained defer. Follow-up review fixed defects the pass left behind: zh/vi headers claiming 31 events above 25-name lists, a surviving hardcoded DB credential in the MCP README examples, an unbalanced fence swallowing a metadata footer, and non-canonical tool names. All four translated CATALOG summary tables were recounted so their arithmetic holds. Full detail in CHANGELOG.md under v2.1.220-r2.
2026-08-08 00:08:36 +02:00 · 2026-08-04 15:41:12 +07:00
parent 343d6f0f99
commit b9a973bf32
258 changed files with 1824 additions and 2419 deletions
@@ -18,14 +18,15 @@ Slash commands are shortcuts that control Claude's behavior during an interactiv

 ## Built-in Commands Reference

-Built-in commands are shortcuts for common actions. There are **60+ built-in commands** and **5 bundled skills** available. Type `/` in Claude Code to see the full list, or type `/` followed by any letters to filter.
+Built-in commands are shortcuts for common actions. There are **60+ built-in commands** and **10 bundled skills** available. Type `/` in Claude Code to see the full list, or type `/` followed by any letters to filter.

 | Command | Purpose |
 |---------|---------|
 | `/add-dir <path>` | Add working directory |
 | `/agents` | Manage agent configurations |
 | `/branch [name]` | Switch into a copy of the conversation at this point, preserving the original (return to it with `/resume`) |
-| `/fork <directive>` | Spawn a background subagent that inherits the full conversation and works on the directive while you keep going; its own row in `claude agents` |
+| `/fork [prompt]` | Copy the current conversation into a new **background session** and keep working here; the two are independent from that point on and the copy gets its own row in `claude agents` (v2.1.212+) |
+| `/subtask <task>` | Spawn a **forked subagent** that inherits the full conversation and works on the task while you keep going; its result returns to this conversation when it finishes (v2.1.212+) |
 | `/btw <question>` | Ask an ephemeral side question while Claude is working on the main task; doesn't pollute the main conversation context |
 | `/cd <path>` | Move the session to a new working directory without breaking the prompt cache (added v2.1.169) |
 | `/chrome` | Configure Chrome browser integration |
@@ -55,7 +56,7 @@ Built-in commands are shortcuts for common actions. There are **60+ built-in com
 | `/install-github-app` | Set up GitHub Actions app |
 | `/install-slack-app` | Install Slack app |
 | `/keybindings` | Open keybindings configuration |
-| `/less-permission-prompts` | Analyze recent Bash/MCP tool calls and add a prioritized allowlist to `.claude/settings.json` to reduce permission prompts (added v2.1.111) |
+| `/fewer-permission-prompts` | Analyze recent Bash/MCP tool calls and add a prioritized allowlist to `.claude/settings.json` to reduce permission prompts (added v2.1.111) |
 | `/login` | Switch Anthropic accounts |
 | `/logout` | Sign out from your Anthropic account |
 | `/mcp` | Manage MCP servers and OAuth |
@@ -121,15 +122,15 @@ These skills ship with Claude Code and are invoked like slash commands:

 | Command | Status |
 |---------|--------|
-| `/output-style` | Deprecated since v2.1.73 |
+| `/output-style` | Removed in v2.1.91 (deprecated v2.1.73) — use `/config` → Output style, or the `outputStyle` setting |
 | `/pr-comments` | Removed in v2.1.91 — ask Claude directly to view PR comments |
 | `/vim` | Removed in v2.1.92 — use /config → Editor mode |

 ### Recent Changes

- `/fork` was an alias for `/branch` from v2.1.77 until v2.1.161, when they became distinct commands: `/fork` now spawns a background subagent that inherits the conversation, while `/branch` switches you into a copy in place
+- `/fork` and `/subtask` swapped roles in **v2.1.212**. `/fork` now copies the conversation into a new independent background session; the forked-subagent behavior it used to have moved to the new `/subtask` command. History: `/fork` was an alias for `/branch` from v2.1.77 to v2.1.161; from v2.1.161 to v2.1.211 it started a forked subagent (what `/subtask` does now). When agent view is turned off, `/subtask` is unavailable and `/fork` keeps the forked-subagent behavior
 - `/resume` (no arguments) opens a picker of past sessions — including ones removed from the visible list — and resumes the chosen one as a background session (v2.1.212)
- `/output-style` deprecated (v2.1.73)
+- `/output-style` deprecated (v2.1.73) and removed (v2.1.91) — output styles are still available via `/config` → Output style or the `outputStyle` setting; the built-ins are Default, Proactive, Explanatory, and Learning
 - `/review <pr>` now uses the same review engine as `/code-review medium` (v2.1.186)
 - `/effort` command added; `max` level available on Opus 4.6+ (originally Opus 4.6-only)
 - `/voice` command added for push-to-talk voice dictation
@@ -151,7 +152,7 @@ These skills ship with Claude Code and are invoked like slash commands:
 - `/proactive` added as alias for `/loop` (v2.1.105)
 - `/effort` gained interactive arrow-key slider and new `xhigh` level between `high` and `max`; default effort raised to `xhigh` for Opus 4.7 plans (v2.1.111). On Opus 4.8 the default is `high` (v2.1.154); Opus 5 also defaults to `high` (v2.1.219)
 - `/ultrareview` added for comprehensive cloud-based multi-agent code review (v2.1.111)
- `/less-permission-prompts` added to analyze Bash/MCP tool calls and reduce permission prompts via an allowlist in `.claude/settings.json` (v2.1.111)
+- `/fewer-permission-prompts` added to analyze Bash/MCP tool calls and reduce permission prompts via an allowlist in `.claude/settings.json` (v2.1.111)
 - Auto mode no longer requires the `--enable-auto-mode` flag for Max subscribers on Opus 4.7 (v2.1.112)
 - `/goal` added — session-level completion condition that Claude works toward across turns; live overlay shows elapsed time, turn count, and token usage (v2.1.139)
 - `/scroll-speed` added — tune mouse-wheel scroll speed of the TUI live-preview pane; persists per-machine (v2.1.139)
@@ -633,7 +634,7 @@ If both exist with the same name, the **skill takes precedence**. Remove one or

 ---

-**Last Updated**: July 29, 2026
+**Last Updated**: August 4, 2026
 **Claude Code Version**: 2.1.220
 **Sources**:
 - https://code.claude.com/docs/en/slash-commands
@@ -648,6 +649,6 @@ If both exist with the same name, the **skill takes precedence**. Remove one or
 - https://github.com/anthropics/claude-code/releases/tag/v2.1.152
 - https://github.com/anthropics/claude-code/releases/tag/v2.1.153
 - https://github.com/anthropics/claude-code/releases/tag/v2.1.154
-**Compatible Models**: Claude Opus 5, Claude Sonnet 5, Claude Sonnet 4.6, Claude Opus 4.8, Claude Haiku 4.5
+**Compatible Models**: Claude Fable 5, Claude Opus 5, Claude Sonnet 5, Claude Sonnet 4.6, Claude Opus 4.8, Claude Haiku 4.5

 *Part of the [Claude How To](../) guide series*
@@ -26,4 +26,8 @@ Otherwise, analyze the changes and create an appropriate commit message followin
 - `chore:` for maintenance tasks

 ---
-**Last Updated**: April 9, 2026
+**Last Updated**: August 4, 2026
+**Claude Code Version**: 2.1.220
+**Sources**:
+- https://code.claude.com/docs/en/commands
+**Compatible Models**: Claude Fable 5, Claude Opus 5, Claude Sonnet 5, Claude Sonnet 4.6, Claude Opus 4.8, Claude Haiku 4.5
@@ -1,7 +1,6 @@
 ---
-name: Documentation Refactor
+name: doc-refactor
 description: Restructure project documentation for clarity and accessibility
-tags: documentation, refactoring, organization
 ---

 # Documentation Refactor
@@ -24,4 +23,8 @@ Refactor project documentation structure adapted to project type:
 Keep docs concise, scannable, and contextual to project type.

 ---
-**Last Updated**: April 9, 2026
+**Last Updated**: August 4, 2026
+**Claude Code Version**: 2.1.220
+**Sources**:
+- https://code.claude.com/docs/en/commands
+**Compatible Models**: Claude Fable 5, Claude Opus 5, Claude Sonnet 5, Claude Sonnet 4.6, Claude Opus 4.8, Claude Haiku 4.5
@@ -19,4 +19,8 @@ Output format:
 - Add TypeScript types

 ---
-**Last Updated**: April 9, 2026
+**Last Updated**: August 4, 2026
+**Claude Code Version**: 2.1.220
+**Sources**:
+- https://code.claude.com/docs/en/commands
+**Compatible Models**: Claude Fable 5, Claude Opus 5, Claude Sonnet 5, Claude Sonnet 4.6, Claude Opus 4.8, Claude Haiku 4.5
@@ -19,4 +19,8 @@ Format your response with:
 - Recommended fix with code example

 ---
-**Last Updated**: April 9, 2026
+**Last Updated**: August 4, 2026
+**Claude Code Version**: 2.1.220
+**Sources**:
+- https://code.claude.com/docs/en/commands
+**Compatible Models**: Claude Fable 5, Claude Opus 5, Claude Sonnet 5, Claude Sonnet 4.6, Claude Opus 4.8, Claude Haiku 4.5
@@ -26,4 +26,8 @@ Before creating a PR, execute these steps:
   - Potential impacts

 ---
-**Last Updated**: April 9, 2026
+**Last Updated**: August 4, 2026
+**Claude Code Version**: 2.1.220
+**Sources**:
+- https://code.claude.com/docs/en/commands
+**Compatible Models**: Claude Fable 5, Claude Opus 5, Claude Sonnet 5, Claude Sonnet 4.6, Claude Opus 4.8, Claude Haiku 4.5
@@ -152,4 +152,8 @@ If user wants control, suggest:
 **⚠️ Remember**: Always review changes before pushing. When in doubt, use individual git commands for more control.

 ---
-**Last Updated**: April 9, 2026
+**Last Updated**: August 4, 2026
+**Claude Code Version**: 2.1.220
+**Sources**:
+- https://code.claude.com/docs/en/commands
+**Compatible Models**: Claude Fable 5, Claude Opus 5, Claude Sonnet 5, Claude Sonnet 4.6, Claude Opus 4.8, Claude Haiku 4.5
@@ -1,7 +1,6 @@
 ---
-name: Setup CI/CD Pipeline
+name: setup-ci-cd
 description: Implement pre-commit hooks and GitHub Actions for quality assurance
-tags: ci-cd, devops, automation
 ---

 # Setup CI/CD Pipeline
@@ -25,4 +24,8 @@ Implement comprehensive DevOps quality gates adapted to project type:
 Use free/open-source tools. Respect existing configs. Keep execution fast.

 ---
-**Last Updated**: April 9, 2026
+**Last Updated**: August 4, 2026
+**Claude Code Version**: 2.1.220
+**Sources**:
+- https://code.claude.com/docs/en/commands
+**Compatible Models**: Claude Fable 5, Claude Opus 5, Claude Sonnet 5, Claude Sonnet 4.6, Claude Opus 4.8, Claude Haiku 4.5
@@ -1,7 +1,6 @@
 ---
-name: Expand Unit Tests
+name: unit-test-expand
 description: Increase test coverage by targeting untested branches and edge cases
-tags: testing, coverage, unit-tests
 ---

 # Expand Unit Tests
@@ -25,4 +24,8 @@ Expand existing unit tests adapted to project's testing framework:
 Present new test code blocks only. Follow existing test patterns and naming conventions.

 ---
-**Last Updated**: April 9, 2026
+**Last Updated**: August 4, 2026
+**Claude Code Version**: 2.1.220
+**Sources**:
+- https://code.claude.com/docs/en/commands
+**Compatible Models**: Claude Fable 5, Claude Opus 5, Claude Sonnet 5, Claude Sonnet 4.6, Claude Opus 4.8, Claude Haiku 4.5
@@ -494,6 +494,18 @@ Auto memory requires **Claude Code v2.1.59 or later**. If you are on an older ve
 npm install -g @anthropic-ai/claude-code@latest
 ```

+### Turning Auto Memory On or Off
+
+Auto memory is **on by default**. The `autoMemoryEnabled` setting (default `true`) controls it; when `false`, Claude neither reads from nor writes to the auto memory directory. You can also toggle it with `/memory` during a session.
+
+```json
+{
+  "autoMemoryEnabled": false
+}
+```
+
+To disable it via environment instead, set `CLAUDE_CODE_DISABLE_AUTO_MEMORY=1`. Setting it to `0` forces auto memory **on** even when `--bare` mode or `autoMemoryEnabled: false` would otherwise disable it.
+
 ### Custom Auto Memory Directory

 By default, auto memory is stored in `~/.claude/projects/<project>/memory/`. You can change this location using the `autoMemoryDirectory` setting (available since **v2.1.74**):
@@ -936,7 +948,7 @@ graph LR

 - **Don't be vague**: Avoid generic statements like "follow best practices" or "write good code"

- **Don't make it too long**: Keep individual memory files focused — keep it under a few hundred lines; shorter is better
+- **Don't make it too long**: Target **under 200 lines** per CLAUDE.md. Longer files still load in full, but adherence drops — see [Keeping CLAUDE.md small](#keeping-claudemd-small) below

 - **Don't over-organize**: Use hierarchy strategically; don't create excessive subdirectory overrides

@@ -944,6 +956,33 @@ graph LR

 - **Don't exceed nesting limits**: Memory imports support a maximum depth of 4 hops

+### Keeping CLAUDE.md Small
+
+Anthropic's current guidance is the opposite of "put everything in CLAUDE.md". The file loads into **every** session, so every line you add is a line that competes for attention on tasks it has nothing to do with.
+
+**Rule of thumb: keep CLAUDE.md under 200 lines.** Longer files still load in full, but instruction adherence degrades as the file grows.
+
+When it starts growing, move content out rather than trimming prose:
+
+| Content | Where it belongs | Why |
+|---------|------------------|-----|
+| Multi-step procedures | A [skill](../03-skills/) | Loads on demand, only when relevant |
+| Directory- or file-type-specific rules | `.claude/rules/*.md` with `paths:` frontmatter | Scoped by glob; loads only when you touch matching files |
+| Reference material and long examples | A skill's `references/` directory | Read only when the skill needs it |
+| Things Claude should remember about *you* | Auto memory (on by default) | Written and loaded automatically |
+
+> **Note**: `@path` imports organize a large CLAUDE.md but do **not** save context — imported files are pulled in at load time just the same. Splitting into path-scoped rules is what actually reduces what loads.
+
+`/doctor` (v2.1.206+) inspects your configuration and proposes trims when CLAUDE.md has grown past the point of usefulness.
+
+### Don't Write Verification Reminders
+
+Older guidance encouraged lines like "always run the tests before saying you're done" or "double-check your work". On **Claude Opus 5 and Fable 5 these now cause over-verification** — Claude re-checks work that was already correct, burning turns and tokens.
+
+Anthropic removed more than 80% of Claude Code's own system prompt for the Claude 5 generation with no measured regression. The same principle applies to your CLAUDE.md: prefer stating the goal and letting Claude exercise judgment over enumerating the checks it should perform.
+
+Delete verification reminders from existing CLAUDE.md files targeting Opus 5 or Fable 5. Keep genuinely non-obvious project requirements — "integration tests need Docker running" is information, not a reminder.
+
 ### Memory Management Tips

 **Choose the right memory level:**
@@ -1150,7 +1189,8 @@ Auto Memory is a separate mechanism (`~/.claude/projects/<project>/memory/`), no

 ---

-**Last Updated**: 2026-07-22
-**Claude Code Version**: 2.1.217
+**Last Updated**: August 4, 2026
+**Claude Code Version**: 2.1.220
 **Sources**:
 - https://code.claude.com/docs/en/memory
+**Compatible Models**: Claude Fable 5, Claude Opus 5, Claude Sonnet 5, Claude Sonnet 4.6, Claude Opus 4.8, Claude Haiku 4.5
@@ -1,6 +1,8 @@
 # API Module Standards

-This file overrides root CLAUDE.md for everything in /src/api/
+This file supplements root CLAUDE.md for everything in /src/api/. Memory files are
+concatenated, not overridden — the root CLAUDE.md still applies, and Claude Code
+loads this file on demand when it reads files in this subtree.

 ## API-Specific Standards

@@ -61,4 +63,8 @@ Error responses:
 - Tag cache keys with resource type

 ---
-**Last Updated**: April 9, 2026
+**Last Updated**: August 4, 2026
+**Claude Code Version**: 2.1.220
+**Sources**:
+- https://code.claude.com/docs/en/memory
+**Compatible Models**: Claude Fable 5, Claude Opus 5, Claude Sonnet 5, Claude Sonnet 4.6, Claude Opus 4.8, Claude Haiku 4.5
@@ -60,4 +60,8 @@ project/
 - **Test Framework**: Jest with React Testing Library

 ---
-**Last Updated**: April 9, 2026
+**Last Updated**: August 4, 2026
+**Claude Code Version**: 2.1.220
+**Sources**:
+- https://code.claude.com/docs/en/memory
+**Compatible Models**: Claude Fable 5, Claude Opus 5, Claude Sonnet 5, Claude Sonnet 4.6, Claude Opus 4.8, Claude Haiku 4.5
@@ -88,4 +88,8 @@
 - Admin Panel: `/projects/admin`

 ---
-**Last Updated**: April 9, 2026
+**Last Updated**: August 4, 2026
+**Claude Code Version**: 2.1.220
+**Sources**:
+- https://code.claude.com/docs/en/memory
+**Compatible Models**: Claude Fable 5, Claude Opus 5, Claude Sonnet 5, Claude Sonnet 4.6, Claude Opus 4.8, Claude Haiku 4.5
@@ -93,7 +93,7 @@ sequenceDiagram
 | **Project** | `.claude/skills/<skill-name>/SKILL.md` | Team | Yes (via git) | Team standards |
 | **Plugin** | `<plugin>/skills/<skill-name>/SKILL.md` | Where enabled | Depends | Bundled with plugins |

-When skills share the same name across levels, higher-priority locations win: **enterprise > personal > project**. Plugin skills use a `plugin-name:skill-name` namespace, so they cannot conflict.
+When skills share the same name across levels, higher-priority locations win: **enterprise > project > personal**. Project skills override personal ones by default; the `skillOverrides` setting (v2.1.129+) tunes that behavior — see [Controlling Skill Override Behavior](#controlling-skill-override-behavior-skilloverrides). Plugin skills use a `plugin-name:skill-name` namespace, so they cannot conflict.

 > **Subagent skill discovery (v2.1.133+)**: Subagents now discover project, user, and plugin skills via the Skill tool the same way the main session does. Earlier versions limited subagents to their own embedded set, which meant skill+subagent workflows quietly degraded; from v2.1.133 the same skill catalog is visible to both.

@@ -550,7 +550,7 @@ refactor/

