fix: apply 2026-04-09 documentation accuracy updates

P0 Critical:
- Remove /vim (removed in v2.1.92) from CATALOG.md, zh/CATALOG.md active tables
- Move /vim to deprecated section in zh/01-slash-commands/README.md
- Fix fake hook events (PreCommit/PrePush/PostPush) in config-examples.json
- Replace with real PreToolUse hook pattern
- Update deprecated model IDs: claude-sonnet-4-5 → claude-sonnet-4-6 (x4)
- Fix notify-team.sh comment: PostPush → PostToolUse with explanation
- Mark # memory shortcut as discontinued in 02-memory/README.md

P2 Conflicts resolved:
- effort:max confirmed valid in current CLI; no changes needed
- Remove WebSocket MCP transport (not supported; only stdio/sse/http valid)
  from 05-mcp/README.md, CATALOG.md, QUICK_REFERENCE.md

P4 Cosmetic:
- Update hook count 25 → 26 in QUICK_REFERENCE.md

Generated with [Claude Code](https://claude.ai/code)
via [Happy](https://happy.engineering)

Co-Authored-By: Claude <noreply@anthropic.com>
Co-Authored-By: Happy <yesreply@happy.engineering>
This commit is contained in:
Luong NGUYEN
2026-04-09 06:32:26 +02:00
parent 561c6cbaa3
commit e015f39c68
8 changed files with 35 additions and 60 deletions
+19 -31
View File
@@ -25,9 +25,7 @@ The memory system operates at multiple levels, from global personal preferences
|---------|---------|-------|-------------|
| `/init` | Initialize project memory | `/init` | Starting new project, first-time CLAUDE.md setup |
| `/memory` | Edit memory files in editor | `/memory` | Extensive updates, reorganization, reviewing content |
| `#` prefix | Quick single-line memory add | `# Your rule here` | Adding quick rules during conversation |
| `# new rule into memory` | Explicit memory addition | `# new rule into memory<br/>Your detailed rule` | Adding complex multi-line rules |
| `# remember this` | Natural language memory | `# remember this<br/>Your instruction` | Conversational memory updates |
| `#` prefix | ~~Quick single-line memory add~~ **Discontinued** | — | Use `/memory` or ask conversationally instead |
| `@path/to/file` | Import external content | `@README.md` or `@docs/api.md` | Referencing existing documentation in CLAUDE.md |
## Quick Start: Initializing Memory
@@ -82,49 +80,39 @@ CLAUDE_CODE_NEW_INIT=1 claude
- Git workflow conventions
```
### Quick Memory Updates with `#`
### Quick Memory Updates
You can quickly add information to memory during any conversation by starting your message with `#`:
> **Note**: The `#` shortcut for inline memory was discontinued. Use `/memory` to edit memory files directly, or ask Claude conversationally to remember something (e.g., "remember that we always use TypeScript strict mode").
**Syntax:**
The recommended ways to add information to memory are:
```markdown
# Your memory rule or instruction here
**Option 1: Use `/memory` command**
```bash
/memory
```
**Examples:**
Opens your memory files in your system editor for direct editing.
```markdown
# Always use TypeScript strict mode in this project
**Option 2: Ask conversationally**
# Prefer async/await over promise chains
# Run npm test before every commit
# Use kebab-case for file names
```
Remember that we always use TypeScript strict mode in this project.
Please add to memory: prefer async/await over promise chains.
```
**How it works:**
Claude will update the appropriate CLAUDE.md file based on your request.
1. Start your message with `#` followed by your rule
2. Claude recognizes this as a memory update request
3. Claude asks which memory file to update (project or personal)
4. The rule is added to the appropriate CLAUDE.md file
5. Future sessions automatically load this context
