bd193cf73a
Added automatic verification of GitHub stars count: - Fetches actual count from GitHub API - Compares with landing index.html badge - Tolerance: ±10% or ±10 stars (whichever is larger) - Prevents future mismatches like 1.2k vs 60 Verification output example: Actual (GitHub API): 60 Landing (index.html): 60 ✓ OK (within tolerance: ±10) Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com> |
||
|---|---|---|
| .claude/commands | ||
| assets | ||
| docs/resource-evaluations | ||
| examples | ||
| exports | ||
| guide | ||
| machine-readable | ||
| quiz | ||
| scripts | ||
| tools | ||
| .gitignore | ||
| CHANGELOG.md | ||
| cheatsheet.pdf | ||
| CITATION.cff | ||
| CLAUDE.md | ||
| CODE_OF_CONDUCT.md | ||
| CONTRIBUTING.md | ||
| IDEAS.md | ||
| LICENSE | ||
| README.md | ||
| VERSION | ||
Claude Code Guide
Complete guide to Claude Code with 86 production-ready templates
⚡ Quick Start
Quickest path: Cheat Sheet — 1 printable page with daily essentials
Interactive onboarding (no clone needed):
claude "Fetch and follow the onboarding instructions from: https://raw.githubusercontent.com/FlorianBruniaux/claude-code-ultimate-guide/main/tools/onboarding-prompt.md"
Browse directly: Full Guide | Examples | Quiz
Prerequisites & Minimal CLAUDE.md Template
Prerequisites: Node.js 18+ | Anthropic API key
# 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
Save as CLAUDE.md in your project root. Claude reads it automatically.
Why This Guide?
The problem: Awesome-lists give links, not learning paths. Official docs are dense. Tutorials get outdated in weeks.
This guide: Structured learning path with 86 copy-paste templates, from first install to advanced workflows.
Reading time: Quick Start ~15 min. Full guide ~4 hours (most read by section).
By Florian BRUNIAUX | Founding Engineer @Méthode Aristote
👥 Not a Developer?
Claude Cowork is the companion guide for non-technical users (knowledge workers, assistants, managers).
Same agentic capabilities as Claude Code, but through a visual interface with no coding required.
→ Claude Cowork Guide — File organization, document generation, automated workflows
⚠️ ClawdBot vs Claude Code?
Seen the buzz about ClawdBot? It's a different tool. ClawdBot = self-hosted chatbot for messaging apps (personal automation, smart home). Claude Code = CLI for developers (terminal/IDE, code generation).
→ See FAQ for detailed comparison table and decision tree
🔧 Hitting Rate Limits or High Costs?
cc-copilot-bridge routes Claude Code through GitHub Copilot Pro+ for flat-rate access ($10/month instead of per-token billing).
# Install
git clone https://github.com/FlorianBruniaux/cc-copilot-bridge.git && cd cc-copilot-bridge && ./install.sh
# Use
ccc # Copilot mode (flat $10/month)
ccd # Direct Anthropic mode (per-token)
cco # Offline mode (Ollama, 100% local)
→ cc-copilot-bridge — Multi-provider switching, rate limit bypass, 99%+ cost savings
🎯 Learning Paths
Junior Developer — Foundation path (7 steps)
- Quick Start — Install & first workflow
- Essential Commands — The 7 commands
- Context Management — Critical concept
- Memory Files — Your first CLAUDE.md
- Learning with AI — Use AI without becoming dependent ⭐
- TDD Workflow — Test-first development
- Cheat Sheet — Print this
Senior Developer — Intermediate path (6 steps)
- Core Concepts — Mental model
- Plan Mode — Safe exploration
- Methodologies — TDD, SDD, BDD reference
- Agents — Custom AI personas
- Hooks — Event automation
- CI/CD Integration — Pipelines
Power User — Comprehensive path (7 steps)
- Complete Guide — End-to-end
- Architecture — How Claude Code works
- Security Hardening — MCP vetting, injection defense
- MCP Servers — Extended capabilities
- Trinity Pattern — Advanced workflows
- Observability — Monitor costs & sessions
- Examples — Production templates
Product Manager — Overview path (5 steps)
- What's Inside — Scope
- Golden Rules — Key principles
- Data Privacy — Retention & compliance
- Adoption Approaches — Team strategies
- PM FAQ — Code-adjacent vs non-coding PMs
Note: Non-coding PMs should consider Claude Cowork Guide instead (visual interface, no CLI).