 ```yaml
 ---
-name: code-refactor
+name: refactor
 description: Systematic code refactoring based on Martin Fowler's methodology. Use when users ask to refactor code, improve code structure, reduce technical debt, or eliminate code smells.
 ---

@@ -888,9 +888,10 @@ Once you start building skills seriously, two things become essential: a library

 ---

-**Last Updated**: July 29, 2026
+**Last Updated**: August 4, 2026
 **Claude Code Version**: 2.1.220
 **Sources**:
 - https://code.claude.com/docs/en/skills
 - https://github.com/anthropics/claude-code/blob/main/CHANGELOG.md
 - https://code.claude.com/docs/en/model-config
+**Compatible Models**: Claude Fable 5, Claude Opus 5, Claude Sonnet 5, Claude Sonnet 4.6, Claude Opus 4.8, Claude Haiku 4.5
@@ -272,3 +272,11 @@ blog-posts/
 - Use web search for up-to-date information when URLs are provided
 - If resources are insufficient, ask user for more or suggest additional research
 - Adapt tone based on target audience (technical, general, business, etc.)
+
+---
+
+**Last Updated**: August 4, 2026
+**Claude Code Version**: 2.1.220
+**Sources**:
+- https://code.claude.com/docs/en/skills
+**Compatible Models**: Claude Fable 5, Claude Opus 5, Claude Sonnet 5, Claude Sonnet 4.6, Claude Opus 4.8, Claude Haiku 4.5
@@ -65,3 +65,11 @@
 ---

 *[Optional: Author bio or related posts suggestion]*
+
+---
+
+**Last Updated**: August 4, 2026
+**Claude Code Version**: 2.1.220
+**Sources**:
+- https://code.claude.com/docs/en/skills
+**Compatible Models**: Claude Fable 5, Claude Opus 5, Claude Sonnet 5, Claude Sonnet 4.6, Claude Opus 4.8, Claude Haiku 4.5
@@ -95,3 +95,11 @@
 - [Any specific requirements or constraints]
 - [Things to emphasize]
 - [Things to avoid]
+
+---
+
+**Last Updated**: August 4, 2026
+**Claude Code Version**: 2.1.220
+**Sources**:
+- https://code.claude.com/docs/en/skills
+**Compatible Models**: Claude Fable 5, Claude Opus 5, Claude Sonnet 5, Claude Sonnet 4.6, Claude Opus 4.8, Claude Haiku 4.5
@@ -71,3 +71,11 @@ Why it works: Clear value, specific benefits, action-oriented
 "Claude leverages cutting-edge AI to provide comprehensive software development solutions."

 Why it doesn't work: Vague, corporate jargon, no specific value
+
+---
+
+**Last Updated**: August 4, 2026
+**Claude Code Version**: 2.1.220
+**Sources**:
+- https://code.claude.com/docs/en/skills
+**Compatible Models**: Claude Fable 5, Claude Opus 5, Claude Sonnet 5, Claude Sonnet 4.6, Claude Opus 4.8, Claude Haiku 4.5
@@ -11,3 +11,11 @@

 ## Educational Blog Post
 "Let's explore how agents improve code review workflows. Here's what we learned..."
+
+---
+
+**Last Updated**: August 4, 2026
+**Claude Code Version**: 2.1.220
+**Sources**:
+- https://code.claude.com/docs/en/skills
+**Compatible Models**: Claude Fable 5, Claude Opus 5, Claude Sonnet 5, Claude Sonnet 4.6, Claude Opus 4.8, Claude Haiku 4.5
@@ -193,10 +193,14 @@ Before finalizing, verify:

 If the user requests AGENTS.md creation/update:

-AGENTS.md is used for defining specialized agent behaviors. Unlike CLAUDE.md (which is for project context), AGENTS.md defines:
- Custom agent roles and capabilities
- Agent-specific instructions and constraints
- Workflow definitions for multi-agent scenarios
+**Claude Code does not read AGENTS.md directly.** To make it take effect, import it from CLAUDE.md with `@AGENTS.md`, or symlink `CLAUDE.md` to it. This is the single most common misunderstanding about the file.
+
+AGENTS.md is a cross-tool project-context file — the same *category* of document as CLAUDE.md, not an agent-definition format. It exists so several coding agents can share one set of project conventions:
+- Build, test, and lint commands
+- Code style and architectural conventions
+- Repository layout and where things live
+
+Subagents are defined separately, in `.claude/agents/*.md` — not in AGENTS.md.

 Apply similar principles:
 - Keep focused and concise
@@ -210,3 +214,11 @@ Apply similar principles:
 - The system reminder tells Claude that CLAUDE.md "may or may not be relevant" - the more noise, the more it gets ignored
 - Monorepos benefit most from clear WHAT/WHY/HOW structure
 - Directory-specific CLAUDE.md files should be even more focused
+
+---
+
+**Last Updated**: August 4, 2026
+**Claude Code Version**: 2.1.220
+**Sources**:
+- https://code.claude.com/docs/en/skills
+**Compatible Models**: Claude Fable 5, Claude Opus 5, Claude Sonnet 5, Claude Sonnet 4.6, Claude Opus 4.8, Claude Haiku 4.5
@@ -77,3 +77,11 @@ List maintainability problems with improvements
 ## Version History

 - v1.0.0 (2024-12-10): Initial release with security, performance, quality, and maintainability analysis
+
+---
+
+**Last Updated**: August 4, 2026
+**Claude Code Version**: 2.1.220
+**Sources**:
+- https://code.claude.com/docs/en/skills
+**Compatible Models**: Claude Fable 5, Claude Opus 5, Claude Sonnet 5, Claude Sonnet 4.6, Claude Opus 4.8, Claude Haiku 4.5
@@ -110,3 +110,11 @@ When reviewing multiple findings, track:
 **Recommendation:** ✅ Approve / ⚠️ Request Changes / 🔄 Needs Discussion

 **Overall Code Quality:** 1-5 stars
+
+---
+
+**Last Updated**: August 4, 2026
+**Claude Code Version**: 2.1.220
+**Sources**:
+- https://code.claude.com/docs/en/skills
+**Compatible Models**: Claude Fable 5, Claude Opus 5, Claude Sonnet 5, Claude Sonnet 4.6, Claude Opus 4.8, Claude Haiku 4.5
@@ -45,3 +45,11 @@
 - [ ] No flaky tests
 - [ ] Mock external dependencies
 - [ ] Clear test names
+
+---
+
+**Last Updated**: August 4, 2026
+**Claude Code Version**: 2.1.220
+**Sources**:
+- https://code.claude.com/docs/en/skills
+**Compatible Models**: Claude Fable 5, Claude Opus 5, Claude Sonnet 5, Claude Sonnet 4.6, Claude Opus 4.8, Claude Haiku 4.5
@@ -18,7 +18,7 @@ description: Generate comprehensive, accurate API documentation from source code

 ### For Each Endpoint

-```markdown
+````markdown
 ## GET /api/v1/users/:id

 ### Description
@@ -73,4 +73,12 @@ response = requests.get(
 )
 user = response.json()
 ```
-```
+````
+
+---
+
+**Last Updated**: August 4, 2026
+**Claude Code Version**: 2.1.220
+**Sources**:
+- https://code.claude.com/docs/en/skills
+**Compatible Models**: Claude Fable 5, Claude Opus 5, Claude Sonnet 5, Claude Sonnet 4.6, Claude Opus 4.8, Claude Haiku 4.5
@@ -1,5 +1,5 @@
 ---
-name: code-refactor
+name: refactor
 description: Systematic code refactoring based on Martin Fowler's methodology. Use when users ask to refactor code, improve code structure, reduce technical debt, clean up legacy code, eliminate code smells, or improve code maintainability. This skill guides through a phased approach with research, planning, and safe incremental implementation.
 ---

@@ -424,3 +424,11 @@ function processOrder(order) {
 ## Version History

 - v1.0.0 (2025-01-15): Initial release with Fowler methodology, phased approach, user consultation points
+
+---
+
+**Last Updated**: August 4, 2026
+**Claude Code Version**: 2.1.220
+**Sources**:
+- https://code.claude.com/docs/en/skills
+**Compatible Models**: Claude Fable 5, Claude Opus 5, Claude Sonnet 5, Claude Sonnet 4.6, Claude Opus 4.8, Claude Haiku 4.5
@@ -667,3 +667,11 @@ Use this checklist when scanning code:
 - Fowler, M. (2018). *Refactoring: Improving the Design of Existing Code* (2nd ed.)
 - Kerievsky, J. (2004). *Refactoring to Patterns*
 - Feathers, M. (2004). *Working Effectively with Legacy Code*
+
+---
+
+**Last Updated**: August 4, 2026
+**Claude Code Version**: 2.1.220
+**Sources**:
+- https://code.claude.com/docs/en/skills
+**Compatible Models**: Claude Fable 5, Claude Opus 5, Claude Sonnet 5, Claude Sonnet 4.6, Claude Opus 4.8, Claude Haiku 4.5
@@ -1021,3 +1021,11 @@ class TelephoneNumber {

 - Fowler, M. (2018). *Refactoring: Improving the Design of Existing Code* (2nd ed.)
 - Online catalog: https://refactoring.com/catalog/
+
+---
+
+**Last Updated**: August 4, 2026
+**Claude Code Version**: 2.1.220
+**Sources**:
+- https://code.claude.com/docs/en/skills
+**Compatible Models**: Claude Fable 5, Claude Opus 5, Claude Sonnet 5, Claude Sonnet 4.6, Claude Opus 4.8, Claude Haiku 4.5
@@ -282,3 +282,11 @@ refactor: [Describe the refactoring]
 - [Testing framework]
 - [Linting tools]
 - [Complexity analysis tools]
+
+---
+
+**Last Updated**: August 4, 2026
+**Claude Code Version**: 2.1.220
+**Sources**:
+- https://code.claude.com/docs/en/skills
+**Compatible Models**: Claude Fable 5, Claude Opus 5, Claude Sonnet 5, Claude Sonnet 4.6, Claude Opus 4.8, Claude Haiku 4.5
@@ -136,6 +136,7 @@ to solving problems.
 | `effort` | No | Reasoning effort level: `low`, `medium`, `high`, `xhigh`, or `max`. Overrides the session effort level; available levels depend on the model |
 | `isolation` | No | Set to `worktree` to give the subagent its own git worktree |
 | `initialPrompt` | No | Auto-submitted first turn when the subagent runs as the main agent |
+| `color` | No | Display color for the subagent in the task list and transcript. Accepts `red`, `blue`, `green`, `yellow`, `purple`, `orange`, `pink`, or `cyan` |

 ### Main-Thread Agent Frontmatter Honoring (v2.1.117+/v2.1.119+)

@@ -1127,6 +1128,38 @@ This folder contains ready-to-use example subagents:

 ---

+### 8. Clean Code Reviewer (`clean-code-reviewer.md`)
+
+**Purpose**: Readability and maintainability review against clean-code principles
+
+**Tools**: Read, Grep, Glob, Bash
+
+**Specialization**:
+- Naming, function length, and argument count
+- Duplication and dead code
+- Comment quality and intent
+- Structural clarity over cleverness
+
+**Use When**: You want a style and maintainability pass distinct from correctness review
+
+---
+
+### 9. Performance Optimizer (`performance-optimizer.md`)
+
+**Purpose**: Identify and remediate performance bottlenecks
+
+**Tools**: Read, Edit, Bash, Grep, Glob
+
+**Specialization**:
+- Algorithmic complexity and hot paths
+- Memory allocation and leaks
+- Caching and query optimization
+- Concurrency and I/O bottlenecks
+
+**Use When**: Code is measurably slow and you need targeted optimization
+
+---
+
 ## Installation Instructions

 ### Method 1: Ask Claude (Recommended)
@@ -1196,7 +1229,9 @@ project/
 │       ├── secure-reviewer.md
 │       ├── implementation-agent.md
 │       ├── debugger.md
-│       └── data-scientist.md
+│       ├── data-scientist.md
+│       ├── clean-code-reviewer.md
+│       └── performance-optimizer.md
 └── ...
 ```

@@ -1285,4 +1320,4 @@ See the OpenTelemetry section in [Advanced Features → Telemetry](../09-advance
 - https://github.com/anthropics/claude-code/releases/tag/v2.1.139
 - https://github.com/anthropics/claude-code/releases/tag/v2.1.140
 - https://code.claude.com/docs/en/model-config
-**Compatible Models**: Claude Opus 5, Claude Sonnet 5, Claude Sonnet 4.6, Claude Opus 4.8, Claude Haiku 4.5
+**Compatible Models**: Claude Fable 5, Claude Opus 5, Claude Sonnet 5, Claude Sonnet 4.6, Claude Opus 4.8, Claude Haiku 4.5
@@ -66,4 +66,8 @@ Fix: [how to fix]
 **Core Philosophy**: Code is read 10x more than written. Optimize for readability, not cleverness.

