mirror of
https://github.com/luongnv89/claude-howto.git
synced 2026-06-10 10:43:54 +02:00
Luong NGUYEN
ee0f4bd5d9
- Add comprehensive built-in commands reference (40+ commands) - Document argument handling ($ARGUMENTS, $1, $2, etc.) - Add bash execution syntax (! prefix) and file references (@ prefix) - Update frontmatter to official fields (allowed-tools, argument-hint, model, etc.) - Add Plugin Commands and MCP Slash Commands sections - Add SlashCommand Tool documentation for programmatic invocation - Add Skills vs Slash Commands comparison table - Create commit.md example with bash execution and context - Update existing examples to use official frontmatter format - Add OpenSpec proposal for change tracking
3.3 KiB
3.3 KiB
Tasks: Update Hooks Lesson
1. Content Structure Update
- 1.1 Update introduction to explain hooks as event-driven automation scripts
- 1.2 Replace hook architecture diagram with correct event flow
- 1.3 Update hook types table with all 9 official hook events
2. Configuration Format
- 2.1 Rewrite configuration section with array-based matcher/hooks structure
- 2.2 Add hook matcher documentation (exact match, regex patterns, wildcards)
- 2.3 Add timeout configuration examples
3. Hook Events Documentation
- 3.1 Document PreToolUse event (matchers, decision control, updatedInput)
- 3.2 Document PermissionRequest event (decision behavior, messages)
- 3.3 Document PostToolUse event (block decision, additionalContext)
- 3.4 Document Notification event (matchers: permission_prompt, idle_prompt, etc.)
- 3.5 Document UserPromptSubmit event (block decision, context addition)
- 3.6 Document Stop event (block continuation, stop_hook_active)
- 3.7 Document SubagentStop event (subagent completion handling)
- 3.8 Document PreCompact event (manual vs auto matchers)
- 3.9 Document SessionStart event (startup/resume/clear/compact matchers, CLAUDE_ENV_FILE)
- 3.10 Document SessionEnd event (reason field)
4. Hook Input/Output
- 4.1 Document JSON stdin input structure (session_id, transcript_path, cwd, etc.)
- 4.2 Document exit code semantics (0=success, 2=blocking error, other=non-blocking)
- 4.3 Document JSON stdout output structure (continue, stopReason, hookSpecificOutput)
- 4.4 Add examples for each hook event's specific output format
5. Prompt-Based Hooks
- 5.1 Add section on type="prompt" hooks for Stop/SubagentStop
- 5.2 Document LLM response schema (decision, reason, continue, stopReason)
- 5.3 Add practical examples of intelligent stop hooks
6. Environment Variables
- 6.1 Document CLAUDE_PROJECT_DIR usage
- 6.2 Document CLAUDE_ENV_FILE for SessionStart env persistence
- 6.3 Document CLAUDE_CODE_REMOTE for web environment detection
- 6.4 Document plugin hook variables (${CLAUDE_PLUGIN_ROOT})
7. Security Section
- 7.1 Add official security disclaimer (USE AT YOUR OWN RISK)
- 7.2 Document security best practices (input validation, quoting, path traversal)
- 7.3 Add configuration safety notes (snapshot at startup, modification warnings)
8. Advanced Features
- 8.1 Add MCP tool hook patterns (mcp____)
- 8.2 Add plugin hooks documentation
- 8.3 Add project-specific hook script examples
9. Debugging and Troubleshooting
- 9.1 Update debugging section with claude --debug flag
- 9.2 Add verbose mode (ctrl+o) documentation
- 9.3 Update troubleshooting with correct error scenarios
10. Example Scripts
- 10.1 Rewrite format-code hook to use JSON stdin
- 10.2 Rewrite security-scan hook with proper JSON input parsing
- 10.3 Rewrite bash command validator example from official docs
- 10.4 Add intelligent stop hook example with prompt type
- 10.5 Remove non-existent PreCommit/PostCommit/PrePush examples
11. Final Cleanup
- 11.1 Update Mermaid diagrams for accuracy
- 11.2 Update variable reference table to reflect JSON input
- 11.3 Update best practices table
- 11.4 Update directory structure section
- 11.5 Verify all links and references