Skip to main content
Code Guide

Master Claude Code

Learn the WHY behind Claude Code, not just the config

Security-first (15 vulnerabilities tracked) • TDD/SDD/BDD workflows • 204 templates • 271-question quiz • Decision frameworks

stars 101 templates 204 quiz 271 questions awesome featured mcp npx ready
Personalized Learning

Start With Interactive Onboarding

Claude asks 2-4 questions about your profile, then guides you through personalized content

1

Choose your language
English or French

2

Select your goal
Learn, audit setup, or explore

3

Pick your level
Junior, Senior, or Power User

4

Get personalized path
Curated content for you

Three tools. One subscription.

Claude AI, Claude Code, and Claude Cowork solve different problems. Here's how to pick yours.

claude.ai

Claude AI

You write, think, search.

Generalist conversational assistant. Zero config, multimodal, available on web and mobile.

📝 Writing & editing
💡 Brainstorming
🔍 Research & synthesis
✓ Zero setup, works instantly
✓ Multimodal (images, PDFs, voice)
✗ No system access
✗ Limited memory between sessions
Ideal for Writer · Consultant · Student · Manager
Desktop app · macOS

Claude Cowork

You automate without code.

Agentic desktop app for knowledge workers. Accesses local folders and apps — no terminal required.

🗂️ Bulk file organization
📊 PDF → spreadsheet extraction
🔄 Cross-app workflows
✓ No code required
✓ Works with your existing apps
✗ macOS only, still in beta
✗ Limited customization
Ideal for Ops · Assistant · SMB non-tech
💡 These three tools are complementary, not competing. All included in the $20/mo Pro plan.

Why This Guide?

Claude Code transforms your terminal into an AI pair programming environment. Stop wasting time on trial and error.

Claude Code Architecture: AI Models (Opus, Sonnet) connect through Claude Code's orchestration layer to your code environment via File Editing, Command Execution, and Repo Navigation
Key insight: Claude Code is NOT a new AI model: it's an orchestration layer connecting Claude to your dev environment.
Diagram by Mohamed Ali Ben Salem

Without the Guide

  • Generic prompts that miss context
  • Default config leaving performance on the table
  • Debugging by trial and error
  • Scattered tutorials, outdated in weeks
  • No clear learning progression

With the Guide

  • Battle-tested prompt patterns
  • Optimized CLAUDE.md configurations
  • Proven methodologies (TDD, SDD, BDD)
  • Decision frameworks (agents vs skills vs hooks — when to use what)
  • 22,000+ lines of curated, maintained content
  • Clear path from beginner to power user

The Prompt Formula

Structure your prompts for better results

WHAT Concrete deliverable
WHERE File paths
HOW Constraints, approach
VERIFY Success criteria

Example

Add input validation to the login form.
WHERE: src/components/LoginForm.tsx
HOW: Use Zod schema, show inline errors
VERIFY: Empty email shows error message

Whitepapers & Fiches Récap

10 whitepapers + 11e (budget IA) sur les thèmes stratégiques Claude Code — format PDF court et dense

11 whitepapers FR + EN
  • WP00 Introduction & Fondamentaux
  • WP01 Prompts Efficaces
  • WP02 Personnalisation & Configuration
  • WP03 Sécurité en Production
  • WP04 Architecture Interne
  • WP05 Adoption en Équipe
  • WP06 Privacy & Conformité
  • WP07 Guide de Référence Condensé
  • WP08 Agent Teams & Sub-Agents
  • WP09 Apprendre avec l'IA — UVAL
  • WP10 Budget & ROI de l'IA
NEW Fiches Récap

10 fiches récap A4 — 1 fiche par whitepaper, format synthèse ultra-dense. Imprimables, prêtes à l'emploi.

  • Format A4 1 page par fiche
  • Synthèse des concepts clés
  • Exemples et commandes intégrés
  • Palette Bold Guy (PDF haute qualité)
Télécharger les PDFs →

MCP in Action

Query the guide directly from Claude Code. Real outputs, live search, source links on every result.

install npx -y claude-code-ultimate-guide-mcp

Guide changes + Claude Code CLI releases for the past 7 days, with GitHub/site links on every resource.

/ccguide:digest week
# Digest — 7 derniers jours (22-28 fév 2026)

## Claude Code CLI — Releases

v2.1.59 (26 fév) — Auto-memory natif (/memory), /copy avec picker
                    interactif, fix race condition MCP OAuth
v2.1.58 (26 fév) — Remote Control élargi à plus d'utilisateurs
v2.1.56 (25 fév) — Fix crash VSCode Windows
v2.1.53 (25 fév) — Stability batch : panics Windows, WebAssembly
                    crashes, fix Remote Control stale sessions
v2.1.51 (24 fév) — claude remote-control subcommand, SDK env vars,
                    /model labels lisibles

Release notes : https://github.com/FlorianBruniaux/claude-code-ultimate-guide
                /blob/main/guide/claude-code-releases.md