 ---
-**Last Updated**: April 9, 2026
+**Last Updated**: August 4, 2026
+**Claude Code Version**: 2.1.220
+**Sources**:
+- https://code.claude.com/docs/en/sub-agents
+**Compatible Models**: Claude Fable 5, Claude Opus 5, Claude Sonnet 5, Claude Sonnet 4.6, Claude Opus 4.8, Claude Haiku 4.5
@@ -61,4 +61,8 @@ Include specific examples of how to fix issues.
 - **Impact**: Response time increases linearly with data size

 ---
-**Last Updated**: April 9, 2026
+**Last Updated**: August 4, 2026
+**Claude Code Version**: 2.1.220
+**Sources**:
+- https://code.claude.com/docs/en/sub-agents
+**Compatible Models**: Claude Fable 5, Claude Opus 5, Claude Sonnet 5, Claude Sonnet 4.6, Claude Opus 4.8, Claude Haiku 4.5
@@ -97,4 +97,8 @@ ORDER BY 1 DESC;
 - [ ] Recommendations provided

 ---
-**Last Updated**: April 9, 2026
+**Last Updated**: August 4, 2026
+**Claude Code Version**: 2.1.220
+**Sources**:
+- https://code.claude.com/docs/en/sub-agents
+**Compatible Models**: Claude Fable 5, Claude Opus 5, Claude Sonnet 5, Claude Sonnet 4.6, Claude Opus 4.8, Claude Haiku 4.5
@@ -80,4 +80,8 @@ npm test -- --grep "test name"
 - [ ] No regressions introduced

 ---
-**Last Updated**: April 9, 2026
+**Last Updated**: August 4, 2026
+**Claude Code Version**: 2.1.220
+**Sources**:
+- https://code.claude.com/docs/en/sub-agents
+**Compatible Models**: Claude Fable 5, Claude Opus 5, Claude Sonnet 5, Claude Sonnet 4.6, Claude Opus 4.8, Claude Haiku 4.5
@@ -61,7 +61,7 @@ For each documentation created:

 ## API Documentation Example

-```markdown
+````markdown
 ## GET /api/users/:id

 Retrieves a user by their unique identifier.
@@ -95,7 +95,11 @@ Retrieves a user by their unique identifier.
 curl -X GET https://api.example.com/api/users/abc123 \
  -H "Authorization: Bearer <token>"
 ```
-```
+````

 ---
-**Last Updated**: April 9, 2026
+**Last Updated**: August 4, 2026
+**Claude Code Version**: 2.1.220
+**Sources**:
+- https://code.claude.com/docs/en/sub-agents
+**Compatible Models**: Claude Fable 5, Claude Opus 5, Claude Sonnet 5, Claude Sonnet 4.6, Claude Opus 4.8, Claude Haiku 4.5
@@ -78,4 +78,8 @@ Before marking complete:
 - [ ] Error handling implemented

 ---
-**Last Updated**: April 9, 2026
+**Last Updated**: August 4, 2026
+**Claude Code Version**: 2.1.220
+**Sources**:
+- https://code.claude.com/docs/en/sub-agents
+**Compatible Models**: Claude Fable 5, Claude Opus 5, Claude Sonnet 5, Claude Sonnet 4.6, Claude Opus 4.8, Claude Haiku 4.5
@@ -126,4 +126,8 @@ For each optimization delivered:
 - [ ] Monitoring / alerting recommended

 ---
-**Last Updated**: April 9, 2026
+**Last Updated**: August 4, 2026
+**Claude Code Version**: 2.1.220
+**Sources**:
+- https://code.claude.com/docs/en/sub-agents
+**Compatible Models**: Claude Fable 5, Claude Opus 5, Claude Sonnet 5, Claude Sonnet 4.6, Claude Opus 4.8, Claude Haiku 4.5
@@ -75,4 +75,8 @@ For each vulnerability:
 - **Remediation**: How to fix it

 ---
-**Last Updated**: April 9, 2026
+**Last Updated**: August 4, 2026
+**Claude Code Version**: 2.1.220
+**Sources**:
+- https://code.claude.com/docs/en/sub-agents
+**Compatible Models**: Claude Fable 5, Claude Opus 5, Claude Sonnet 5, Claude Sonnet 4.6, Claude Opus 4.8, Claude Haiku 4.5
@@ -74,4 +74,8 @@ describe('Feature: User Authentication', () => {
 ```

 ---
-**Last Updated**: April 9, 2026
+**Last Updated**: August 4, 2026
+**Claude Code Version**: 2.1.220
+**Sources**:
+- https://code.claude.com/docs/en/sub-agents
+**Compatible Models**: Claude Fable 5, Claude Opus 5, Claude Sonnet 5, Claude Sonnet 4.6, Claude Opus 4.8, Claude Haiku 4.5
@@ -324,11 +324,22 @@ This allows Claude to fetch and include MCP resource content inline as part of t

 MCP configurations can be stored at different scopes with varying levels of sharing:

-| Scope | Location | Description | Shared With | Requires Approval |
-|-------|----------|-------------|-------------|------------------|
-| **Local** (default) | `~/.claude.json` (under project path) | Private to current user, current project only (was called `project` in older versions) | Just you | No |
-| **Project** | `.mcp.json` | Checked into git repository | Team members | Yes (first use) |
-| **User** | `~/.claude.json` | Available across all projects (was called `global` in older versions) | Just you | No |
+| Scope | Flag | Location | Description | Shared With | Requires Approval |
+|-------|------|----------|-------------|-------------|------------------|
+| **Local** (default) | `--scope local` | `~/.claude.json` (under project path) | Private to current user, current project only (was called `project` in older versions) | Just you | No |
+| **Project** | `--scope project` | `.mcp.json` | Checked into git repository | Team members | Yes (first use) |
+| **User** | `--scope user` | `~/.claude.json` | Available across all projects (was called `global` in older versions) | Just you | No |
+
+Select a scope when adding a server with `--scope` (short form `-s`). Omit it and
+Claude Code uses `local`:
+
+```bash
+# Project scope — writes to .mcp.json so the team shares it
+claude mcp add --scope project --transport http github https://api.github.com/mcp
+
+# User scope — available in every project
+claude mcp add --scope user --transport stdio memory -- npx @modelcontextprotocol/server-memory
+```

 ### Using Project Scope

@@ -378,8 +389,13 @@ claude mcp logout github

 # Import from Claude Desktop
 claude mcp add-from-claude-desktop
+
+# Add a server from a JSON blob (useful for scripted setup)
+claude mcp add-json events-server '{"type":"stdio","command":"npx","args":["@modelcontextprotocol/server-events"]}'
 ```

+> **Note**: In JSON configs — `.mcp.json`, `~/.claude.json`, or `claude mcp add-json` — the `type` field accepts `streamable-http` as an alias for `http`. The MCP specification uses the name `streamable-http` for this transport, so configurations copied from a server's own documentation work unmodified.
+
 `claude mcp login <name>` / `claude mcp logout <name>` are the non-interactive equivalent of the OAuth flow in the `/mcp` menu — authenticate or sign out without opening it. Add `--no-browser` to `login` to complete OAuth over SSH or in a headless session (it redirects the flow through stdin).

 ## Available MCP Servers Table
@@ -503,7 +519,7 @@ Variables are expanded at runtime:
      "command": "npx",
      "args": ["@modelcontextprotocol/server-database"],
      "env": {
-        "DATABASE_URL": "postgresql://user:pass@localhost/mydb"
+        "DATABASE_URL": "${DATABASE_URL}"
      }
    }
  }
@@ -1236,7 +1252,7 @@ export GITHUB_TOKEN="your_token"

 ---

-**Last Updated**: July 29, 2026
+**Last Updated**: August 4, 2026
 **Claude Code Version**: 2.1.220
 **Sources**:
 - https://code.claude.com/docs/en/mcp
@@ -1245,4 +1261,4 @@ export GITHUB_TOKEN="your_token"
 - https://github.com/anthropics/claude-code/releases/tag/v2.1.139
 - https://github.com/anthropics/claude-code/blob/main/CHANGELOG.md
 - https://code.claude.com/docs/en/model-config
-**Compatible Models**: Claude Opus 5, Claude Sonnet 5, Claude Sonnet 4.6, Claude Opus 4.8, Claude Haiku 4.5
+**Compatible Models**: Claude Fable 5, Claude Opus 5, Claude Sonnet 5, Claude Sonnet 4.6, Claude Opus 4.8, Claude Haiku 4.5
@@ -1,10 +1,13 @@
 {
  "mcpServers": {
    "database": {
+      "type": "stdio",
      "command": "npx",
-      "args": ["@modelcontextprotocol/server-database"],
+      "args": [
+        "@modelcontextprotocol/server-database"
+      ],
      "env": {
-        "DATABASE_URL": "postgresql://user:pass@localhost/mydb"
+        "DATABASE_URL": "${DATABASE_URL}"
      }
    }
  }
@@ -1,8 +1,12 @@
 {
  "mcpServers": {
    "filesystem": {
+      "type": "stdio",
      "command": "npx",
-      "args": ["@modelcontextprotocol/server-filesystem", "/home/user/projects"]
+      "args": [
+        "@modelcontextprotocol/server-filesystem",
+        "/home/user/projects"
+      ]
    }
  }
 }
@@ -1,8 +1,11 @@
 {
  "mcpServers": {
    "github": {
+      "type": "stdio",
      "command": "npx",
-      "args": ["@modelcontextprotocol/server-github"],
+      "args": [
+        "@modelcontextprotocol/server-github"
+      ],
      "env": {
        "GITHUB_TOKEN": "${GITHUB_TOKEN}"
      }
@@ -1,29 +1,42 @@
 {
  "mcpServers": {
    "github": {
+      "type": "stdio",
      "command": "npx",
-      "args": ["@modelcontextprotocol/server-github"],
+      "args": [
+        "@modelcontextprotocol/server-github"
+      ],
      "env": {
        "GITHUB_TOKEN": "${GITHUB_TOKEN}"
      }
    },
    "database": {
+      "type": "stdio",
      "command": "npx",
-      "args": ["@modelcontextprotocol/server-database"],
+      "args": [
+        "@modelcontextprotocol/server-database"
+      ],
      "env": {
        "DATABASE_URL": "${DATABASE_URL}"
      }
    },
    "slack": {
+      "type": "stdio",
      "command": "npx",
-      "args": ["@modelcontextprotocol/server-slack"],
+      "args": [
+        "@modelcontextprotocol/server-slack"
+      ],
      "env": {
        "SLACK_TOKEN": "${SLACK_TOKEN}"
      }
    },
    "filesystem": {
+      "type": "stdio",
      "command": "npx",
-      "args": ["@modelcontextprotocol/server-filesystem", "/home/user/projects"]
+      "args": [
+        "@modelcontextprotocol/server-filesystem",
+        "/home/user/projects"
+      ]
    }
  }
 }
@@ -299,8 +299,13 @@ Runs after Claude creates tool parameters and before processing. Use this to val
 **Common matchers:** `Task`, `Bash`, `Glob`, `Grep`, `Read`, `Edit`, `Write`, `WebFetch`, `WebSearch`

 **Output control:**
- `permissionDecision`: `"allow"`, `"deny"`, or `"ask"`
- `permissionDecisionReason`: Explanation for decision
+- `permissionDecision`: `"allow"`, `"deny"`, `"ask"`, or `"defer"`
+  - `"allow"` skips the permission prompt (except for tools that require user interaction, and connector tools your organization set to `ask`)
+  - `"deny"` prevents the tool call
+  - `"ask"` prompts the user to confirm
+  - `"defer"` exits gracefully so the tool can be resumed later; `permissionDecisionReason`, `updatedInput` and `additionalContext` are all ignored for this value
+  - Deny and ask rules are still evaluated regardless of what the hook returns. When multiple `PreToolUse` hooks disagree, precedence is `deny` > `defer` > `ask` > `allow`
+- `permissionDecisionReason`: Explanation for decision. Shown to the user (not Claude) for `"allow"` and `"ask"`; shown to Claude for `"deny"`; ignored for `"defer"`
 - `updatedInput`: Modified tool input parameters

 ### PostToolUse
@@ -1512,9 +1517,10 @@ Edit `~/.claude/settings.json` or `.claude/settings.json` with the hook configur

 ---

-**Last Updated**: July 29, 2026
+**Last Updated**: August 4, 2026
 **Claude Code Version**: 2.1.220
 **Sources**:
 - https://code.claude.com/docs/en/hooks
 - https://github.com/anthropics/claude-code/blob/main/CHANGELOG.md
 - https://code.claude.com/docs/en/sub-agents
+**Compatible Models**: Claude Fable 5, Claude Opus 5, Claude Sonnet 5, Claude Sonnet 4.6, Claude Opus 4.8, Claude Haiku 4.5
@@ -32,7 +32,7 @@ except ImportError:
    )

 # Configuration
-CONTEXT_LIMIT = 128000  # Claude's context window (adjust for your model)
+CONTEXT_LIMIT = 1000000  # 1M on Opus 5, Sonnet 5, Opus 4.8, Sonnet 4.6; 200000 on Haiku 4.5 (adjust for your model)


 def get_state_file(session_id: str) -> str:
@@ -19,7 +19,7 @@ import sys
 import tempfile

 # Configuration
-CONTEXT_LIMIT = 128000  # Claude's context window (adjust for your model)
+CONTEXT_LIMIT = 1000000  # 1M on Opus 5, Sonnet 5, Opus 4.8, Sonnet 4.6; 200000 on Haiku 4.5 (adjust for your model)


 def get_state_file(session_id: str) -> str:
@@ -1,15 +1,21 @@
 #!/bin/bash
 # Check for known vulnerabilities in dependencies after manifest files are modified.
-# Hook: PostToolUse:Write
+# Hook: PostToolUse (matcher: Write)
+#
+# Reads the target file path from stdin JSON (Claude Code hook protocol).
+# Source: https://code.claude.com/docs/en/hooks

-FILE=$1
+# Read JSON input from stdin (Claude Code hook protocol)
+INPUT=$(cat)
+
+# Extract file_path using sed (compatible with all platforms)
+FILE=$(echo "$INPUT" | sed -n 's/.*"file_path"[[:space:]]*:[[:space:]]*"\([^"]*\)".*/\1/p' | head -1)

 if [ -z "$FILE" ]; then
-  echo "Usage: $0 <file_path>"
  exit 0
 fi

-# Use basename for matching — $1 may be an absolute path
+# Use basename for matching — file_path may be an absolute path
 BASENAME=$(basename "$FILE")

 # Only run when a dependency manifest is written
@@ -1,6 +1,6 @@
 #!/bin/bash
 # Auto-format code after writing
-# Hook: PostToolUse:Write
+# Hook: PostToolUse (matcher: Write)
 #
 # Reads the target file path from stdin JSON and runs the appropriate formatter
 # in-place on the file after Claude writes it.
@@ -1,6 +1,6 @@
 #!/bin/bash
 # Log all bash commands
-# Hook: PostToolUse:Bash
+# Hook: PostToolUse (matcher: Bash)
 #
 # Reads the executed command from stdin JSON and logs it to a file.
 #
@@ -3,6 +3,10 @@
 # Hook: PreToolUse (matcher: Bash) - checks if the command is a git commit
 # Note: There is no "PreCommit" hook event. Use PreToolUse with a Bash matcher
 # and inspect the command to detect git commit operations.
+#
+# Exit codes: 2 blocks the tool call and surfaces stderr as the block reason.
+# Any other non-zero value is a NON-blocking error — the commit would proceed.
+# Source: https://code.claude.com/docs/en/hooks

 echo "🧪 Running tests before commit..."

@@ -11,8 +15,8 @@ if [ -f "package.json" ]; then
  if grep -q "\"test\":" package.json; then
    npm test
    if [ $? -ne 0 ]; then
-      echo "❌ Tests failed! Commit blocked."
-      exit 1
+      echo "❌ Tests failed! Commit blocked." >&2
+      exit 2
    fi
  fi
 fi
@@ -22,8 +26,8 @@ if [ -f "pytest.ini" ] || [ -f "setup.py" ]; then
  if command -v pytest &> /dev/null; then
    pytest
    if [ $? -ne 0 ]; then
-      echo "❌ Tests failed! Commit blocked."
-      exit 1
+      echo "❌ Tests failed! Commit blocked." >&2
+      exit 2
    fi
  fi
 fi
@@ -32,8 +36,8 @@ fi
 if [ -f "go.mod" ]; then
  go test ./...
  if [ $? -ne 0 ]; then
-    echo "❌ Tests failed! Commit blocked."
-    exit 1
+    echo "❌ Tests failed! Commit blocked." >&2
+    exit 2
  fi
 fi

@@ -41,8 +45,8 @@ fi
 if [ -f "Cargo.toml" ]; then
  cargo test
  if [ $? -ne 0 ]; then
-    echo "❌ Tests failed! Commit blocked."
-    exit 1
+    echo "❌ Tests failed! Commit blocked." >&2
+    exit 2
  fi
 fi

@@ -1,6 +1,6 @@
 #!/bin/bash
 # Security scan on file write
-# Hook: PostToolUse:Write
+# Hook: PostToolUse (matcher: Write)
 #
 # Scans files for hardcoded secrets, API keys, and credentials.
 # Outputs a non-blocking warning via additionalContext when issues are found.
@@ -92,3 +92,5 @@ echo ""
 echo " Saved to $PROGRESS_FILE"
 [ -n "$NOTES" ] && echo " Notes: $NOTES"
 echo ""
+
+exit 0
@@ -386,7 +386,7 @@ This command initiates a complete pull request review including:
 ---
 name: security-reviewer
 description: Security-focused code review
-tools: read, grep, diff
+tools: Read, Grep, Bash
 ---

 # Security Reviewer
@@ -466,7 +466,16 @@ documentation/

 ## Plugin Marketplace

-The official Anthropic-managed plugin directory is `anthropics/claude-plugins-official`. Enterprise admins can also create private plugin marketplaces for internal distribution.
+The official Anthropic-managed plugin directory is `anthropics/claude-plugins-official`, auto-registered on first interactive launch. Enterprise admins can also create private plugin marketplaces for internal distribution.
+
+There is also a **community marketplace**, `anthropics/claude-plugins-community`, hosting third-party plugins that have passed Anthropic's automated validation and safety screening — each pinned to a specific commit SHA in the catalog. Unlike the official marketplace you add it manually:
+
+```bash
+/plugin marketplace add anthropics/claude-plugins-community
+
+# Then install from it using the claude-community marketplace name
+/plugin install <plugin-name>@claude-community
+```

