CalvinBackup/claude-howto
1
0
Fork 0
mirror of https://github.com/luongnv89/claude-howto.git synced 2026-09-22 01:10:42 +02:00
Code Issues Packages Projects Releases Wiki Activity

docs: sync to Claude Code v2.1.278 (#183)

Browse Source 
* docs: sync to Claude Code v2.1.278

Type: docs

Audit of the tutorial against Claude Code 2.1.278 (repo baseline was
2.1.263). Fixes claims the repo asserts that are now false; new-feature
coverage is English-only.

P0 - the repo stated the opposite of current behavior:
- AGENTS.md: the claude-md skill said Claude Code "does not read
  AGENTS.md directly" in all 5 languages. It has since v2.1.277, when no
  CLAUDE.md exists at or above the working directory.
- /output-style: listed as "Removed in v2.1.91" in 5 languages and in
  09-advanced-features. Re-added in v2.1.269; row moved out of the
  Deprecated Commands table.
- Permission rules: setup-auto-mode-permissions.py seeded Write(*),
  Glob(*) and NotebookEdit(*), which Claude Code accepts but never
  consults and warns about at startup. Removed; same fix in the
  config-examples.json profile and the 06/09 category tables.
- taskOutputMaxChars: documented as live. The TaskOutput tool was
  removed in v2.1.278 and the key is inert.

P1:
- Dynamic workflow "medium" guideline is fewer than 10 agents, not 15;
  the default is small on Pro plans since v2.1.271.
- Todo-tool availability restated as the official allowlist (Claude 3.x,
  Opus 4-4.7, Sonnet 4-4.6, Haiku 4.5) instead of a denylist; 23 sites
  across 5 languages.
- Memory hierarchy now notes the AGENTS.md fallback.
- Auto-mode classifier cost qualified: not charged on Enterprise plans
  and Claude API accounts since v2.1.278.

P3 (English only): full AGENTS.md section in 02-memory; omitClaudeMd
subagent field; plugin eval / --json / --accept-command / --marketplace;
maxEffortLevel, bashEditDiffEnabled, syncClaudeAi*, 4 env vars,
--system-prompt-snapshot, --plugin-dir folders; send-now key and Monitor
deadlines; checkpoints subagent-edit limitation.

Learning skills audited clean: 100 quiz questions and 100 Review
pointers all valid, 20 self-assessment options correctly mapped.

Cross-file anchors: 15 broken before, 15 after, 0 introduced.