DevOps / SRE — Infrastructure path (5 steps)
- DevOps & SRE Guide — FIRE framework for infrastructure diagnosis
- K8s Troubleshooting — Prompts by symptom
- Incident Response — Solo & multi-agent workflows
- IaC Patterns — Terraform, Ansible, GitOps
- Guardrails — Security boundaries & team adoption
Product Designer — Design-to-code path (5 steps)
- Working with Images — Image analysis basics
- Wireframing Tools — ASCII/Excalidraw workflows
- Figma MCP — Design file access & tokens
- Design-to-Code Workflow — Figma Make → Claude handoff ⭐
- Cheat Sheet — Print this
📚 What's Inside
Core Documentation
| File | Purpose | Time |
|---|---|---|
| Ultimate Guide | Complete reference (~15K lines), 10 sections | ~4 hours |
| Cheat Sheet | 1-page printable reference | 5 min |
| Architecture | How Claude Code works internally | 25 min |
| Methodologies | TDD, SDD, BDD reference | 20 min |
| Workflows | Practical guides (TDD, Plan-Driven, Task Management) | 30 min |
| Data Privacy | Retention & compliance | 10 min |
| Security Hardening | MCP vetting, injection defense | 25 min |
| Production Safety | Port stability, DB safety, infrastructure lock | 20 min |
| DevOps & SRE | FIRE framework, K8s troubleshooting, incident response | 30 min |
| Claude Code Releases | Official release history | 10 min |
Repository Structure
claude-code-ultimate-guide/
├── guide/ # 📖 Core documentation
│ ├── ultimate-guide.md # Complete reference (~15K lines)
│ ├── cheatsheet.md # 1-page printable reference
│ ├── architecture.md # How Claude Code works internally
│ ├── methodologies.md # 15 development methodologies
│ └── workflows/ # TDD, Task Management, Plan-Driven guides
│
├── examples/ # 📦 Production templates
│ ├── agents/ # Custom AI personas
│ ├── commands/ # Slash commands (/pr, /commit...)
│ ├── hooks/ # Security & automation (bash + PS)
│ ├── skills/ # Knowledge modules
│ └── scripts/ # Utility scripts
│
├── docs/ # 📚 Public documentation
│ └── resource-evaluations/ # Community resource assessments (14 files)
│
├── tools/ # 🔧 Interactive utilities
│ ├── audit-prompt.md # Setup audit
│ └── onboarding-prompt.md # Personalized guided tour
│
├── machine-readable/ # 🤖 LLM/AI consumption
│ ├── reference.yaml # Structured index (~2K tokens)
│ └── llms.txt # Standard LLM context file
│
└── quiz/ # 🧠 Interactive quiz (227 questions)
Examples Library (86 templates)
Agents (6): code-reviewer, test-writer, security-auditor, refactoring-specialist, output-evaluator, devops-sre ⭐
Slash Commands (18): /pr, /commit, /release-notes, /diagnose, /security, /refactor, /explain, /optimize, /ship...
Security Hooks (18): dangerous-actions-blocker, prompt-injection-detector, unicode-injection-scanner, output-secrets-scanner...
Skills (1): Claudeception — Meta-skill that auto-generates skills from session discoveries ⭐
Plugins (1): SE-CoVe — Chain-of-Verification for independent code review (Meta AI, ACL 2024)
Utility Scripts: session-search.sh, audit-scan.sh
GitHub Actions: claude-pr-auto-review.yml, claude-security-review.yml, claude-issue-triage.yml
Integrations (1): Agent Vibes TTS - Text-to-speech narration for Claude Code responses
Knowledge Quiz (227 questions)
Test your Claude Code knowledge with an interactive CLI quiz covering all guide sections.
cd quiz && npm install && npm start
Features: 4 profiles (Junior/Senior/Power User/PM), 10 topic categories, immediate feedback with doc links, score tracking with weak area identification.
Resource Evaluations (15 assessments)
Systematic evaluation of external resources (tools, methodologies, articles) before integration into the guide.
Methodology: 5-point scoring system (Critical → Low) with technical review and challenge phase for objectivity.
Evaluations: GSD methodology, Worktrunk, Boris Cowork video, AST-grep, ClawdBot analysis, and more.
Audit Tools
Quick scan (~2s):
curl -sL https://raw.githubusercontent.com/FlorianBruniaux/claude-code-ultimate-guide/main/examples/scripts/audit-scan.sh | bash
Deep audit with personalized recommendations: tools/audit-prompt.md
For AI Assistants (LLM-optimized)
| Resource | Purpose | Tokens |
|---|---|---|
| llms.txt | Standard context file | ~1K |
| reference.yaml | Structured index with line numbers | ~2K |
Quick load: curl -sL https://raw.githubusercontent.com/FlorianBruniaux/claude-code-ultimate-guide/main/machine-readable/reference.yaml
Alternative Formats
- DeepWiki — AI-powered Q&A
- NotebookLM Slides — Visual overview
- Kimi PDF — Full text export
🔑 Golden Rules
- Always review diffs before accepting changes — Claude suggests, you decide
- Use
/compactbefore context hits 70% — prevention beats recovery - Be specific in requests — Include WHAT, WHERE, HOW, VERIFY
- Start with Plan Mode for risky/complex tasks — read-only exploration first
- Create CLAUDE.md for every project — single source of truth
Context management is critical. See the Cheat Sheet for thresholds and actions.
