Florian BRUNIAUX
|
8a4d116e2e
|
feat(docs): add LLM Handbook + Google Whitepaper integration v3.3.0
Advanced Guardrails:
- prompt-injection-detector.sh (PreToolUse)
- output-validator.sh (PostToolUse heuristics)
- claudemd-scanner.sh (SessionStart injection detection)
- output-secrets-scanner.sh (PostToolUse secrets leak prevention)
Observability & Monitoring:
- session-logger.sh (JSONL activity logging)
- session-stats.sh (cost tracking & analysis)
- guide/observability.md (full documentation)
LLM-as-a-Judge Evaluation:
- output-evaluator.md agent (Haiku)
- /validate-changes command
- pre-commit-evaluator.sh (opt-in git hook)
Google Agent Whitepaper Integration:
- Context Triage Guide (Section 2.2.4)
- CLAUDE.md Injection Warning (Section 3.1.3)
- Agent Validation Checklist (Section 4.2.4)
- MCP Security: Tool Shadowing & Confused Deputy (Section 8.6)
- Session vs Memory patterns (Section 3.3.3)
Stats: 10 new files, 8 modified, 5 new guide sections
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
|
2026-01-14 21:00:49 +01:00 |
|
Florian BRUNIAUX
|
b2acc9b115
|
feat: add Learning Paths, examples, and project governance files
### New Content
- Learning Paths section in README (Junior/Senior/Power User/PM tracks)
- examples/ folder with 18 ready-to-use templates:
- 4 agents (code-reviewer, test-writer, security-auditor, refactoring)
- 2 skills (TDD workflow, security checklist)
- 3 commands (commit, review-pr, generate-tests)
- 4 hooks (bash + PowerShell for security, formatting)
- 3 config templates (settings, MCP, gitignore)
- 2 memory templates (project + personal CLAUDE.md)
### Governance
- CHANGELOG.md: Version history (1.0.0 → 1.1.0 → Unreleased)
- CONTRIBUTING.md: Contribution guidelines for community
### Documentation
- llms.txt: Updated structure with new files/folders
This update makes the guide more actionable with concrete templates
and provides clear learning paths for different skill levels.
Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
|
2026-01-10 14:25:22 +01:00 |
|