---
## Guide — Changements majeurs

- Remote Control (§9.22) — workflow QR/URL/app, tmux multi-session,
  limitations slash commands, architecture sécurité
- Terminal Personalization (§3.3) — spinnerVerbs, spinnerTipsOverride,
  113+ tips en 13 catégories
- MLflow Tracing (observability.md) — CLI zero-Python, LLM-as-judge
- Threat Database v2.1.0 → v2.2.0 : CVE-2026-0755 (CVSS 9.8, RCE),
  SNYK mcp-run-python SSRF, technique T010 agent-to-agent injection

---
## Resources mentionnées

- examples/config/settings-personalization.json
  https://github.com/FlorianBruniaux/...
- guide/observability.md
  https://github.com/FlorianBruniaux/... | https://cc.bruniaux.com/guide/observability
- examples/hooks/bash/security-gate.sh
  https://github.com/FlorianBruniaux/...
- examples/agents/security-patcher.md
  https://github.com/FlorianBruniaux/...

204 production-ready templates — agents, commands, hooks, skills, scripts — with direct GitHub links.

/ccguide:examples
# Claude Code Ultimate Guide — Templates
GitHub: https://github.com/FlorianBruniaux/claude-code-ultimate-guide/tree/main/examples

## Agents (6)

code-reviewer.md         → Review Anti Hallucination
planner.md               → Planner Agent
implementer.md           → Implementer Agent
architecture-reviewer.md → Architecture Reviewer Agent
devops-sre.md            → Devops Agent
security-patcher.md      → Security Patcher Agent

## Commands (15)

review-pr.md             → Review PR Advanced
review-plan.md           → Review Plan Command
quiz.md                  → Learn Quiz Command
audit-agents-skills.md   → Audit Agents Skills Command
git-worktree.md          → Git Worktree Command
security-check.md        → Security Check Command
security-audit.md        → Security Audit Command
update-threat-db.md      → Update Threat DB Command
... +7 more

## Hooks (6)

rtk-auto-wrapper.sh      → RTK Auto Wrapper
learning-capture.sh      → Learning Capture Hook
pre-commit-secrets.sh    → Pre-Commit Secrets Hook
security-gate.sh         → Security Gate Hook
tts-selective.sh         → TTS Hook Example
sandbox-validation.sh    → Sandbox Validation Hook

## Skills (17)

Talk pipeline complet (orchestrateur + 6 stages), pdf-generator,
rtk-optimizer, audit-agents-skills, voice-refine, design-patterns,
ast-grep-patterns...

## Scripts (5)

session-search.sh  · cc-sessions.py  · bridge.py
sync-claude-config.sh  · bridge-plan-schema.json

---
Pour récupérer un template : /ccguide:example <nom>
ex: /ccguide:example security-gate

893 entries across 25 categories — browse the full index before diving into specific sections.

/ccguide:topics
# Claude Code Ultimate Guide — 893 indexed entries, 25 categories (v3.34.2)

┌────────────┬─────────┬───────────────────────────────────────────────┐
│ Category   │ Entries │ Examples                                       │
├────────────┼─────────┼───────────────────────────────────────────────┤
│ deep       │     740 │ Mermaid diagrams, exploration workflow,        │
│            │         │ script generation, anti-anchoring prompts,     │
│            │         │ session limits                                  │
├────────────┼─────────┼───────────────────────────────────────────────┤
│ mcp        │      61 │ Serena, claude-mem, plugin, repo, guide        │
├────────────┼─────────┼───────────────────────────────────────────────┤
│ onboarding │      33 │ Matrix meta, changelog, get started (5min)     │
├────────────┼─────────┼───────────────────────────────────────────────┤
│ ecosystem  │      27 │ This guide, MCP server npm/install/readme      │
├────────────┼─────────┼───────────────────────────────────────────────┤
│ hooks      │       7 │ Execution model, async, use cases, matrix      │
├────────────┼─────────┼───────────────────────────────────────────────┤
│ agent      │       4 │ Template, official fields, memory scopes       │
├────────────┼─────────┼───────────────────────────────────────────────┤
│ context    │       3 │ Zones, fresh context, symptoms                 │
└────────────┴─────────┴───────────────────────────────────────────────┘

Single-entry categories:
updated · decide · prompt · workflow · commands · shortcuts · cli
memory · folder · permissions · architecture · cost · tools · debug
hook · rules

---
Usage:
  /ccguide:search hooks
  /ccguide:search mcp serena
  /ccguide:search agent memory

Latest Claude Code CLI release notes, tracked and condensed. Pass a version for a specific entry.