**Historical reference** (no longer functional):
**Alternative patterns:**
The `#` prefix shortcut previously allowed adding rules inline:
```markdown
# new rule into memory
Always validate user input with Zod schemas
# remember this
Use semantic versioning for all releases
# add to memory
Database migrations must be reversible
# Always use TypeScript strict mode in this project ← no longer works
```
If you relied on this pattern, switch to the `/memory` command or conversational requests.
### The `/memory` Command
The `/memory` command provides direct access to edit your CLAUDE.md memory files within Claude Code sessions. It opens your memory files in your system editor for comprehensive editing.
-8
View File
@@ -105,14 +105,6 @@ Server-Sent Events transport is deprecated in favor of `http` but still supporte
claude mcp add --transport sse legacy-server https://example.com/sse
```
### WebSocket Transport
WebSocket transport for persistent bidirectional connections:
```bash
claude mcp add --transport ws realtime-server wss://example.com/mcp
```
### Windows-Specific Note
On native Windows (not WSL), use `cmd /c` for npx commands:
+3 -1
View File
@@ -1,6 +1,8 @@
#!/bin/bash
# Send notifications on events
# Hook: PostPush
# Hook: PostToolUse (matcher: Bash) — run after bash commands; filter for git push in script logic
# Note: Claude Code has no native PostPush event. To trigger on git push, check the bash command
# string for "git push" using a matcher or conditional logic within this script.
REPO_NAME=$(basename $(git rev-parse --show-toplevel 2>/dev/null) 2>/dev/null)
COMMIT_MSG=$(git log -1 --pretty=%B 2>/dev/null)
+9 -12
View File
@@ -7,7 +7,7 @@
"description": "Configuration for active development work",
"config": {
"general": {
"model": "claude-sonnet-4-5",
"model": "claude-sonnet-4-6",
"temperature": 0.7
},
"planning": {
@@ -24,8 +24,7 @@
},
"hooks": {
"PreToolUse:Write": "prettier --write ${file_path}",
"PostToolUse:Write": "eslint ${file_path}",
"PreCommit": "npm test"
"PostToolUse:Write": "eslint ${file_path}"
}
}
},
@@ -35,7 +34,7 @@
"description": "Configuration for reviewing code without modifications",
"config": {
"general": {
"model": "claude-sonnet-4-5",
"model": "claude-sonnet-4-6",
"temperature": 0.3
},
"permissions": {
@@ -56,7 +55,7 @@
"description": "Configuration for learning and experimentation",
"config": {
"general": {
"model": "claude-sonnet-4-5",
"model": "claude-sonnet-4-6",
"temperature": 0.5
},
"permissions": {
@@ -90,9 +89,7 @@
"requireConfirmationFor": ["Bash", "Git", "Write", "Edit"]
},
"hooks": {
"PreCommit": "npm test && npm run lint && npm run build",
"PrePush": "npm run test:e2e",
"PostPush": "~/.claude/hooks/notify-team.sh"
"PreToolUse": "~/.claude/hooks/pre-commit.sh"
},
"checkpoints": {
"autoCheckpoint": true
@@ -109,7 +106,7 @@
"description": "Configuration for automated CI/CD operations",
"config": {
"general": {
"model": "claude-sonnet-4-5",
"model": "claude-sonnet-4-6",
"temperature": 0
},
"permissions": {
@@ -158,7 +155,7 @@
"description": "Configuration for performance analysis and optimization",
"config": {
"general": {
"model": "claude-sonnet-4-5",
"model": "claude-sonnet-4-6",
"temperature": 0.4
},
"planning": {
@@ -180,7 +177,7 @@
"description": "Configuration for collaborative development",
"config": {
"general": {
"model": "claude-sonnet-4-5",
"model": "claude-sonnet-4-6",
"temperature": 0.6
},
"permissions": {
@@ -255,7 +252,7 @@
"description": "Configuration for writing documentation",
"config": {
"general": {
"model": "claude-sonnet-4-5",
"model": "claude-sonnet-4-6",
"temperature": 0.7
},
"permissions": {
-2
View File