🌍 About
Origins & Philosophy
This guide is the result of several months of daily practice with Claude Code. I don't claim expertise—I'm sharing what I've learned to help peers and evangelize AI-assisted development best practices.
Philosophy: Learning journey over reference manual. Understanding why before how. Progressive complexity — start simple, master advanced at your pace.
Created with Claude Code. Community-validated through contributions and feedback.
Key Inspirations:
- Claudelog.com — Excellent patterns & tutorials
- zebbern/claude-code-guide — Comprehensive reference with security focus
- ykdojo/claude-code-tips — Practical productivity techniques
External Research Tools:
Privacy & Data
Claude Code sends your prompts, file contents, and MCP results to Anthropic servers.
- Default: 5 years retention (training enabled) | Opt-out: 30 days | Enterprise: 0
- Action: Disable training | Full privacy guide
Claude Cowork (for Non-Developers)
Cowork is Claude's agentic desktop feature for knowledge workers — same AI, files-only interface.
📦 Complete Documentation Now Has Its Own Repository!
⭐ Star the repo: FlorianBruniaux/claude-cowork-guide
Quick Access (34 files, v1.0.0):
| Resource | Description |
|---|---|
| 🏠 Main Hub | Complete documentation repository |
| 🚀 Getting Started | Setup, first workflow, CTOC framework |
| ⚡ Cheatsheet | 1-page printable reference |
| ❓ FAQ | 20+ frequently asked questions |
Content:
- 📖 6 Core Guides: Overview, capabilities, security, troubleshooting
- 📝 60+ Prompts: File ops, document creation, data extraction, research
- 🔧 5 Workflows: File organization, expense tracking, report synthesis, meeting prep, team handoff
- 🎓 Interactive Onboarding: Personalized learning path
- 🛠️ 3 Scripts: Version sync, stats update, validation
Status: Research preview (Pro $20/mo or Max $100-200/mo, macOS only, VPN incompatible)
Archive: Historical versions available in git history (pre-v3.16.0)
Ecosystem & Related Resources
This Guide's Ecosystem (4 interconnected repositories):
| Repository | Purpose | Audience |
|---|---|---|
| Claude Code Guide (this repo) | Comprehensive documentation (13K lines, 82 templates) | Developers |
| Claude Cowork Guide | Non-technical usage (67 prompts, 5 workflows) | Knowledge workers |
| Code Landing (to be deployed) | Marketing site for Claude Code guide | Discovery |
| Cowork Landing (to be deployed) | Marketing site for Cowork guide | Discovery |
💡 Architecture: Separate repos for clear audience separation (devs vs non-devs), bidirectional cross-links for easy navigation.
Complementary resources:
| Project | Focus | Best For |
|---|---|---|
| claude-code-templates | Distribution - Install & use | Getting 200+ templates via CLI (17k⭐) |
| skills.sh | Skills marketplace - Discover & install | One-command skill installation (npx add-skill) from Vercel Labs |
| awesome-claude-code | Curation - Discover & link | Exploring community resources |
| Claude-Code-Everything | Visual walkthrough | Learning through screenshots |
| AI Coding Agents Matrix | Technical comparison | Comparing Claude Code vs 22+ alternatives |
AI Coding Agents Matrix (by Packmind):
- Interactive comparison: 23 AI coding agents across 11 technical criteria
- Criteria: CLI, MCP Support, Skills, Commands, Subagents, Plan Mode, AGENTS.md, and more
- Sortable/filterable matrix for precision discovery
- Open source (Apache-2.0), community-driven
- Use case: Discovery (Matrix: "Which agent has X feature?") → Mastery (This Guide: "How to use Claude Code?")
Positioning: Use Matrix to discover and compare → Choose Claude Code → Use this guide to master it.
Community: 🇫🇷 Dev With AI — 1500+ devs on Slack, meetups in Paris, Bordeaux, Lyon
Official docs: docs.anthropic.com/claude-code
Windows & Translation
Windows Users: Most commands work with Git Bash. Use %USERPROFILE%\.claude\ for paths. Report issues
Language: Written in English for wider reach. French is my native language. Request translations via issues.
🤝 Contributing
Found an error? Have a suggestion? See CONTRIBUTING.md.
Ways to Help: Star the repo • Report issues • Submit PRs • Share workflows in Discussions
📄 License & Support
Licensed under CC BY-SA 4.0. Free to share and adapt with attribution.
Stay Updated: Watch releases | Discussions | Connect on LinkedIn
Version 3.16.0 | January 2026 | Crafted with Claude