 ```mermaid
 graph TB
@@ -941,7 +950,7 @@ Complete PR review workflow with security, testing, and documentation checks.
 ```

 ## Requirements
- Claude Code 1.0+
+- Claude Code 2.1+
 - GitHub access
 - CodeQL (optional)
 ```
@@ -1125,7 +1134,7 @@ The following Claude Code features work together with plugins:

 ---

-**Last Updated**: July 29, 2026
+**Last Updated**: August 4, 2026
 **Claude Code Version**: 2.1.220
 **Sources**:
 - https://code.claude.com/docs/en/plugins
@@ -1143,4 +1152,4 @@ The following Claude Code features work together with plugins:
 - https://github.com/anthropics/claude-code/releases/tag/v2.1.143
 - https://code.claude.com/docs/en/cli-reference
 - https://code.claude.com/docs/en/model-config
-**Compatible Models**: Claude Opus 5, Claude Sonnet 5, Claude Sonnet 4.6, Claude Opus 4.8, Claude Haiku 4.5
+**Compatible Models**: Claude Fable 5, Claude Opus 5, Claude Sonnet 5, Claude Sonnet 4.6, Claude Opus 4.8, Claude Haiku 4.5
@@ -75,7 +75,7 @@ Complete DevOps automation for deployment, monitoring, and incident response.

 ## Requirements

- Claude Code 1.0+
+- Claude Code 2.1+
 - Kubernetes CLI (kubectl)
 - Cluster access configured

@@ -108,11 +108,11 @@ Result:

 ---

-**Last Updated**: July 29, 2026
+**Last Updated**: August 4, 2026
 **Claude Code Version**: 2.1.220
 **Sources**:
 - https://code.claude.com/docs/en/plugins
 - https://github.com/anthropics/claude-code/releases/tag/v2.1.131
 - https://github.com/anthropics/claude-code/releases/tag/v2.1.138
 - https://code.claude.com/docs/en/model-config
-**Compatible Models**: Claude Opus 5, Claude Sonnet 5, Claude Sonnet 4.6, Claude Opus 4.8, Claude Haiku 4.5
+**Compatible Models**: Claude Fable 5, Claude Opus 5, Claude Sonnet 5, Claude Sonnet 4.6, Claude Opus 4.8, Claude Haiku 4.5
@@ -1,7 +1,7 @@
 ---
 name: alert-analyzer
 description: Analyzes monitoring alerts and system metrics
-tools: read, grep, bash
+tools: Read, Grep, Bash
 ---

 # Alert Analyzer
@@ -12,3 +12,11 @@ Analyzes system health and alerts:
 - Root cause identification
 - Metric visualization
 - Proactive issue detection
+
+---
+
+**Last Updated**: August 4, 2026
+**Claude Code Version**: 2.1.220
+**Sources**:
+- https://code.claude.com/docs/en/plugins
+**Compatible Models**: Claude Fable 5, Claude Opus 5, Claude Sonnet 5, Claude Sonnet 4.6, Claude Opus 4.8, Claude Haiku 4.5
@@ -1,7 +1,7 @@
 ---
 name: deployment-specialist
 description: Handles all deployment operations
-tools: read, write, bash, grep
+tools: Read, Write, Bash, Grep
 ---

 # Deployment Specialist
@@ -12,3 +12,11 @@ Expert in deployment operations:
 - Rollback procedures
 - Health checks
 - Database migrations
+
+---
+
+**Last Updated**: August 4, 2026
+**Claude Code Version**: 2.1.220
+**Sources**:
+- https://code.claude.com/docs/en/plugins
+**Compatible Models**: Claude Fable 5, Claude Opus 5, Claude Sonnet 5, Claude Sonnet 4.6, Claude Opus 4.8, Claude Haiku 4.5
@@ -1,7 +1,7 @@
 ---
 name: incident-commander
 description: Coordinates incident response
-tools: read, write, bash, grep
+tools: Read, Write, Bash, Grep
 ---

 # Incident Commander
@@ -12,3 +12,11 @@ Manages incident response:
 - Status updates
 - Resolution tracking
 - Post-mortem facilitation
+
+---
+
+**Last Updated**: August 4, 2026
+**Claude Code Version**: 2.1.220
+**Sources**:
+- https://code.claude.com/docs/en/plugins
+**Compatible Models**: Claude Fable 5, Claude Opus 5, Claude Sonnet 5, Claude Sonnet 4.6, Claude Opus 4.8, Claude Haiku 4.5
@@ -13,3 +13,11 @@ Execute deployment workflow:
 4. Deploy to target environment
 5. Run health checks
 6. Notify team on Slack
+
+---
+
+**Last Updated**: August 4, 2026
+**Claude Code Version**: 2.1.220
+**Sources**:
+- https://code.claude.com/docs/en/plugins
+**Compatible Models**: Claude Fable 5, Claude Opus 5, Claude Sonnet 5, Claude Sonnet 4.6, Claude Opus 4.8, Claude Haiku 4.5
@@ -14,3 +14,11 @@ Structured incident response workflow:
 5. Coordinate response efforts
 6. Document resolution
 7. Schedule post-mortem
+
+---
+
+**Last Updated**: August 4, 2026
+**Claude Code Version**: 2.1.220
+**Sources**:
+- https://code.claude.com/docs/en/plugins
+**Compatible Models**: Claude Fable 5, Claude Opus 5, Claude Sonnet 5, Claude Sonnet 4.6, Claude Opus 4.8, Claude Haiku 4.5
@@ -12,3 +12,11 @@ Rollback to previous stable version:
 3. Execute rollback procedure
 4. Run health checks
 5. Notify team
+
+---
+
+**Last Updated**: August 4, 2026
+**Claude Code Version**: 2.1.220
+**Sources**:
+- https://code.claude.com/docs/en/plugins
+**Compatible Models**: Claude Fable 5, Claude Opus 5, Claude Sonnet 5, Claude Sonnet 4.6, Claude Opus 4.8, Claude Haiku 4.5
@@ -13,3 +13,11 @@ Check system health across all services:
 4. Review error rates
 5. Check resource utilization
 6. Report overall health
+
+---
+
+**Last Updated**: August 4, 2026
+**Claude Code Version**: 2.1.220
+**Sources**:
+- https://code.claude.com/docs/en/plugins
+**Compatible Models**: Claude Fable 5, Claude Opus 5, Claude Sonnet 5, Claude Sonnet 4.6, Claude Opus 4.8, Claude Haiku 4.5
@@ -66,7 +66,7 @@ Comprehensive documentation generation and maintenance for your project.

 ## Requirements

- Claude Code 1.0+
+- Claude Code 2.1+
 - GitHub access (optional)

 ## Example Workflow
@@ -120,11 +120,11 @@ export GITHUB_TOKEN="your_github_token"

 ---

-**Last Updated**: July 29, 2026
+**Last Updated**: August 4, 2026
 **Claude Code Version**: 2.1.220
 **Sources**:
 - https://code.claude.com/docs/en/plugins
 - https://github.com/anthropics/claude-code/releases/tag/v2.1.131
 - https://github.com/anthropics/claude-code/releases/tag/v2.1.138
 - https://code.claude.com/docs/en/model-config
-**Compatible Models**: Claude Opus 5, Claude Sonnet 5, Claude Sonnet 4.6, Claude Opus 4.8, Claude Haiku 4.5
+**Compatible Models**: Claude Fable 5, Claude Opus 5, Claude Sonnet 5, Claude Sonnet 4.6, Claude Opus 4.8, Claude Haiku 4.5
@@ -1,7 +1,7 @@
 ---
 name: api-documenter
 description: API documentation specialist
-tools: read, write, grep
+tools: Read, Write, Grep
 ---

 # API Documenter
@@ -12,3 +12,11 @@ Creates comprehensive API documentation:
 - Response schemas
 - Code examples (curl, JS, Python)
 - Error codes
+
+---
+
+**Last Updated**: August 4, 2026
+**Claude Code Version**: 2.1.220
+**Sources**:
+- https://code.claude.com/docs/en/plugins
+**Compatible Models**: Claude Fable 5, Claude Opus 5, Claude Sonnet 5, Claude Sonnet 4.6, Claude Opus 4.8, Claude Haiku 4.5
@@ -1,7 +1,7 @@
 ---
 name: code-commentator
 description: Code comment and inline documentation specialist
-tools: read, write, edit
+tools: Read, Write, Edit
 ---

 # Code Commentator
@@ -12,3 +12,11 @@ Improves code documentation:
 - Parameter descriptions
 - Return type documentation
 - Usage examples
+
+---
+
+**Last Updated**: August 4, 2026
+**Claude Code Version**: 2.1.220
+**Sources**:
+- https://code.claude.com/docs/en/plugins
+**Compatible Models**: Claude Fable 5, Claude Opus 5, Claude Sonnet 5, Claude Sonnet 4.6, Claude Opus 4.8, Claude Haiku 4.5
@@ -1,7 +1,7 @@
 ---
 name: example-generator
 description: Code example and tutorial specialist
-tools: read, write
+tools: Read, Write
 ---

 # Example Generator
@@ -12,3 +12,11 @@ Creates practical code examples:
 - Integration examples
 - Best practices
 - Troubleshooting scenarios
+
+---
+
+**Last Updated**: August 4, 2026
+**Claude Code Version**: 2.1.220
+**Sources**:
+- https://code.claude.com/docs/en/plugins
+**Compatible Models**: Claude Fable 5, Claude Opus 5, Claude Sonnet 5, Claude Sonnet 4.6, Claude Opus 4.8, Claude Haiku 4.5
@@ -13,3 +13,11 @@ Generate complete API documentation:
 4. Create markdown with examples
 5. Include request/response schemas
 6. Add error documentation
+
+---
+
+**Last Updated**: August 4, 2026
+**Claude Code Version**: 2.1.220
+**Sources**:
+- https://code.claude.com/docs/en/plugins
+**Compatible Models**: Claude Fable 5, Claude Opus 5, Claude Sonnet 5, Claude Sonnet 4.6, Claude Opus 4.8, Claude Haiku 4.5
@@ -13,3 +13,11 @@ Generate comprehensive README:
 4. API documentation links
 5. Contributing guidelines
 6. License information
+
+---
+
+**Last Updated**: August 4, 2026
+**Claude Code Version**: 2.1.220
+**Sources**:
+- https://code.claude.com/docs/en/plugins
+**Compatible Models**: Claude Fable 5, Claude Opus 5, Claude Sonnet 5, Claude Sonnet 4.6, Claude Opus 4.8, Claude Haiku 4.5
@@ -12,3 +12,11 @@ Synchronize documentation with codebase:
 3. Update affected docs
 4. Verify examples still work
 5. Update version numbers
+
+---
+
+**Last Updated**: August 4, 2026
+**Claude Code Version**: 2.1.220
+**Sources**:
+- https://code.claude.com/docs/en/plugins
+**Compatible Models**: Claude Fable 5, Claude Opus 5, Claude Sonnet 5, Claude Sonnet 4.6, Claude Opus 4.8, Claude Haiku 4.5
@@ -12,3 +12,11 @@ Validate documentation quality:
 3. Ensure completeness
 4. Check formatting
 5. Validate against actual code
+
+---
+
+**Last Updated**: August 4, 2026
+**Claude Code Version**: 2.1.220
+**Sources**:
+- https://code.claude.com/docs/en/plugins
+**Compatible Models**: Claude Fable 5, Claude Opus 5, Claude Sonnet 5, Claude Sonnet 4.6, Claude Opus 4.8, Claude Haiku 4.5
@@ -37,3 +37,11 @@ Description and reason for not choosing.
 - Related ADRs
 - External documentation
 - Discussion links
+
+---
+
+**Last Updated**: August 4, 2026
+**Claude Code Version**: 2.1.220
+**Sources**:
+- https://code.claude.com/docs/en/plugins
+**Compatible Models**: Claude Fable 5, Claude Opus 5, Claude Sonnet 5, Claude Sonnet 4.6, Claude Opus 4.8, Claude Haiku 4.5
@@ -99,3 +99,11 @@ data = response.json()
 ## Related Endpoints
 - [GET /api/v1/related](#)
 - [POST /api/v1/related](#)
+
+---
+
+**Last Updated**: August 4, 2026
+**Claude Code Version**: 2.1.220
+**Sources**:
+- https://code.claude.com/docs/en/plugins
+**Compatible Models**: Claude Fable 5, Claude Opus 5, Claude Sonnet 5, Claude Sonnet 4.6, Claude Opus 4.8, Claude Haiku 4.5
@@ -48,3 +48,11 @@ const result = functionName(
 ## See Also
 - [Related Function](#)
 - [API Documentation](#)
+
+---
+
+**Last Updated**: August 4, 2026
+**Claude Code Version**: 2.1.220
+**Sources**:
+- https://code.claude.com/docs/en/plugins
+**Compatible Models**: Claude Fable 5, Claude Opus 5, Claude Sonnet 5, Claude Sonnet 4.6, Claude Opus 4.8, Claude Haiku 4.5
@@ -58,7 +58,7 @@ Complete PR review workflow with security, testing, and documentation checks.