* docs: address review — stale version stamps, /output-style re-add, permission tables
This commit is contained in:
Luong NGUYEN
2026-09-20 01:15:34 +02:00
committed by GitHub
parent 97bfb0685e
commit 8aeb5a72dc
49 changed files with 356 additions and 198 deletions
Download Patch File Download Diff File Expand all files Collapse all files
02-memory/README.md
+55 -3
View File
@@ -219,7 +219,7 @@ Claude Code has two complementary memory systems, both loaded at the start of ev
|-------|----------|---------|
| Managed policy | macOS: `/Library/Application Support/ClaudeCode/CLAUDE.md`<br>Linux/WSL: `/etc/claude-code/CLAUDE.md`<br>Windows: `C:\Program Files\ClaudeCode\CLAUDE.md` | Organization-wide instructions managed by IT/DevOps. Cannot be excluded by individual settings. |
| User instructions | `~/.claude/CLAUDE.md` | Personal preferences for all projects |
| Project instructions | `./CLAUDE.md` or `./.claude/CLAUDE.md` | Team-shared instructions, version controlled |
| Project instructions | `./CLAUDE.md` or `./.claude/CLAUDE.md` | Team-shared instructions, version controlled. Since v2.1.277, `./AGENTS.md` loads at this same tier instead, when no `CLAUDE.md` or `CLAUDE.local.md` exists at or above the working directory — controlled by **Project instructions** in `/config` |
| Local instructions | `./CLAUDE.local.md` | Personal project-specific preferences; add to `.gitignore` |
Within the directory tree, Claude Code walks up from your working directory: `foo/CLAUDE.md` loads before `foo/bar/CLAUDE.md` if you launch from `foo/bar/`, so instructions closer to where you launched are read *last* — not "highest priority" in an override sense, just most recent in context. Within each directory, `CLAUDE.local.md` is appended after `CLAUDE.md`. CLAUDE.md and CLAUDE.local.md files in subdirectories *under* your working directory load on demand, when Claude reads files in those subdirectories, rather than at launch.
@@ -253,6 +253,57 @@ graph TD
All files shown are concatenated into one context, not selected by override — later boxes appear later in context, not "instead of" earlier ones.
## AGENTS.md
`AGENTS.md` is a cross-tool project-context file: the same *category* of document as CLAUDE.md, written so that several coding agents can share one set of project conventions. Since **v2.1.277**, Claude Code reads it directly as project instructions rather than requiring you to import it.
**Default behavior** (`claude-md-or-agents-md`):
| What the project contains | What Claude Code reads |
|---------------------------|------------------------|
| `AGENTS.md`, no `CLAUDE.md` | `AGENTS.md` |
| Both `AGENTS.md` and `CLAUDE.md` | `CLAUDE.md` only |
| A `CLAUDE.md` that imports `AGENTS.md` with `@AGENTS.md` | `CLAUDE.md`, with the import expanded |
**Which files suppress AGENTS.md.** Claude Code checks the working directory and every directory above it for `CLAUDE.md`, `.claude/CLAUDE.md`, or `CLAUDE.local.md`. If it finds any of them, `AGENTS.md` is not read. `~/.claude/CLAUDE.md`, managed CLAUDE.md, and `.claude/rules/` do **not** count for this check and keep loading alongside whichever project file wins.
> **Warning**: adding a `CLAUDE.local.md` silently stops `AGENTS.md` being read. If your project instructions seem to vanish after you create a local override, this is usually why.
**What gets read.** Every `AGENTS.md` and `.claude/AGENTS.md` at and above the working directory loads at session start; files in subdirectories load on demand, when Claude reads files there. `@path` imports expand the same way they do in CLAUDE.md, and `claudeMdExcludes` applies.
**What is never read**: `AGENTS.local.md`, `AGENTS.override.md`, and anything under `.agents/`.
**Choosing the behavior.** The **Project instructions** setting takes four values:
| Value | Effect |
|-------|--------|
| `claude-md-or-agents-md` | Default — `AGENTS.md` only when no CLAUDE.md file is found |
| `claude-md-and-agents-md` | Both are read when both exist |
| `claude-md` | Only CLAUDE.md files; `AGENTS.md` is ignored |
| `managed-only` | Only managed policy instructions |
Set it through `/config`, or in settings:
```jsonc
{
"pluginConfigs": {
"agents-md@builtin": {
"options": {
"instructionFiles": "claude-md-and-agents-md"
}
}
}
}
```
This key is honored in user and managed settings only — setting it in project or local settings has no effect.
**Where direct reading is unavailable.** On versions before v2.1.277, on Bedrock/Vertex/Foundry, with telemetry disabled, during the first session after upgrading, under `disableAllHooks` or `allowManagedHooksOnly`, or with the built-in `agents-md` plugin disabled, Claude Code will not pick up `AGENTS.md` on its own. In those cases, import it from CLAUDE.md:
```markdown
@AGENTS.md
```
## Excluding CLAUDE.md Files with `claudeMdExcludes`
In large monorepos, some CLAUDE.md files may be irrelevant to your current work. The `claudeMdExcludes` setting lets you skip specific CLAUDE.md files so they are not loaded into context:
@@ -1193,8 +1244,9 @@ Auto Memory is a separate mechanism (`~/.claude/projects/<project>/memory/`), no
---
**Last Updated**: August 25, 2026
**Claude Code Version**: 2.1.245
**Last Updated**: September 19, 2026
**Claude Code Version**: 2.1.278
**Sources**:
- https://code.claude.com/docs/en/memory
- https://code.claude.com/docs/en/memory#agents-md
**Compatible Models**: Claude Fable 5, Claude Opus 5, Claude Sonnet 5, Claude Sonnet 4.6, Claude Opus 4.8, Claude Haiku 4.5