@@ -63,7 +63,6 @@ Commands are user-invoked shortcuts that execute specific actions.
| `/login` | Authenticate with Anthropic | Access features |
| `/logout` | Sign out | Switch accounts |
| `/sandbox` | Toggle sandbox mode | Safe command execution |
| `/vim` | Toggle vim mode | Vim-style editing |
| `/doctor` | Run diagnostics | Troubleshoot issues |
| `/reload-plugins` | Reload installed plugins | Plugin management |
| `/release-notes` | Show release notes | Check new features |
@@ -453,7 +452,6 @@ cp 02-memory/personal-CLAUDE.md ~/.claude/CLAUDE.md
| **Agent Hook Type** | Hooks that spawn a subagent instead of running a shell command | Set `"type": "agent"` in hook configuration |
| **Prompt Hook Type** | Hooks that inject prompt text into the conversation | Set `"type": "prompt"` in hook configuration |
| **MCP Elicitation** | MCP servers can request user input during tool execution | Handle via `Elicitation` and `ElicitationResult` hook events |
| **WebSocket MCP Transport** | WebSocket-based transport for MCP server connections | Use `"transport": "websocket"` in MCP server config |
| **Plugin LSP Support** | Language Server Protocol integration via plugins | Configure LSP servers in `plugin.json` for editor features |
| **Managed Drop-ins** | Organization-managed drop-in configurations (v2.1.83) | Admin-configured via managed policies; auto-applied to all users |
+3 -4
View File
@@ -389,9 +389,8 @@ cp -r 03-skills/code-review ~/.claude/skills/
| **Auto Mode** | Fully autonomous operation with background classifier | `--enable-auto-mode` flag, `Shift+Tab` to cycle modes |
| **Channels** | Discord and Telegram integration | `--channels` flag, Discord/Telegram bots |
| **Voice Dictation** | Speak commands and context to Claude | `/voice` command |
| **Hooks (25 events)** | Expanded hook system with 4 types | command, http, prompt, agent hook types |
| **Hooks (26 events)** | Expanded hook system with 4 types | command, http, prompt, agent hook types |
| **MCP Elicitation** | MCP servers can request user input at runtime | Auto-prompted when server needs clarification |
| **WebSocket MCP** | WebSocket transport for MCP connections | Configure in `.mcp.json` with `ws://` URLs |
| **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 |
| **Web Sessions** | Browser-based Claude Code interface | `claude web` to launch |
@@ -444,8 +443,8 @@ echo $GITHUB_TOKEN
| Team standards | Memory | `02-memory/project-CLAUDE.md` |
| Auto workflow | Skill | `03-skills/code-review/` |
| Specialized task | Subagent | `04-subagents/code-reviewer.md` |
| External data | MCP (+ Elicitation, WebSocket) | `05-mcp/github-mcp.json` |
| Event automation | Hook (25 events, 4 types) | `06-hooks/pre-commit.sh` |
| External data | MCP (+ Elicitation) | `05-mcp/github-mcp.json` |
| Event automation | Hook (26 events, 4 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 | `--enable-auto-mode` or `Shift+Tab` |
+1 -1
View File
@@ -81,7 +81,6 @@ Claude Code 目前提供 55+ 个内置命令和 5 个内置 Skills。你可以
| `/tasks` | 列出/管理后台任务 |
| `/terminal-setup` | 配置终端快捷键 |
| `/theme` | 更改颜色主题 |
| `/vim` | 切换 Vim/Normal 模式 |
| `/voice` | 切换按住说话语音输入 |
### 内置 Skills
@@ -103,6 +102,7 @@ Claude Code 目前提供 55+ 个内置命令和 5 个内置 Skills。你可以
| `/review` | 已弃用,已被 `code-review` 插件替代 |
| `/output-style` | 自 v2.1.73 起弃用 |
| `/fork` | 已重命名为 `/branch`(别名仍可用,v2.1.77 |
| `/vim` | 自 v2.1.92 起移除;改用 `/config → Editor mode` |
### 最近变化
-1
View File
@@ -63,7 +63,6 @@
| `/login` | 通过 Anthropic 认证 | 访问功能 |
| `/logout` | 登出 | 切换账号 |
| `/sandbox` | 切换 sandbox 模式 | 安全执行命令 |
| `/vim` | 切换 vim 模式 | 类 Vim 编辑 |
| `/doctor` | 运行诊断 | 排查问题 |
| `/reload-plugins` | 重新加载已安装的 plugins | 插件管理 |
| `/release-notes` | 显示更新说明 | 查看新功能 |