 ## Requirements

- Claude Code 1.0+
+- Claude Code 2.1+
 - GitHub access
 - Git repository

@@ -92,11 +92,11 @@ Result:

 ---

-**Last Updated**: July 29, 2026
+**Last Updated**: August 4, 2026
 **Claude Code Version**: 2.1.220
 **Sources**:
 - https://code.claude.com/docs/en/plugins
 - https://github.com/anthropics/claude-code/releases/tag/v2.1.131
 - https://github.com/anthropics/claude-code/releases/tag/v2.1.138
 - https://code.claude.com/docs/en/model-config
-**Compatible Models**: Claude Opus 5, Claude Sonnet 5, Claude Sonnet 4.6, Claude Opus 4.8, Claude Haiku 4.5
+**Compatible Models**: Claude Fable 5, Claude Opus 5, Claude Sonnet 5, Claude Sonnet 4.6, Claude Opus 4.8, Claude Haiku 4.5
@@ -1,7 +1,7 @@
 ---
 name: performance-analyzer
 description: Performance impact analysis
-tools: read, grep, bash
+tools: Read, Grep, Bash
 ---

 # Performance Analyzer
@@ -11,3 +11,11 @@ Evaluates performance impact of changes:
 - Database query efficiency
 - Memory usage
 - Caching opportunities
+
+---
+
+**Last Updated**: August 4, 2026
+**Claude Code Version**: 2.1.220
+**Sources**:
+- https://code.claude.com/docs/en/plugins
+**Compatible Models**: Claude Fable 5, Claude Opus 5, Claude Sonnet 5, Claude Sonnet 4.6, Claude Opus 4.8, Claude Haiku 4.5
@@ -1,7 +1,7 @@
 ---
 name: security-reviewer
 description: Security-focused code review
-tools: read, grep, bash
+tools: Read, Grep, Bash
 ---

 # Security Reviewer
@@ -11,3 +11,11 @@ Specializes in finding security vulnerabilities:
 - Data exposure
 - Injection attacks
 - Secure configuration
+
+---
+
+**Last Updated**: August 4, 2026
+**Claude Code Version**: 2.1.220
+**Sources**:
+- https://code.claude.com/docs/en/plugins
+**Compatible Models**: Claude Fable 5, Claude Opus 5, Claude Sonnet 5, Claude Sonnet 4.6, Claude Opus 4.8, Claude Haiku 4.5
@@ -1,7 +1,7 @@
 ---
 name: test-checker
 description: Test coverage and quality analysis
-tools: read, bash, grep
+tools: Read, Bash, Grep
 ---

 # Test Checker
@@ -11,3 +11,11 @@ Analyzes test coverage and quality:
 - Missing test cases
 - Test quality assessment
 - Edge case identification
+
+---
+
+**Last Updated**: August 4, 2026
+**Claude Code Version**: 2.1.220
+**Sources**:
+- https://code.claude.com/docs/en/plugins
+**Compatible Models**: Claude Fable 5, Claude Opus 5, Claude Sonnet 5, Claude Sonnet 4.6, Claude Opus 4.8, Claude Haiku 4.5
@@ -12,3 +12,11 @@ Perform focused security analysis on code changes:
 3. Injection vulnerabilities
 4. Cryptographic weaknesses
 5. Sensitive data in logs
+
+---
+
+**Last Updated**: August 4, 2026
+**Claude Code Version**: 2.1.220
+**Sources**:
+- https://code.claude.com/docs/en/plugins
+**Compatible Models**: Claude Fable 5, Claude Opus 5, Claude Sonnet 5, Claude Sonnet 4.6, Claude Opus 4.8, Claude Haiku 4.5
@@ -12,3 +12,11 @@ Analyze test coverage and quality:
 3. Review test quality
 4. Suggest missing test cases
 5. Verify edge cases are covered
+
+---
+
+**Last Updated**: August 4, 2026
+**Claude Code Version**: 2.1.220
+**Sources**:
+- https://code.claude.com/docs/en/plugins
+**Compatible Models**: Claude Fable 5, Claude Opus 5, Claude Sonnet 5, Claude Sonnet 4.6, Claude Opus 4.8, Claude Haiku 4.5
@@ -12,3 +12,11 @@ This command initiates a complete pull request review including:
 3. Documentation updates
 4. Code quality checks
 5. Performance impact assessment
+
+---
+
+**Last Updated**: August 4, 2026
+**Claude Code Version**: 2.1.220
+**Sources**:
+- https://code.claude.com/docs/en/plugins
+**Compatible Models**: Claude Fable 5, Claude Opus 5, Claude Sonnet 5, Claude Sonnet 4.6, Claude Opus 4.8, Claude Haiku 4.5
@@ -214,15 +214,21 @@ Since checkpoints are created automatically, you can focus on your work without

 Checkpoints are a built-in default behavior in Claude Code and do not require any configuration to enable. Every user prompt automatically creates a checkpoint.

-The only checkpoint-related setting is `cleanupPeriodDays`, which controls how long sessions and checkpoints are retained:
+Two settings govern checkpoint behavior — whether snapshots are taken at all, and how long they are kept:

 ```json
 {
+  "fileCheckpointingEnabled": true,
  "cleanupPeriodDays": 30
 }
 ```

- `cleanupPeriodDays`: Number of days to retain session history and checkpoints (default: `30`)
+| Setting | Default | Effect |
+|---------|---------|--------|
+| `fileCheckpointingEnabled` | `true` | Snapshot files before each edit so `/rewind` can restore them. Requires v2.1.119+. Surfaces in `/config` as **Rewind code (checkpoints)**. Env equivalent: `CLAUDE_CODE_DISABLE_FILE_CHECKPOINTING` |
+| `cleanupPeriodDays` | `30` | Number of days to retain session history and checkpoints |
+
+Claude Code keeps snapshots for the **100 most recent checkpoints**; older ones are dropped even inside the retention window.

 > **v2.1.117 update**: `cleanupPeriodDays` now governs retention for four on-disk caches, not just checkpoints:
 >
@@ -330,11 +336,11 @@ Remember: checkpoints are not a replacement for git. Use checkpoints for rapid e

 ---

-**Last Updated**: July 29, 2026
+**Last Updated**: August 4, 2026
 **Claude Code Version**: 2.1.220
 **Sources**:
 - https://code.claude.com/docs/en/checkpointing
 - https://code.claude.com/docs/en/settings
 - https://github.com/anthropics/claude-code/releases/tag/v2.1.117
 - https://code.claude.com/docs/en/model-config
-**Compatible Models**: Claude Opus 5, Claude Sonnet 5, Claude Sonnet 4.6, Claude Opus 4.8, Claude Haiku 4.5
+**Compatible Models**: Claude Fable 5, Claude Opus 5, Claude Sonnet 5, Claude Sonnet 4.6, Claude Opus 4.8, Claude Haiku 4.5
@@ -345,4 +345,4 @@ User: Now let's continue with the approach that worked.
 - https://code.claude.com/docs/en/checkpointing
 - https://code.claude.com/docs/en/changelog
 - https://code.claude.com/docs/en/model-config
-**Compatible Models**: Claude Opus 5, Claude Sonnet 5, Claude Sonnet 4.6, Claude Opus 4.8, Claude Haiku 4.5
+**Compatible Models**: Claude Fable 5, Claude Opus 5, Claude Sonnet 5, Claude Sonnet 4.6, Claude Opus 4.8, Claude Haiku 4.5
@@ -22,22 +22,24 @@ Comprehensive guide to Claude Code's advanced capabilities including planning mo
 11. [Headless Mode](#headless-mode)
 12. [Session Management](#session-management)
 13. [Interactive Features](#interactive-features)
-14. [TUI Mode (Fullscreen)](#tui-mode-fullscreen)
-15. [Voice Dictation](#voice-dictation)
-16. [Channels](#channels)
-17. [Chrome Integration](#chrome-integration)
-18. [Remote Control](#remote-control)
-19. [Web Sessions](#web-sessions)
-20. [Desktop App](#desktop-app)
-21. [Task List](#task-list)
-22. [Prompt Suggestions](#prompt-suggestions)
-23. [Git Worktrees](#git-worktrees)
-24. [Sandboxing](#sandboxing)
-25. [Managed Settings (Enterprise)](#managed-settings-enterprise)
-26. [Configuration and Settings](#configuration-and-settings)
-27. [Agent Teams](#agent-teams)
-28. [Best Practices](#best-practices)
-29. [Additional Resources](#additional-resources)
+14. [Output Styles](#output-styles)
+15. [Status Line](#status-line)
+16. [TUI Mode (Fullscreen)](#tui-mode-fullscreen)
+17. [Voice Dictation](#voice-dictation)
+18. [Channels](#channels)
+19. [Chrome Integration](#chrome-integration)
+20. [Remote Control](#remote-control)
+21. [Web Sessions](#web-sessions)
+22. [Desktop App](#desktop-app)
+23. [Task List](#task-list)
+24. [Prompt Suggestions](#prompt-suggestions)
+25. [Git Worktrees](#git-worktrees)
+26. [Sandboxing](#sandboxing)
+27. [Managed Settings (Enterprise)](#managed-settings-enterprise)
+28. [Configuration and Settings](#configuration-and-settings)
+29. [Agent Teams](#agent-teams)
+30. [Best Practices](#best-practices)
+31. [Additional Resources](#additional-resources)

 ---

@@ -320,6 +322,14 @@ Separate from the [`fallbackModel` setting](#fallback-models-fallbackmodel) (whi

 Why this matters here: if you run [security-review subagents](../04-subagents/README.md) or CTF/pentest work on Opus 5, expect silent re-runs on Opus 4.8 (different effort ceiling and context window) for cybersecurity prompts, and outright refusals for biology-adjacent ones. Pin a different model explicitly if that behavior gets in the way.

+**Controlling the switch** — the `switchModelsOnFlag` setting (v2.1.170+, default `true`) decides whether the fallback happens silently. Set it to `false` and Claude Code pauses instead, letting you choose between switching models and editing the prompt. It appears in `/config` as **Switch models when a message is flagged**.
+
+```json
+{
+  "switchModelsOnFlag": false
+}
+```
+
 ### Benefits of Extended Thinking

 - **Deep reasoning**: Spend more time thinking about complex problems
@@ -900,7 +910,7 @@ Permission modes control what actions Claude can take without explicit approval.
 | `bypassPermissions` | All actions, no permission checks (dangerous) |
 | `dontAsk` | Only pre-approved tools execute; all others denied |

-> **Note**: The interactive default mode was renamed from `default` to **Manual** in v2.1.200 (across the CLI, `--help`, VS Code, and JetBrains), and a grey ⏸ badge appears in the footer while it is active (v2.1.203). Both `--permission-mode manual` and `--permission-mode default` work, as do `"defaultMode": "manual"` and `"defaultMode": "default"` in settings — so the `"mode": "default"` values in the config examples below remain valid.
+> **Note**: The interactive default mode was renamed from `default` to **Manual** in v2.1.200 (across the CLI, `--help`, VS Code, and JetBrains), and a grey ⏸ badge appears in the footer while it is active (v2.1.203). Both `--permission-mode manual` and `--permission-mode default` work, as do `"defaultMode": "manual"` and `"defaultMode": "default"` in settings. Note that the settings key is `permissions.defaultMode` — there is no `permissions.mode` key, so the examples below use the canonical spelling.

 Cycle through modes with `Shift+Tab` in the CLI. Set a default with the `--permission-mode` flag or the `permissions.defaultMode` setting.

@@ -1136,7 +1146,8 @@ Manage multiple Claude Code sessions effectively.
 |---------|-------------|
 | `/resume` | Resume a conversation by ID or name |
 | `/rename` | Name the current session |
-| `/fork <directive>` | Spawn a background subagent that inherits the full conversation and works on the directive while you keep going |
+| `/fork [prompt]` | Copy the conversation into a new independent background session and keep working here (v2.1.212+) |
+| `/subtask <task>` | Spawn a forked subagent that inherits the full conversation and reports its result back here (v2.1.212+) |
 | `/branch [name]` | Switch into a copy of the conversation at this point, preserving the original |
 | `claude -c` | Continue most recent conversation |
 | `claude -r "session"` | Resume session by name or ID |
@@ -1162,19 +1173,27 @@ claude -r "auth-refactor" "finish this PR"

 ### Forking and Branching Sessions

-`/fork <directive>` spawns a background subagent that inherits the full conversation and works on the directive while you keep working in the current session — its own row in `claude agents`, with the result returned to your conversation when it finishes:
+Three commands make copies of a conversation, and they differ in *where the copy runs*:
+
+`/subtask <task>` spawns a forked subagent that inherits the full conversation and works on the task while you keep working — its own row in `claude agents`, with the result returned to your conversation when it finishes:

 ```
-/fork Investigate why the auth tests are flaky
+/subtask Investigate why the auth tests are flaky
 ```

-To switch into a copy of the conversation yourself instead of delegating to a background subagent, use `/branch [name]`, which preserves the original and lets you return to it with `/resume`:
+`/fork [prompt]` copies the conversation into a new **background session** instead. The copy starts with everything up to now and runs independently — nothing comes back to this conversation:
+
+```
+/fork Try the OAuth approach end to end
+```
+
+To switch into a copy yourself rather than delegating at all, use `/branch [name]`, which preserves the original and lets you return to it with `/resume`:

 ```
 /branch try-oauth-instead
 ```

-> **Note**: Before v2.1.161, `/fork` was simply an alias for `/branch`. Since v2.1.161 they are distinct: `/fork` delegates to a background subagent, `/branch` switches you into a copy in place.
+> **Note**: `/fork` and `/subtask` swapped roles in **v2.1.212**. Before v2.1.161 `/fork` was an alias for `/branch`; from v2.1.161 to v2.1.211 it started a forked subagent — the behavior now carried by `/subtask`. When agent view is turned off, `/subtask` is unavailable and `/fork` retains the forked-subagent behavior.

