Commit Graph

6 Commits

Author SHA1 Message Date
Luong NGUYEN 821709b143 Update all lessons 2026-01-08 23:51:46 +01:00
Luong NGUYEN 8ef1e4a0c0 docs: Update hooks lesson with improved context tracker example
- Replace simple Stop-only context-usage hook with hook pair pattern
- Add UserPromptSubmit + Stop hook combination for tracking delta
- Include both char-estimation and tiktoken versions as separate files
- Show how to use session_id for isolated state tracking
2025-12-25 18:10:16 +01:00
Luong NGUYEN 513171332e fix: correct token calculation in context-usage hook example
The hook was converting total_chars to string before calculating tokens,
resulting in ~0 tokens reported. Fixed to calculate directly from char count.

- Remove unused estimate_tokens() function
- Calculate tokens as total_chars // 4 directly
- Archive fix-context-usage-hook change
2025-12-24 23:54:35 +01:00
Luong NGUYEN 9c5c7c5049 docs: Add context usage reporter hook example
Add Example 6 showing how to create a hook that reports context/token
usage after each Claude response:

- Python script reads transcript_path to access conversation history
- Estimates tokens using ~4 chars/token heuristic
- Outputs one-line report: "Context: ~45k/200k tokens (77% remaining)"
- Documents both Stop and UserPromptSubmit hook configurations
- Explains limitations (estimate vs exact /context command)
2025-12-24 23:21:38 +01:00
Luong NGUYEN c1ef277925 docs: Rewrite hooks documentation based on official Claude Code docs
- Update configuration format to use array-based matcher/hooks structure
- Document all 9 official hook events (PreToolUse, PermissionRequest,
  PostToolUse, Notification, UserPromptSubmit, Stop, SubagentStop,
  PreCompact, SessionStart, SessionEnd)
- Add JSON stdin input/output documentation with schemas
- Document exit code semantics (0=success, 2=blocking, other=warning)
- Add prompt-based hooks for Stop/SubagentStop events
- Add environment variables (CLAUDE_PROJECT_DIR, CLAUDE_ENV_FILE, etc.)
- Add security considerations with official disclaimer
- Add MCP tool hook patterns (mcp__<server>__<tool>)
- Update example scripts to use JSON stdin parsing
- Add debugging section with claude --debug flag
- Remove incorrect hook types (PreCommit, PostCommit, PrePush)

Based on official documentation: https://code.claude.com/docs/en/hooks
2025-12-24 15:36:49 +01:00
Luong NGUYEN 5caeff2f1c refactor: Reorganize repository structure for optimal learning path
Reorder folders based on learning dependencies, complexity, and frequency of use:
- 01-slash-commands (unchanged) - Quick wins for beginners
- 02-memory (was 03) - Essential foundation
- 03-skills (was 05) - Auto-invoked capabilities
- 04-subagents (was 02) - Task delegation
- 05-mcp (was 04) - External integration
- 06-hooks (was 07) - Event automation
- 07-plugins (was 06) - Bundled solutions
- 08-checkpoints (unchanged) - Safe experimentation
- 09-advanced-features (unchanged) - Power user tools

Documentation improvements:
- Add LEARNING-ROADMAP.md with detailed milestones and exercises
- Simplify README.md for better scannability
- Consolidate Quick Start and Getting Started sections
- Combine Feature Comparison and Use Case Matrix tables
- Reorder README sections: Learning Path → Quick Reference → Getting Started
- Update all cross-references across module READMEs

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude <noreply@anthropic.com>
2025-11-09 17:54:58 +01:00