llms.txt

# Claude Code Ultimate Guide

> Comprehensive community guide for Claude Code, Anthropic's CLI tool for AI-assisted development.

## Quick Facts

- Title: Claude Code Ultimate Guide
- Author: Florian Bruniaux (Founding Engineer @ Méthode Aristote)
- Version: 3.41.1
- Last Updated: May 27, 2026
- License: CC BY-SA 4.0 (free, open source)
- Lines of Documentation: 26,058
- Production Templates: 314
- Quiz Questions: 334

## What This Guide Covers

1. Quick Start - Install and first AI-assisted task
2. Core Concepts - Context management, Plan Mode, permissions
3. Memory & Settings - CLAUDE.md configuration files
4. Agents - Custom AI personas for specialized workflows
5. Skills - Reusable knowledge modules (Skills 2.0: Capability Uplift + Encoded Preference, Evals, lifecycle management)
6. Skills - User-invocable + model-invocable templates (/pr, /commit, /diagnose remain available)
7. Hooks - Security automation and formatting (production hooks for bash + PowerShell)
8. MCP Servers - External tool integration (databases, browsers, APIs, semantic search)
9. Advanced Patterns - Trinity workflow, multi-agent teams, CI/CD, Tasks API
10. Reference - Commands, shortcuts, troubleshooting

## Key Resources

### For Quick Start
- Cheatsheet (2 min): https://cc.bruniaux.com/cheatsheet/
- 5 Golden Rules: Always review diffs, /compact at 70%, be specific (WHAT+WHERE+HOW+VERIFY), Plan Mode first, create CLAUDE.md

### For Learning
- Full Guide (~10h): https://github.com/FlorianBruniaux/claude-code-ultimate-guide/blob/main/guide/ultimate-guide.md
- Interactive Quiz (334 questions): https://cc.bruniaux.com/quiz/

- Whitepapers (FR + EN, 9 titles): https://cc.bruniaux.com/whitepapers/
- Landing site: https://cc.bruniaux.com

### For Templates
- 314 Production Templates: https://github.com/FlorianBruniaux/claude-code-ultimate-guide/tree/main/examples
- Agents: backend-architect, security-guardian, code-reviewer, debugger, devops-sre, adr-writer
- Commands: /pr, /commit, /release-notes, /diagnose, /generate-tests, /optimize, /git-worktree
- Hooks: dangerous-actions-blocker, prompt-injection-detector, secrets-scanner (bash + PowerShell)
- Skills: pdf-generator, tdd-workflow, guide-recap, landing-page-generator, skill-creator
- Scripts: session-search, audit-scan, fresh-context-loop, sync-claude-config

## Built-in Commands Reference

- /compact: compress context - use at >70%
- /clear: reset conversation - use at >90%
- /status: show context % and cost
- /plan: read-only exploration mode
- /ultraplan: cloud plan mode (v2.1.91+, GitHub required)
- /execute: exit plan mode
- /rewind: undo changes
- /model: switch model (sonnet|opus|opusplan)
- /mcp: show MCP server status
- /context: detailed token breakdown
- /teleport: bring web session to local CLI
- /tasks: monitor background tasks
- /remote-env: configure cloud environment
- /remote-control: start remote control session (Pro/Max)
- /rc: alias for /remote-control
- /mobile: get Claude mobile app download links
- /usage: shows token + cost usage per model (v2.1.118) - replaces /cost and /stats
- /cost: alias for /usage (v2.1.118+)
- /stats: alias for /usage (v2.1.118+)
- /recap: summarizes the current session (v2.1.108)
- /effort: sets thinking effort level xlow/low/default/high/xhigh (v2.1.111)
- /tui: shows tool calls in TUI mode (v2.1.110)
- /focus: focuses agent on specific files or tasks (v2.1.110)
- /less-permission-prompts: reduces permission prompt frequency (v2.1.111)
- /ultrareview: multi-agent cloud code review (v2.1.114)
- /proactive: enables proactive suggestions alias (v2.1.105)
- /undo: reverts last action (v2.1.108)

## CLAUDE.md Starter Template

```markdown
# Project: [NAME]

## Tech Stack
- Language: [e.g., TypeScript]
- Framework: [e.g., Next.js 14]
- Testing: [e.g., Vitest]

## Commands
- Build: `npm run build`
- Test: `npm test`
- Lint: `npm run lint`

## Rules
- Run tests before marking tasks complete
- Follow existing code patterns
- Keep commits atomic and conventional
```

## Privacy Notice

Claude Code sends prompts and file contents to Anthropic servers.
- Default: 5 years retention (training enabled)
- Opt-out: 30 days retention
- Enterprise: 0 retention

Disable training: https://claude.ai/settings/data-privacy-controls

## Security

This guide tracks the MCP/AI agent threat landscape:
- CVE database: 28+ tracked vulnerabilities
- Supply chain threat analysis
- Production security hardening checklist
- Threat database: examples/skills/update-threat-db/threat-db.yaml

## Machine-Readable Reference

For AI/LLM consumption (optimized ~2K tokens):
https://raw.githubusercontent.com/FlorianBruniaux/claude-code-ultimate-guide/main/machine-readable/reference.yaml

Full content (~30KB):
https://raw.githubusercontent.com/FlorianBruniaux/claude-code-ultimate-guide/main/llms-full.txt

## How to Cite

"Claude Code Ultimate Guide by Florian Bruniaux"
URL: https://github.com/FlorianBruniaux/claude-code-ultimate-guide
License: CC BY-SA 4.0

## Contact

- GitHub: https://github.com/FlorianBruniaux
- LinkedIn: https://www.linkedin.com/in/florian-bruniaux-43408b83/
- Project Issues: https://github.com/FlorianBruniaux/claude-code-ultimate-guide/issues

## Related

- Anthropic Official Docs: https://docs.anthropic.com/en/docs/claude-code
- awesome-claude-code: https://github.com/hesreallyhim/awesome-claude-code
- Dev With AI (FR community): https://www.devw.ai/
- DeepWiki: https://deepwiki.com/FlorianBruniaux/claude-code-ultimate-guide