 Or fork from the CLI:
 ```bash
@@ -1460,6 +1479,128 @@ Use this for quick command execution without switching contexts.

 ---

+## Output Styles
+
+Output styles change **how** Claude responds, not what it knows. They modify the system prompt to set role, tone, and default response format. Reach for one when you keep re-prompting for the same voice every turn, or when you want Claude acting as something other than a software engineer.
+
+For instructions about your project or codebase, use [CLAUDE.md](../02-memory/) instead — that is a different mechanism with different tradeoffs.
+
+### Built-in styles
+
+| Style | Behavior |
+|-------|----------|
+| **Default** | The standard system prompt, tuned for completing software engineering tasks efficiently |
+| **Proactive** | Claude executes immediately and makes reasonable assumptions instead of pausing for routine decisions. Stronger autonomous-execution guidance than auto mode, but it does **not** change your permission mode — you still see permission prompts |
+| **Explanatory** | Adds educational "Insights" between steps, explaining implementation choices and codebase patterns |
+| **Learning** | Collaborative learn-by-doing. Claude shares insights *and* leaves `TODO(human)` markers for you to implement small, strategic pieces yourself |
+
+### Selecting a style
+
+Run `/config` and choose **Output style**. The selection is saved to `.claude/settings.local.json`. To set it without the menu, edit the setting directly:
+
+```json
+{
+  "outputStyle": "Explanatory"
+}
+```
+
+> **Note**: The standalone `/output-style` command was deprecated in v2.1.73 and **removed in v2.1.91**. Use `/config` or the `outputStyle` setting.
+
+Output style is part of the system prompt, which Claude Code reads once at session start — changes take effect after `/clear` or in a new session.
+
+### Custom output styles
+
+A custom style is a Markdown file with frontmatter, saved at one of three levels:
+
+- User: `~/.claude/output-styles/`
+- Project: `.claude/output-styles/`
+- Managed policy: `.claude/output-styles/` inside the managed settings directory
+
+Project styles load from every `.claude/output-styles/` between the working directory and the repo root. As of v2.1.178, when nested directories define the same style name, the one closest to the working directory wins.
+
+```markdown
+---
+name: Diagrams first
+description: Lead every explanation with a diagram
+keep-coding-instructions: true
+---
+
+When explaining code, architecture, or data flow, start with a Mermaid diagram
+showing the structure, then explain in prose.
+```
+
+| Frontmatter | Purpose | Default |
+|-------------|---------|---------|
+| `name` | Style name, if not the file name | Inherits from file name |
+| `description` | Shown in the `/config` picker | None |
+| `keep-coding-instructions` | Keep Claude Code's built-in software engineering instructions | `false` |
+| `force-for-plugin` | Plugin styles only: apply automatically whenever the plugin is enabled, overriding the user's `outputStyle` | `false` |
+
+**Set `keep-coding-instructions: true`** when you are changing how Claude communicates but still want it coding the same way. Leave it out when Claude is not doing software engineering at all — a writing assistant or data analyst.
+
+### Scope and cost
+
+Output styles apply to the **main conversation only**. A subagent runs its own system prompt, so styles do not change how subagents respond; a fork is the exception, since it inherits the parent's full system prompt.
+
+Adding instructions increases input tokens, though prompt caching absorbs most of that after the first request. Explanatory and Learning produce longer responses by design, which increases output tokens.
+
+### How it compares
+
+| Feature | How it works | Use it when |
+|---------|--------------|-------------|
+| Output styles | Modifies the system prompt | You want a different role, tone, or format every turn |
+| [CLAUDE.md](../02-memory/) | Adds a user message after the system prompt | Claude should always know your project conventions |
+| `--append-system-prompt` | Appends to the system prompt without removing anything | A one-off addition for a single invocation |
+| [Subagents](../04-subagents/) | Runs with its own system prompt, model, and tools | You want a separately scoped helper |
+| [Skills](../03-skills/) | Loads task-specific instructions when invoked | You have a reusable workflow |
+
+---
+
+## Status Line
+
+The status line is a custom command whose output renders at the bottom of the session. Configure it with `/statusline`, or set it directly:
+
+```json
+{
+  "statusLine": {
+    "type": "command",
+    "command": "~/.claude/statusline.sh",
+    "padding": 0
+  }
+}
+```
+
+`padding` defaults to `0`. Claude Code pipes a JSON object to the command on stdin, so the script decides what to display.
+
+### Available input fields
+
+| Group | Fields |
+|-------|--------|
+| Session | `session_id`, `session_name`, `prompt_id`, `transcript_path`, `cwd`, `version` |
+| Model | `model.id`, `output_style.name`, `effort.level`, `fast_mode`, `thinking.enabled` |
+| Agent | `agent.name`, `vim.mode` |
+| Cost | `cost.total_cost_usd`, `cost.total_duration_ms`, `cost.total_api_duration_ms`, `cost.total_lines_added` |
+| Context | `context_window.context_window_size`, `.current_usage`, `.remaining_percentage`, `.total_input_tokens`, `.used_percentage` |
+| Limits | `rate_limits.five_hour.used_percentage`, `.resets_at` |
+| Repo | `pr.number`, `pr.review_state`, `workspace.project_dir`, `workspace.added_dirs`, `workspace.git_worktree`, `workspace.repo.host` |
+| Worktree | `worktree.name`, `.branch`, `.path`, `.original_branch`, `.original_cwd` |
+
+### Example
+
+```bash
+#!/bin/bash
+# ~/.claude/statusline.sh — model, context usage, and cost
+input=$(cat)
+model=$(echo "$input" | jq -r '.model.id')
+used=$(echo "$input" | jq -r '.context_window.used_percentage')
+cost=$(echo "$input" | jq -r '.cost.total_cost_usd')
+printf '%s | ctx %.0f%% | $%.2f' "$model" "$used" "$cost"
+```
+
+> **Note**: `statusLine` requires workspace trust. Status-line scripts also receive `COLUMNS` and `LINES` in their environment (v2.1.153+) so they can size output to the terminal.
+
+---
+
 ## TUI Mode (Fullscreen)

 > **New in v2.1.110**
@@ -2129,7 +2270,7 @@ Since v2.1.83, administrators can deploy multiple managed settings files into a
 ```json
 {
  "permissions": {
-    "mode": "default"
+    "defaultMode": "manual"
  },
  "hooks": {
    "PreToolUse:Edit": "eslint --fix ${file_path}",
@@ -2152,7 +2293,7 @@ Since v2.1.83, administrators can deploy multiple managed settings files into a
 ```json
 {
  "permissions": {
-    "mode": "default",
+    "defaultMode": "manual",
    "allowedTools": ["Bash(git log:*)", "Read"],
    "disallowedTools": ["Bash(rm -rf:*)"]
  },
@@ -2315,7 +2456,7 @@ Create `.claude/config.json` in your project:
    "PreToolUse": [{ "matcher": "Bash", "hooks": ["npm test && npm run lint"] }]
  },
  "permissions": {
-    "mode": "default"
+    "defaultMode": "manual"
  },
  "mcp": {
    "servers": {
@@ -2447,7 +2588,7 @@ For more information about Claude Code and related features:

 ---

-**Last Updated**: July 29, 2026
+**Last Updated**: August 4, 2026
 **Claude Code Version**: 2.1.220
 **Sources**:
 - https://code.claude.com/docs/en/settings
@@ -2455,3 +2596,4 @@ For more information about Claude Code and related features:
 - https://github.com/anthropics/claude-code/blob/main/CHANGELOG.md
 - https://code.claude.com/docs/en/model-config
 - https://code.claude.com/docs/en/permission-modes
+**Compatible Models**: Claude Fable 5, Claude Opus 5, Claude Sonnet 5, Claude Sonnet 4.6, Claude Opus 4.8, Claude Haiku 4.5
@@ -44,7 +44,7 @@
      "config": {
        "model": "claude-sonnet-5",
        "permissions": {
-          "defaultMode": "default"
+          "defaultMode": "manual"
        },
        "env": {
          "CLAUDE_CODE_EFFORT_LEVEL": "high"
@@ -57,9 +57,9 @@
      "name": "Production Deployment",
      "description": "Configuration for production operations with safety checks",
      "config": {
-        "model": "claude-opus-4-8",
+        "model": "claude-opus-5",
        "permissions": {
-          "defaultMode": "default",
+          "defaultMode": "manual",
          "deny": ["Bash(git push --force*)", "Bash(rm -rf*)"]
        },
        "hooks": {
@@ -95,7 +95,7 @@
      "name": "Security Audit",
      "description": "Configuration for security-focused code analysis",
      "config": {
-        "model": "claude-opus-4-8",
+        "model": "claude-opus-5",
        "permissions": {
          "defaultMode": "plan"
        },
@@ -133,7 +133,7 @@
      "config": {
        "model": "claude-sonnet-5",
        "permissions": {
-          "defaultMode": "default"
+          "defaultMode": "manual"
        },
        "env": {
          "CLAUDE_CODE_EFFORT_LEVEL": "high"
@@ -145,9 +145,9 @@
      "name": "Large Refactoring",
      "description": "Configuration for major refactoring work: backup before edits, run related tests after",
      "config": {
-        "model": "claude-opus-4-8",
+        "model": "claude-opus-5",
        "permissions": {
-          "defaultMode": "default",
+          "defaultMode": "manual",
          "allow": ["Bash(npm test -- --findRelatedTests *)"]
        },
        "fileCheckpointingEnabled": true,
@@ -539,4 +539,4 @@ Proceed with this plan? (yes/no/modify)
 - https://code.claude.com/docs/en/changelog
 - https://code.claude.com/docs/en/best-practices
 - https://code.claude.com/docs/en/model-config
-**Compatible Models**: Claude Opus 5, Claude Sonnet 5, Claude Sonnet 4.6, Claude Opus 4.8, Claude Haiku 4.5
+**Compatible Models**: Claude Fable 5, Claude Opus 5, Claude Sonnet 5, Claude Sonnet 4.6, Claude Opus 4.8, Claude Haiku 4.5
@@ -1020,4 +1020,4 @@ claude -p --output-format json "query"
 - https://code.claude.com/docs/en/overview
 - https://code.claude.com/docs/en/sub-agents
 - https://code.claude.com/docs/en/headless
-**Compatible Models**: Claude Opus 5, Claude Sonnet 5, Claude Sonnet 4.6, Claude Opus 4.8, Claude Haiku 4.5
+**Compatible Models**: Claude Fable 5, Claude Opus 5, Claude Sonnet 5, Claude Sonnet 4.6, Claude Opus 4.8, Claude Haiku 4.5
@@ -16,13 +16,13 @@
 | Feature | Built-in | Examples | Total | Reference |
 |---------|----------|----------|-------|-----------|
 | **Slash Commands** | 60+ | 8 | 68+ | [01-slash-commands/](01-slash-commands/) |
-| **Subagents** | 6 | 11 | 17 | [04-subagents/](04-subagents/) |
+| **Subagents** | 6 | 9 | 15 | [04-subagents/](04-subagents/) |
 | **Skills** | 10 bundled | 6 | 16 | [03-skills/](03-skills/) |
 | **Plugins** | - | 3 | 3 | [07-plugins/](07-plugins/) |
-| **MCP Servers** | 1 | 8 | 9 | [05-mcp/](05-mcp/) |
-| **Hooks** | 29 events | 8 | 8 | [06-hooks/](06-hooks/) |
-| **Memory** | 7 types | 3 | 3 | [02-memory/](02-memory/) |
-| **Total** | **104** | **47** | **126** | |
+| **MCP Servers** | 1 | 4 | 5 | [05-mcp/](05-mcp/) |
+| **Hooks** | 31 events | 11 | 42 | [06-hooks/](06-hooks/) |
+| **Memory** | 7 types | 3 | 10 | [02-memory/](02-memory/) |
+| **Total** | **115** | **44** | **159** | |

 ---

@@ -84,7 +84,8 @@ Commands are user-invoked shortcuts that execute specific actions.
 | `/theme` | Change color theme; v2.1.118 added custom named themes via `~/.claude/themes/<name>.json` (plugins can ship a `themes/` dir) | Customize appearance |
 | `/usage` | Canonical command for usage/cost/stats — merged `/cost` and `/stats` into a single tabbed view (v2.1.118); as of v2.1.149 the cost view breaks spending down by category (skills, subagents, plugins, per-MCP-server). In the **VSCode extension** (v2.1.174), the `/usage` (Account & usage) dialog adds an attribution breakdown — cache misses, long-context cost, subagents, and per-skill / per-agent / per-plugin / per-MCP usage over 24h and 7d windows | Monitor quota and costs |
 | `/focus` | Toggle focus view (distraction-free output display) | Reduce visual noise during long tasks |
-| `/fork` | Fork current conversation | Explore alternatives |
+| `/fork` | Copy the conversation into a new independent background session (v2.1.212+) | Explore alternatives in parallel |
+| `/subtask` | Spawn a forked subagent that inherits the conversation and reports back (v2.1.212+) | Delegate a side task without losing your place |
 | `/stats` | Shortcut alias that opens the stats tab of `/usage` (v2.1.118+) | Review session metrics |
 | `/statusline` | Configure status line | Customize status display |
 | `/stickers` | View session stickers | Fun rewards |
@@ -95,7 +96,7 @@ Commands are user-invoked shortcuts that execute specific actions.
 | `/team-onboarding` | Generate a teammate ramp-up guide from this project's Claude Code usage | Onboarding new teammates (v2.1.101) |
 | `/ultraplan` | Hand a planning task to a Claude Code web session in plan mode | Heavy planning offload (Research Preview, v2.1.91+) |
 | `/ultrareview` | Run a cloud multi-agent code review over your current changes | Deep pre-merge review across multiple agents (v2.1.112) |
-| `/less-permission-prompts` | Scan transcripts and propose a prioritized allowlist for common read-only tools | Reduce repeat permission prompts in a project (v2.1.112) |
+| `/fewer-permission-prompts` | Scan transcripts and propose a prioritized allowlist for common read-only tools | Reduce repeat permission prompts in a project (v2.1.112) |

 ### Custom Commands (Examples)

@@ -461,6 +462,9 @@ cp 02-memory/personal-CLAUDE.md ~/.claude/CLAUDE.md
 | **/tui** | Toggle fullscreen TUI (text user interface) mode for flicker-free rendering (v2.1.110) | Use `/tui` in fullscreen terminals or tmux |
 | **/undo** | Alias for `/rewind` — reverts to the previous checkpoint (v2.1.108) | Use `/undo` interchangeably with `/rewind` |
 | **Monitor Tool** | Watch a background command's stdout stream and react to events instead of polling (v2.1.98+) | Use the Monitor tool via [Advanced Features](09-advanced-features/) |
+| **Output Styles** | Change Claude's role, tone, and default response format via the system prompt. Built-ins: Default, Proactive, Explanatory, Learning | `/config` → Output style, or set `outputStyle`. The `/output-style` command was removed in v2.1.91. See [Advanced Features](09-advanced-features/#output-styles) |
+| **Status Line** | Render a custom status line from a command that receives session, model, cost, and context JSON on stdin | `/statusline` or the `statusLine` setting. See [Advanced Features](09-advanced-features/#status-line) |
+| **Community Marketplace** | Third-party plugins that passed Anthropic's automated validation, each pinned to a commit SHA | `/plugin marketplace add anthropics/claude-plugins-community`, then `/plugin install <name>@claude-community` |
 | **/team-onboarding** | Auto-generate a teammate ramp-up guide from the project's Claude Code setup (v2.1.101) | Run `/team-onboarding` in your project |
 | **Ultraplan auto-create** | Cloud environment created automatically on first `/ultraplan` invocation — no manual setup required (v2.1.101) | Use `/ultraplan <prompt>` |
 | **Remote Control** | Control Claude Code sessions remotely via API | Use the remote control API to send prompts and receive responses programmatically |
@@ -545,7 +549,7 @@ chmod +x ~/.claude/hooks/*.sh

 ---

-**Last Updated**: July 29, 2026
+**Last Updated**: August 4, 2026
 **Claude Code Version**: 2.1.220
 **Sources**:
 - https://code.claude.com/docs/en/sub-agents
@@ -562,4 +566,4 @@ chmod +x ~/.claude/hooks/*.sh
 - https://code.claude.com/docs/en/cli-reference
 - https://code.claude.com/docs/en/model-config
 - https://code.claude.com/docs/en/skills
-**Compatible Models**: Claude Opus 5, Claude Sonnet 5, Claude Sonnet 4.6, Claude Opus 4.8, Claude Haiku 4.5
+**Compatible Models**: Claude Fable 5, Claude Opus 5, Claude Sonnet 5, Claude Sonnet 4.6, Claude Opus 4.8, Claude Haiku 4.5
@@ -1,5 +1,109 @@
 # Changelog

+## [v2.1.220-r2] — 2026-08-04
+
+### Accuracy pass against Claude Code v2.1.220 (no upstream version change)
+
+v2.1.220 (2026-07-25) is still the current Claude Code release, so this entry
+records **internal corrections**, not a version sync. An audit against the
+official docs found no missing upstream features — every v2.1.218–v2.1.220
+capability was already documented. What it did find was broken example code,
+counts and names that disagreed between files, and metadata drift.
+
+### Fixed
+
+- **`06-hooks/pre-commit.sh` never actually blocked a commit** — the script
+  printed "Commit blocked." and then `exit 1` at four places. Per this repo's own
+  exit-code table (`06-hooks/README.md`), exit 1 is a *non-blocking* error, so the
+  commit proceeded anyway; only exit 2 blocks. All four now `exit 2` and write the
+  reason to stderr, which is where Claude Code reads the block reason from.
+- **`06-hooks/dependency-check.sh` never ran** — it read its target from `$1`, but
+  hooks receive JSON on stdin, so the path was always empty and the script exited
+  immediately. Now parses `file_path` from stdin, matching `format-code.sh`.
+- **Nested-subagent depth said 5 in `claude_concepts_guide.md`** — stated "up to 5
+  levels deep as of v2.1.172", contradicting the depth-3 default (v2.1.219) already
+  documented in four other files. Rewritten to lead with current behavior plus the
+  same three-era history note used in `04-subagents/README.md`.
+- **Hook event count was 29 in five files** — `README.md`, `CATALOG.md`,
+  `QUICK_REFERENCE.md` (×4), `INDEX.md` and `resources.md` all said 29; the correct
+  figure is **31**, confirmed name-by-name against the official hook list. The
+  previous sync fixed two files and missed the rest. `README.md`'s event list also
+  enumerated only 25 names and `INDEX.md`'s only 29 — both now list all 31.
+- **`/less-permission-prompts` is not a real command** — the built-in is
+  `/fewer-permission-prompts`. `CATALOG.md` had used *both* names in one file.
+- **`/fork` and `/subtask` were documented with swapped meanings** — they exchanged
+  roles in v2.1.212. `/fork` now copies the conversation into a new independent
+  background session; the forked-subagent behavior moved to `/subtask`, which was
+  absent from the repo entirely. Corrected and added in four files.
+- **`08-checkpoints/README.md` claimed `cleanupPeriodDays` was the only checkpoint
+  setting** — `fileCheckpointingEnabled` (default `true`) also exists, along with
+  `CLAUDE_CODE_DISABLE_FILE_CHECKPOINTING` and a 100-checkpoint retention cap. The
+  repo's own `config-examples.json` already used the key it denied existed.
+- **`03-skills/refactor/SKILL.md` declared `name: code-refactor`** while living in
+  `refactor/` — the same defect fixed for `doc-generator` last sync. Renamed in the
+  English copy and mirrored to `ja/`, `zh/`, `uk/`, `vi/`.
+- **`03-skills/README.md` stated skill precedence two contradictory ways** —
+  "enterprise > personal > project" in one place, "project wins by default" in
+  another. Now consistently **enterprise > project > personal**.
+- **`claude-md` skill described AGENTS.md incorrectly** — called it an
+  agent-definition format. It is a cross-tool project-context file, and Claude Code
+  **does not read it directly**; it must be imported via `@AGENTS.md` or symlinked.
+- **`02-memory/directory-api-CLAUDE.md` claimed it "overrides" root CLAUDE.md** —
+  memory files are concatenated, never overridden.
+- **`INDEX.md` described `auto` and `dontAsk` backwards** — `dontAsk` was written up
+  as permissive ("accept all except risky") when it is the most restrictive mode:
+  it auto-denies anything not pre-approved. Corrected to the official definitions.
+- **`permissions.mode` is not a settings key** — four config samples in
+  `09-advanced-features/README.md` and `claude_concepts_guide.md` used it (with the
+  superseded value `default`). All now use `permissions.defaultMode: "manual"`.
+- **`09-advanced-features/config-examples.json` had no Opus 5** — still used
+  `claude-opus-4-8` for its three "most capable" profiles despite Opus 5 being the
+  default Opus since v2.1.219.
+- **`05-mcp/database-mcp.json` hardcoded a credential** —
+  `postgresql://user:pass@localhost/mydb`, contradicting the module's own "don't
+  hardcode credentials" rule. Now `${DATABASE_URL}`.
+- **`05-mcp/README.md` documented MCP scopes but never the `--scope` flag** —
+  readers had no way to actually select a scope. Added with examples.
+- **`/output-style` was listed as deprecated** — it was *removed* in v2.1.91.
+  Output styles remain available via `/config` or the `outputStyle` setting.
+- **Hook `permissionDecision` was missing `defer`** — the accepted values are
+  `allow`, `deny`, `ask`, `defer`, with precedence `deny` > `defer` > `ask` > `allow`.
+- **Context-tracker hooks assumed a 128k window** — no current Claude model has one.
+  Default raised to 1M, with Haiku 4.5's 200k noted.
+- **Local memory path was wrong in `claude_concepts_guide.md`** —
+  `.claude/local/CLAUDE.md` corrected to `./CLAUDE.local.md`.
+- **Broken fence in `03-skills/doc-generator/SKILL.md`** — the outer ```` ```markdown ````
+  block closed early and left a stray unclosed fence, so half the example rendered
+  as live markdown. Now uses a four-backtick outer fence. Neither validator caught
+  this, because `check_markdown_rendering.py` only scans README files.
+- **Three command templates had invalid skill names** — `Documentation Refactor`,
+  `Setup CI/CD Pipeline` and `Expand Unit Tests` are not valid `name:` values
+  (lowercase/hyphens only), so they would fail if copied into `.claude/skills/` as
+  the README instructs. Also removed a non-standard `tags:` field.
+- **Nine plugin agents used lowercase tool names** (`read, grep, bash`) while the
+  `04-subagents/` templates used canonical `Read, Grep, Bash`. Unified.
+- **"Claude Code 1.0+" requirement in five files** — raised to 2.1+.
+- **Miscounted inventories** — `CATALOG.md`'s summary table did not add up *and*
+  three of its Examples counts were wrong (Subagents 11→9, MCP 8→4, Hooks 8→11);
+  `INDEX.md` understated Plugins (27→39), Skills (21→23), Hooks (9→12), Subagents
+  (9→10) and Advanced (3→4), omitted three hook scripts and
+  `setup-auto-mode-permissions.py`, and mislabeled three hook events. All recounted
+  from the file tree.
+- **`CONTRIBUTING.md` said "all four checks"** — there are five.
+- **Two subagent templates were undocumented** — `clean-code-reviewer.md` and
+  `performance-optimizer.md` existed on disk but appeared in neither the example
+  list nor the file tree of `04-subagents/README.md`.
+- **`resources.md` Mermaid diagrams used an off-guide palette** — remapped to the
+  five `STYLE_GUIDE.md` colors with the required `stroke`/`color`.
+- **Metadata footers** — 61 files had a legacy `Last Updated`-only footer or none at
+  all; all now carry the full block. Four module READMEs were missing the
+  `Compatible Models` line, and `02-memory/README.md` was stranded at v2.1.217 with
+  an ISO-formatted date. All 87 in-scope markdown files now report **2.1.220**.
+- **Smaller fixes** — explicit `exit 0` in `session-end.sh`; `# Hook: Event:Matcher`
+  shorthand (not real syntax) reworded in four scripts; `"type": "stdio"` added to
+  the four MCP example configs; a worked example that reported 42 PRs in one place
+  and 47 in another.
+
 ## [v2.1.220] — 2026-07-29

 ### Synced to Claude Code v2.1.220
@@ -217,4 +217,8 @@ If you have questions about this Code of Conduct, please reach out to the projec
 **Thank you for helping us create a welcoming, inclusive, and respectful community!** 🌟

 ---
-**Last Updated**: April 9, 2026
+**Last Updated**: August 4, 2026
+**Claude Code Version**: 2.1.220
+**Sources**:
+- https://code.claude.com/docs/en/overview
+**Compatible Models**: Claude Fable 5, Claude Opus 5, Claude Sonnet 5, Claude Sonnet 4.6, Claude Opus 4.8, Claude Haiku 4.5
@@ -68,7 +68,7 @@ git checkout -b docs/improvement-area

 ### 3. Set Up Your Environment

-Pre-commit hooks run the same checks as CI locally before every commit. All four checks must pass before a PR will be accepted.
+Pre-commit hooks run the same checks as CI locally before every commit. All five checks must pass before a PR will be accepted.

 **Required dependencies:**

@@ -378,4 +378,8 @@ By contributing to this project, you agree that your contributions will be licen
 Thank you for contributing! 🙏

 ---
-**Last Updated**: April 9, 2026
+**Last Updated**: August 4, 2026
+**Claude Code Version**: 2.1.220
+**Sources**:
+- https://code.claude.com/docs/en/overview
+**Compatible Models**: Claude Fable 5, Claude Opus 5, Claude Sonnet 5, Claude Sonnet 4.6, Claude Opus 4.8, Claude Haiku 4.5
@@ -60,7 +60,7 @@ Persistent context and project standards.

 ---

-## 03. Skills (21 files)
+## 03. Skills (23 files)

 Auto-invoked capabilities with scripts and templates.

@@ -158,20 +158,21 @@ blog-draft/

 ---

-## 04. Subagents (9 files)
+## 04. Subagents (10 files)

 Specialized AI assistants with custom capabilities.

 | File | Description | Tools | Use Case |
 |------|-------------|-------|----------|
-| `code-reviewer.md` | Code quality analysis | read, grep, diff, lint_runner | Comprehensive reviews |
-| `test-engineer.md` | Test coverage analysis | read, write, bash, grep | Test automation |
-| `documentation-writer.md` | Documentation creation | read, write, grep | Doc generation |
-| `secure-reviewer.md` | Security review (read-only) | read, grep | Security audits |
-| `implementation-agent.md` | Full implementation | read, write, bash, grep, edit, glob | Feature development |
-| `debugger.md` | Debugging specialist | read, bash, grep | Bug investigation |
-| `data-scientist.md` | Data analysis specialist | read, write, bash | Data workflows |
-| `clean-code-reviewer.md` | Clean code standards | read, grep | Code quality |
+| `code-reviewer.md` | Code quality analysis | Read, Grep, Glob, Bash | Comprehensive reviews |
+| `test-engineer.md` | Test coverage analysis | Read, Write, Bash, Grep | Test automation |
+| `documentation-writer.md` | Documentation creation | Read, Write, Grep | Doc generation |
+| `secure-reviewer.md` | Security review (read-only) | Read, Grep | Security audits |
+| `implementation-agent.md` | Full implementation | Read, Write, Edit, Bash, Grep, Glob | Feature development |
+| `debugger.md` | Debugging specialist | Read, Edit, Bash, Grep, Glob | Bug investigation |
+| `data-scientist.md` | Data analysis specialist | Bash, Read, Write | Data workflows |
+| `clean-code-reviewer.md` | Clean code standards | Read, Grep, Glob, Bash | Code quality |
+| `performance-optimizer.md` | Performance bottleneck analysis | Read, Edit, Bash, Grep, Glob | Optimization work |
 | `README.md` | Documentation | - | Setup and usage guide |

 **Installation Path**: `.claude/agents/`
@@ -198,35 +199,38 @@ External tool and API integrations.

 ---

-## 06. Hooks (9 files)
+## 06. Hooks (12 files)

 Event-driven automation scripts that execute automatically.

 | File | Description | Event | Use Case |
 |------|-------------|-------|----------|
-| `format-code.sh` | Auto-format code | PreToolUse:Write | Code formatting |
-| `pre-commit.sh` | Run tests before commit | PreToolUse:Bash | Test automation |
-| `security-scan.sh` | Security scanning | PostToolUse:Write | Security checks |
-| `log-bash.sh` | Log bash commands | PostToolUse:Bash | Command logging |
-| `validate-prompt.sh` | Validate prompts | PreToolUse | Input validation |
-| `notify-team.sh` | Send notifications | Notification | Team notifications |
-| `context-tracker.py` | Track context window usage | PostToolUse | Context monitoring |
-| `context-tracker-tiktoken.py` | Token-based context tracking | PostToolUse | Precise token counting |
+| `format-code.sh` | Auto-format code | PostToolUse (matcher: Write) | Code formatting |
+| `pre-commit.sh` | Run tests before commit | PreToolUse (matcher: Bash) | Test automation |
+| `pre-tool-check.sh` | Validate and audit commands before they run | PreToolUse (matcher: Bash) | Guardrails, audit log |
+| `security-scan.sh` | Security scanning | PostToolUse (matcher: Write) | Security checks |
+| `dependency-check.sh` | Scan dependency manifests for vulnerabilities | PostToolUse (matcher: Write) | Supply-chain checks |
+| `log-bash.sh` | Log bash commands | PostToolUse (matcher: Bash) | Command logging |
+| `notify-team.sh` | Send notifications | PostToolUse (matcher: Bash) | Team notifications |
+| `validate-prompt.sh` | Validate prompts | UserPromptSubmit | Input validation |
+| `session-end.sh` | Capture progress when a session ends | SessionEnd | Progress tracking |
+| `context-tracker.py` | Track context window usage | UserPromptSubmit, Stop | Context monitoring |
+| `context-tracker-tiktoken.py` | Token-based context tracking | UserPromptSubmit, Stop | Precise token counting |
 | `README.md` | Documentation | - | Setup and usage guide |

 **Installation Path**: Configure in `~/.claude/settings.json`

 **Usage**: Configured in settings, executed automatically

-**Hook Types** (5 types, 29 events):
+**Hook Types** (5 types, 31 events):
 - Tool Hooks: PreToolUse, PostToolUse, PostToolUseFailure, PostToolBatch, PermissionRequest, PermissionDenied
 - Session Hooks: SessionStart, Setup, SessionEnd, Stop, StopFailure, SubagentStart, SubagentStop
- Task Hooks: UserPromptSubmit, UserPromptExpansion, TaskCompleted, TaskCreated, TeammateIdle
- Lifecycle Hooks: ConfigChange, CwdChanged, FileChanged, PreCompact, PostCompact, WorktreeCreate, WorktreeRemove, Notification, InstructionsLoaded, Elicitation, ElicitationResult
+- Task Hooks: UserPromptSubmit, UserPromptExpansion, MessageDisplay, TaskCompleted, TaskCreated, TeammateIdle
+- Lifecycle Hooks: ConfigChange, CwdChanged, DirectoryAdded, FileChanged, PreCompact, PostCompact, WorktreeCreate, WorktreeRemove, Notification, InstructionsLoaded, Elicitation, ElicitationResult

 ---

-## 07. Plugins (3 complete plugins, 27 files)
+## 07. Plugins (3 complete plugins, 39 files)

 Bundled collections of features.

@@ -358,7 +362,7 @@ Save conversation state and explore alternative approaches.

 ---

-## 09. Advanced Features (3 files)
+## 09. Advanced Features (4 files)

 Advanced capabilities for complex workflows.

@@ -367,6 +371,7 @@ Advanced capabilities for complex workflows.
 | `README.md` | Complete guide | All advanced features documentation |
 | `config-examples.json` | Configuration examples | 10+ use-case-specific configurations |
 | `planning-mode-examples.md` | Planning examples | REST API, database migration, refactoring |
+| `setup-auto-mode-permissions.py` | Seed `permissions.allow` for auto mode | Idempotent, `--dry-run` and opt-in flags |
 | Dynamic Workflows | Deterministic multi-agent orchestration via `/workflows` (v2.1.154) | Comprehensive audits, migrations, scale-out |
 | Scheduled Tasks | Recurring tasks with `/loop` and cron tools | Automated recurring workflows |
 | Chrome Integration | Browser automation via headless Chromium | Web testing and scraping |
@@ -402,8 +407,8 @@ Advanced capabilities for complex workflows.
 - **manual**: Ask for approval on risky actions (renamed from `default` in v2.1.200; `default` still accepted)
 - **acceptEdits**: Auto-accept file edits, ask for others
 - **plan**: Read-only analysis, no modifications
- **auto**: Automatically approve safe actions, prompt for risky ones
- **dontAsk**: Accept all actions except risky ones
+- **auto**: Everything, with background safety checks — a classifier reviews commands and protected-directory writes (configured via the `autoMode` settings object)
+- **dontAsk**: Only pre-approved tools — auto-denies every call that would otherwise prompt. Claude runs only `permissions.allow` matches, read-only Bash commands, and calls approved by a `PreToolUse` hook
 - **bypassPermissions**: Accept all (requires `--dangerously-skip-permissions`)

 ### Headless Mode (`claude -p`)
@@ -768,13 +773,13 @@ Run tests in background
 |----------|----------|--------|-----|-------|---------|-----------|------|--------|-------|
 | **01 Slash Commands** | 8 | - | - | - | - | - | 1 | 1 | **10** |
 | **02 Memory** | - | - | - | - | - | 3 | 1 | 2 | **6** |
-| **03 Skills** | - | - | - | - | 5 | 9 | 7 | - | **21** |
-| **04 Subagents** | - | 8 | - | - | - | - | 1 | - | **9** |
+| **03 Skills** | - | - | - | - | 5 | 7 | 11 | - | **23** |
+| **04 Subagents** | - | 9 | - | - | - | - | 1 | - | **10** |
 | **05 MCP** | - | - | 4 | - | - | - | 1 | - | **5** |
-| **06 Hooks** | - | - | - | 8 | - | - | 1 | - | **9** |
+| **06 Hooks** | - | - | - | 11 | - | - | 1 | - | **12** |
 | **07 Plugins** | 11 | 9 | 3 | 3 | 3 | 3 | 7 | - | **39** |
 | **08 Checkpoints** | - | - | - | - | - | - | 1 | 1 | **2** |
-| **09 Advanced** | - | - | - | - | - | - | 1 | 2 | **3** |
+| **09 Advanced** | - | - | - | - | 1 | 1 | 2 | - | **4** |
 | **10 CLI** | - | - | - | - | - | - | 1 | - | **1** |

 ---
@@ -881,7 +886,7 @@ Want to add more examples? Follow the structure:

 ---

-**Last Updated**: July 29, 2026
+**Last Updated**: August 4, 2026
 **Claude Code Version**: 2.1.220
 **Sources**:
 - https://code.claude.com/docs/en/overview
@@ -892,9 +897,9 @@ Want to add more examples? Follow the structure:
 - https://github.com/anthropics/claude-code/releases/tag/v2.1.154
 - https://github.com/anthropics/claude-code/blob/main/CHANGELOG.md
 - https://code.claude.com/docs/en/model-config
-**Compatible Models**: Claude Opus 5, Claude Sonnet 5, Claude Sonnet 4.6, Claude Opus 4.8, Claude Haiku 4.5
+**Compatible Models**: Claude Fable 5, Claude Opus 5, Claude Sonnet 5, Claude Sonnet 4.6, Claude Opus 4.8, Claude Haiku 4.5
 **Total Examples**: 100+ files
 **Categories**: 10 features
-**Hooks**: 9 automation scripts
+**Hooks**: 11 automation scripts
 **Configuration Examples**: 10+ scenarios
 **Ready to Use**: All examples
@@ -97,7 +97,7 @@ graph TD

 | Step | Feature | Complexity | Time | Level | Dependencies | Why Learn This | Key Benefits |
 |------|---------|-----------|------|-------|--------------|----------------|--------------|
-| **1** | [Slash Commands](01-slash-commands/) | ⭐ Beginner | 30 min | Level 1 | None | Quick productivity wins (60+ built-in + 5 bundled skills) | Instant automation, team standards |
+| **1** | [Slash Commands](01-slash-commands/) | ⭐ Beginner | 30 min | Level 1 | None | Quick productivity wins (60+ built-in + 10 bundled skills) | Instant automation, team standards |
 | **2** | [Memory](02-memory/) | ⭐⭐ Beginner+ | 45 min | Level 1 | None | Essential for all features | Persistent context, preferences |
 | **3** | [Checkpoints](08-checkpoints/) | ⭐⭐ Intermediate | 45 min | Level 1 | Session management | Safe exploration | Experimentation, recovery |
 | **4** | [CLI Basics](10-cli/) | ⭐⭐ Beginner+ | 30 min | Level 1 | None | Core CLI usage | Interactive & print mode |
@@ -738,7 +738,7 @@ Once you've completed all milestones:

 ---

-**Last Updated**: July 29, 2026
+**Last Updated**: August 4, 2026
 **Claude Code Version**: 2.1.220
 **Sources**:
 - https://code.claude.com/docs/en/overview
@@ -747,7 +747,7 @@ Once you've completed all milestones:
 - https://github.com/anthropics/claude-code/releases/tag/v2.1.144
 - https://github.com/anthropics/claude-code/releases/tag/v2.1.145
 - https://code.claude.com/docs/en/model-config
-**Compatible Models**: Claude Opus 5, Claude Sonnet 5, Claude Sonnet 4.6, Claude Opus 4.8, Claude Haiku 4.5
+**Compatible Models**: Claude Fable 5, Claude Opus 5, Claude Sonnet 5, Claude Sonnet 4.6, Claude Opus 4.8, Claude Haiku 4.5
 **Maintained by**: Claude How-To Contributors
 **License**: Educational purposes, free to use and adapt

@@ -119,7 +119,7 @@ claude -r "session"    # Resume session by name/ID
 | **Skills** | `.claude/skills/*/SKILL.md` | Auto-invoked |
 | **Subagents** | `.claude/agents/*.md` | Auto-delegated |
 | **MCP** | `.mcp.json` (project) or `~/.claude.json` (user) | `/mcp__server__action` |
-| **Hooks (29 events)** | `~/.claude/hooks/*.sh` | Event-triggered (5 types) |
+| **Hooks (31 events)** | `~/.claude/hooks/*.sh` | Event-triggered (5 types) |
 | **Plugins** | Via `/plugin install` | Bundles all |
 | **Checkpoints** | Built-in | `Esc+Esc` or `/rewind` |
 | **Planning Mode** | Built-in | `/plan <task>` |
@@ -190,7 +190,7 @@ vim CLAUDE.md

 ### Automation & Hooks
 ```bash
-# Install hooks (29 events, 5 types: command, http, mcp_tool, prompt, agent)
+# Install hooks (31 events, 5 types: command, http, mcp_tool, prompt, agent)
 mkdir -p ~/.claude/hooks
 cp 06-hooks/*.sh ~/.claude/hooks/
 chmod +x ~/.claude/hooks/*.sh
@@ -390,7 +390,9 @@ cp -r 03-skills/code-review-specialist ~/.claude/skills/
 | **Auto Mode** | Fully autonomous operation with background classifier; available by default on Bedrock/Vertex/Foundry as of v2.1.207 | `Shift+Tab` to cycle modes, or `--permission-mode auto` |
 | **Channels** | Discord and Telegram integration | `--channels` flag, Discord/Telegram bots |
 | **Voice Dictation** | Speak commands and context to Claude | `/voice` command |
-| **Hooks (29 events)** | Expanded hook system with 5 types | command, http, mcp_tool, prompt, agent hook types |
+| **Output Styles** | Change Claude's role, tone, and default response format | `/config` → Output style, or `outputStyle` setting. Built-ins: Default, Proactive, Explanatory, Learning |
+| **Status Line** | Custom bottom-of-session status from a command | `/statusline`, or `statusLine` setting; receives session/model/cost/context JSON on stdin |
+| **Hooks (31 events)** | Expanded hook system with 5 types | command, http, mcp_tool, prompt, agent hook types |
 | **MCP Elicitation** | MCP servers can request user input at runtime | Auto-prompted when server needs clarification |
 | **Plugin LSP** | Language Server Protocol support for plugins | `userConfig`, `${CLAUDE_PLUGIN_DATA}` variable |
 | **Remote Control** | Control Claude Code via WebSocket API | `claude --remote` for external integrations |
@@ -453,7 +455,7 @@ echo $GITHUB_TOKEN
 | Auto workflow | Skill | `03-skills/code-review-specialist/` |
 | Specialized task | Subagent | `04-subagents/code-reviewer.md` |
 | External data | MCP (+ Elicitation) | `05-mcp/github-mcp.json` |
-| Event automation | Hook (29 events, 5 types) | `06-hooks/pre-commit.sh` |
+| Event automation | Hook (31 events, 5 types) | `06-hooks/pre-commit.sh` |
 | Complete solution | Plugin (+ LSP support) | `07-plugins/pr-review/` |
 | Safe experiment | Checkpoint | `08-checkpoints/checkpoint-examples.md` |
 | Fully autonomous | Auto Mode | `--permission-mode auto` or `Shift+Tab` |
@@ -514,7 +516,7 @@ Getting started checklist:

 ---

-**Last Updated**: July 29, 2026
+**Last Updated**: August 4, 2026
 **Claude Code Version**: 2.1.220
 **Sources**:
 - https://code.claude.com/docs/en/cli-reference
@@ -522,4 +524,4 @@ Getting started checklist:
 - https://code.claude.com/docs/en/sub-agents
 - https://code.claude.com/docs/en/model-config
 - https://code.claude.com/docs/en/settings
-**Compatible Models**: Claude Opus 5, Claude Sonnet 5, Claude Sonnet 4.6, Claude Opus 4.8, Claude Haiku 4.5
+**Compatible Models**: Claude Fable 5, Claude Opus 5, Claude Sonnet 5, Claude Sonnet 4.6, Claude Opus 4.8, Claude Haiku 4.5
@@ -12,7 +12,7 @@
 [![GitHub Stars](https://img.shields.io/github/stars/luongnv89/claude-howto?style=flat&color=gold)](https://github.com/luongnv89/claude-howto/stargazers)
 [![GitHub Forks](https://img.shields.io/github/forks/luongnv89/claude-howto?style=flat)](https://github.com/luongnv89/claude-howto/network/members)
 [![License: MIT](https://img.shields.io/badge/License-MIT-blue.svg)](LICENSE)
-[![Version](https://img.shields.io/badge/version-2.1.217-brightgreen)](CHANGELOG.md)
+[![Version](https://img.shields.io/badge/version-2.1.220-brightgreen)](CHANGELOG.md)
 [![Claude Code](https://img.shields.io/badge/Claude_Code-2.1+-purple)](https://code.claude.com)

 🌐 **Language / Ngôn ngữ / 语言 / Мова:** [English](README.md) | [Tiếng Việt](vi/README.md) | [中文](zh/README.md) | [Українська](uk/README.md) | [日本語](ja/README.md)
@@ -102,7 +102,7 @@ Run `/lesson-quiz [topic]` after each module. The quiz pinpoints what you missed

 - **GitHub stars** from developers who use Claude Code daily
 - **Forks** from teams adapting this guide for their own workflows
- **Actively maintained** — synced with every Claude Code release (latest: v2.1.217, July 2026)
+- **Actively maintained** — synced with every Claude Code release (latest: v2.1.220, July 2026)
 - **Community-driven** — contributions from developers who share their real-world configurations

 [![Star History Chart](https://api.star-history.com/svg?repos=luongnv89/claude-howto&type=Date)](https://star-history.com/#luongnv89/claude-howto&Date)
@@ -201,7 +201,7 @@ cp -r 03-skills/code-review-specialist ~/.claude/skills/
 Yes. MIT licensed, free forever. Use it in personal projects, at work, in your team — no restrictions beyond including the license notice.

 **Is this maintained?**
-Actively. The guide is synced with every Claude Code release. Current version: v2.1.217 (July 2026), compatible with Claude Code 2.1+.
+Actively. The guide is synced with every Claude Code release. Current version: v2.1.220 (July 2026), compatible with Claude Code 2.1+.

 **How is this different from the official docs?**
 The official docs are a feature reference. This guide is a tutorial with diagrams, production-ready templates, and a progressive learning path. They complement each other — start here to learn, reference the docs when you need specifics.
@@ -482,11 +482,11 @@ Configure hooks in `~/.claude/settings.json`:

 **Usage**: Hooks execute automatically on events

-**Hook Types** (5 types, 29 events):
- **Tool Hooks**: `PreToolUse`, `PostToolUse`, `PostToolUseFailure`, `PermissionRequest`
- **Session Hooks**: `SessionStart`, `SessionEnd`, `Stop`, `StopFailure`, `SubagentStart`, `SubagentStop`
- **Task Hooks**: `UserPromptSubmit`, `TaskCompleted`, `TaskCreated`, `TeammateIdle`
- **Lifecycle Hooks**: `ConfigChange`, `CwdChanged`, `FileChanged`, `PreCompact`, `PostCompact`, `WorktreeCreate`, `WorktreeRemove`, `Notification`, `InstructionsLoaded`, `Elicitation`, `ElicitationResult`
+**Hook Types** (5 types, 31 events):
+- **Tool Hooks**: `PreToolUse`, `PostToolUse`, `PostToolUseFailure`, `PostToolBatch`, `PermissionRequest`, `PermissionDenied`
+- **Session Hooks**: `SessionStart`, `Setup`, `SessionEnd`, `Stop`, `StopFailure`, `SubagentStart`, `SubagentStop`
+- **Task Hooks**: `UserPromptSubmit`, `UserPromptExpansion`, `MessageDisplay`, `TaskCompleted`, `TaskCreated`, `TeammateIdle`
+- **Lifecycle Hooks**: `ConfigChange`, `CwdChanged`, `DirectoryAdded`, `FileChanged`, `PreCompact`, `PostCompact`, `WorktreeCreate`, `WorktreeRemove`, `Notification`, `InstructionsLoaded`, `Elicitation`, `ElicitationResult`

 </details>

@@ -871,7 +871,7 @@ MIT License - see [LICENSE](LICENSE). Free to use, modify, and distribute. The o

 ---

-**Last Updated**: July 29, 2026
+**Last Updated**: August 4, 2026
 **Claude Code Version**: 2.1.220
 **Sources**:
 - https://code.claude.com/docs/en/overview
@@ -882,4 +882,4 @@ MIT License - see [LICENSE](LICENSE). Free to use, modify, and distribute. The o
 - https://github.com/anthropics/claude-code/releases/tag/v2.1.154
 - https://code.claude.com/docs/en/model-config
 - https://github.com/anthropics/claude-code/blob/main/CHANGELOG.md
-**Compatible Models**: Claude Opus 5, Claude Sonnet 5, Claude Sonnet 4.6, Claude Opus 4.8, Claude Haiku 4.5
+**Compatible Models**: Claude Fable 5, Claude Opus 5, Claude Sonnet 5, Claude Sonnet 4.6, Claude Opus 4.8, Claude Haiku 4.5
@@ -326,7 +326,11 @@ This security policy is reviewed and updated:
 - When the project scope changes
 - Annually as a minimum

-**Last Updated**: April 27, 2026
+**Last Updated**: August 4, 2026
+**Claude Code Version**: 2.1.220
+**Sources**:
+- https://code.claude.com/docs/en/overview
+**Compatible Models**: Claude Fable 5, Claude Opus 5, Claude Sonnet 5, Claude Sonnet 4.6, Claude Opus 4.8, Claude Haiku 4.5
 **Next Review**: April 2027

 ---
@@ -599,7 +599,7 @@ Lesson READMEs end with a metadata block:
 ---
 **Last Updated**: July 29, 2026
 **Claude Code Version**: 2.1.220
-**Compatible Models**: Claude Opus 5, Claude Sonnet 5, Claude Sonnet 4.6, Claude Opus 4.8, Claude Haiku 4.5
+**Compatible Models**: Claude Fable 5, Claude Opus 5, Claude Sonnet 5, Claude Sonnet 4.6, Claude Opus 4.8, Claude Haiku 4.5
 ```

 - Use month + day + year format (e.g., "May 20, 2026")
@@ -638,4 +638,4 @@ Before submitting content, verify:
 - https://code.claude.com/docs/en/changelog
 - https://code.claude.com/docs/en/model-config
 - https://github.com/anthropics/claude-code/releases/tag/v2.1.154
-**Compatible Models**: Claude Opus 5, Claude Sonnet 5, Claude Sonnet 4.6, Claude Opus 4.8, Claude Haiku 4.5
+**Compatible Models**: Claude Fable 5, Claude Opus 5, Claude Sonnet 5, Claude Sonnet 4.6, Claude Opus 4.8, Claude Haiku 4.5
@@ -108,4 +108,8 @@ These rules guide code generation to produce maintainable, professional-quality
 **Core Philosophy**: Code is read 10x more than written. Optimize for readability and maintainability, not cleverness.

 ---
-**Last Updated**: April 9, 2026
+**Last Updated**: August 4, 2026
+**Claude Code Version**: 2.1.220
+**Sources**:
+- https://code.claude.com/docs/en/overview
+**Compatible Models**: Claude Fable 5, Claude Opus 5, Claude Sonnet 5, Claude Sonnet 4.6, Claude Opus 4.8, Claude Haiku 4.5
@@ -56,7 +56,7 @@
 | `/install-github-app` | GitHub Actions アプリをセットアップ |
 | `/install-slack-app` | Slack アプリをインストール |
 | `/keybindings` | キーバインド設定を開く |
-| `/less-permission-prompts` | 直近の Bash／MCP ツール呼び出しを分析し、優先度の高い許可リストを `.claude/settings.json` に追加して権限プロンプトを減らす（v2.1.111 で追加） |
+| `/fewer-permission-prompts` | 直近の Bash／MCP ツール呼び出しを分析し、優先度の高い許可リストを `.claude/settings.json` に追加して権限プロンプトを減らす（v2.1.111 で追加） |
 | `/login` | Anthropic アカウントを切り替え |
 | `/logout` | Anthropic アカウントからサインアウト |
 | `/mcp` | MCP サーバーと OAuth を管理 |
@@ -116,7 +116,7 @@
 | コマンド | ステータス |
 |---------|----------|
 | `/review` | 非推奨 — `code-review` プラグインに置き換え |
-| `/output-style` | v2.1.73 から非推奨 |
+| `/output-style` | v2.1.91 で削除 — 出力スタイルは `/config` または `outputStyle` 設定から引き続き利用できる |
 | `/fork` | `/branch` に改名（エイリアスは引き続き有効、v2.1.77） |
 | `/pr-comments` | v2.1.91 で削除 — Claude に直接 PR コメントを見るよう依頼する |
 | `/vim` | v2.1.92 で削除 — /config → エディタモードを使う |
@@ -124,7 +124,7 @@
 ### 直近の変更点

 - `/fork` を `/branch` に改名し、`/fork` はエイリアスとして残置（v2.1.77）
- `/output-style` を非推奨化（v2.1.73）
+- `/output-style` を削除（v2.1.91）。出力スタイル自体は `/config` または `outputStyle` 設定で引き続き利用できる
 - `/review` を非推奨化、`code-review` プラグインを推奨
 - `/effort` コマンドを追加。`max` レベルは Opus 4.7 が必要（当初は Opus 4.6 限定）
 - プッシュトゥトーク音声入力の `/voice` コマンドを追加
@@ -146,7 +146,7 @@
 - `/proactive` を `/loop` のエイリアスとして追加（v2.1.105）
 - `/effort` がインタラクティブな矢印キースライダーを獲得し、`high` と `max` の間に新しい `xhigh` レベルを追加。Opus 4.7 プランではデフォルト思考量が `xhigh` に引き上げられた（v2.1.111）
 - 包括的なクラウドベースのマルチエージェントコードレビュー用に `/ultrareview` を追加（v2.1.111）
- Bash／MCP ツール呼び出しを分析し、`.claude/settings.json` の許可リストで権限プロンプトを減らす `/less-permission-prompts` を追加（v2.1.111）
+- Bash／MCP ツール呼び出しを分析し、`.claude/settings.json` の許可リストで権限プロンプトを減らす `/fewer-permission-prompts` を追加（v2.1.111）
 - Opus 4.7 を利用する Max サブスクライバについて、Auto モードに `--enable-auto-mode` フラグが不要になった（v2.1.112）

 ### `/team-onboarding` — チームメイト向けランプアップガイド
@@ -3,9 +3,8 @@
 <!-- i18n-date: 2026-04-27 -->

 ---
-name: Documentation Refactor
+name: doc-refactor
 description: プロジェクトドキュメントを再構成して明瞭性とアクセシビリティを高める
-tags: documentation, refactoring, organization
 ---

 # ドキュメントリファクタリング
@@ -3,9 +3,8 @@
 <!-- i18n-date: 2026-04-27 -->

 ---
-name: Setup CI/CD Pipeline
+name: setup-ci-cd
 description: 品質保証のための pre-commit フックと GitHub Actions を導入する
-tags: ci-cd, devops, automation
 ---

 # CI/CD パイプラインのセットアップ
--- a/Show More
+++ b/Show More