/ccguide:release
# Claude Code Releases
Latest: v2.1.59 (updated: 2026-02-26)
https://github.com/FlorianBruniaux/.../guide/claude-code-releases.md

---
v2.1.59 — 26 fév 2026

- Auto-memory : Claude sauvegarde automatiquement le contexte utile,
  gérable via /memory
- /copy : picker interactif pour copier un bloc ou la réponse complète
- Suggestions "always allow" plus intelligentes pour les commandes
  bash composées (prefixes par sous-commande)
- Fix : race condition MCP OAuth token refresh avec plusieurs instances
- Fix : corruption du fichier config effaçant l'auth multi-instances

v2.1.58 — 26 fév 2026
- Remote Control élargi à plus d'utilisateurs

v2.1.56 — 25 fév 2026
- VSCode : fix crash "command claude-vscode.editor.openLast not found"

v2.1.55 — 25 fév 2026
- Fix BashTool EINVAL sur Windows

v2.1.53 — 25 fév 2026
- Stability batch : panics Windows, crashes process spawn, WebAssembly
- Fix Remote Control : sessions stale après graceful shutdown
- Fix UI flicker, kill agents en masse (ctrl+f)

---
76 releases trackées au total.
Pour une version spécifique : /ccguide:release 2.1.51

Browse 28 CVEs and 14 attack techniques from the threat database. Look up any CVE or T-code for full details, mitigations, and sources.

get_threat / list_threats
# Threat Database Summary
Version 2.4.0 — updated 2026-02-28
https://github.com/FlorianBruniaux/.../threat-db.yaml

| Category              | Count |
|-----------------------|-------|
| CVEs                  |    28 |
| Malicious Authors     |     6 |
| Malicious Skills      |   655 |
| Attack Techniques     |    14 |
| Minimum Safe Versions |    12 |
| Research Sources      |    23 |

--- get_threat("CVE-2025-53109") ---

# CVE-2025-53109 — Filesystem MCP Server
Severity: HIGH | Source: Cymulate EscapeRoute

## Description
Symlink escape to arbitrary filesystem access / potential LPE

Fixed in: 0.6.3 / 2025.7.1

## Mitigation
Update to >= 0.6.3; avoid Filesystem MCP in sensitive environments

--- get_threat("T001") ---

# T001 — Tool Poisoning via SKILL.md
## Description
Hidden instructions in SKILL.md that instruct the agent
to run malicious commands.

## Examples
- curl | bash from glot.io scripts
- Password-protected ZIP with embedded malware
- Base64-decoded eval commands

Campaigns: ClawHavoc, ToxicSkills
Mitigation: Scan SKILL.md for shell commands;
            never auto-execute prerequisites

8 shortcuts /ccguide:* — one keystroke to search, fetch templates, get the digest, or browse the cheatsheet.

Slash commands
# Slash commands /ccguide:*

Copy once to ~/.claude/commands/ccguide/ → available in every project.

┌──────────────────────────┬────────────────────────────────────────────────┐
│ Command                  │ What it does                                   │
├──────────────────────────┼────────────────────────────────────────────────┤
│ /ccguide:search <query>  │ Search 893 indexed entries with scores + links │
│ /ccguide:digest <period> │ Guide + CC CLI changes (day/week/month)        │
│ /ccguide:examples        │ List all 204 templates by category             │
│ /ccguide:example <name>  │ Fetch a template (agent/hook/command/skill)    │
│ /ccguide:cheatsheet      │ Full cheatsheet or filtered by section         │
│ /ccguide:release         │ Latest Claude Code CLI release notes           │
│ /ccguide:changelog       │ Last N CHANGELOG entries from the guide        │
│ /ccguide:topics          │ Browse 25 topic categories (893 entries)       │
└──────────────────────────┴────────────────────────────────────────────────┘

Install:
  cp -r .claude/commands/ccguide ~/.claude/commands/ccguide

Examples:
  /ccguide:search hooks
  /ccguide:digest week
  /ccguide:example code-reviewer
  /ccguide:cheatsheet memory
  /ccguide:release 2.1.59

Onboarding one-liner (after install):
  claude "Use the claude-code-guide MCP. Activate claude-code-expert
  prompt, ask me 3 questions about my goal and level, build a
  personalized learning path with search_guide + read_section."

5 Golden Rules

Data-driven principles for working safely and effectively with AI code generation

1

Verify Trust Before Use

AI-generated code contains 1.75x more logic errors than human code (ACM 2025). Test everything, peer review AI output like you would a junior dev's PR.

1.75x more logic errors ACM 2025
2

Never Approve MCPs from Unknown Sources

15 vulnerabilities tracked, 655 malicious skills detected in the wild. Use the 5-minute audit checklist before installing any MCP server.

15 vulnerabilities 655 malicious skills
3

Context Pressure Changes Behavior

At 70% context usage, Claude starts losing precision. Run /compact at 70%, /clear at 90%. Monitor with /status.

70% = precision loss /compact at 70%
4

Start Simple, Scale Smart

2-week test period before scaling. 4-phase adoption: solo tasks, multi-file work, agents, then CI/CD integration. Work through each phase, don't skip ahead.

2-week test period 4-phase adoption
5

Methodologies Matter More with AI

AI amplifies good code AND bad code. TDD for critical logic, SDD for architecture-first, BDD for PM/dev collaboration. Choose by context, not by habit.

TDD / SDD / BDD Choose by context

Secure Your Setup

36.82% of AI agent skills have measurable security flaws. Understand the threat landscape before it becomes your problem.

534
Critical-Risk Skills
15
Vulnerabilities Tracked
655
Malicious Skills
Supply Chain Attacks
Malicious MCP servers on PyPI & npm with embedded reverse shells
Credential Theft
Skills that read .env files and POST secrets to attacker webhooks
Prompt Injection
Hidden instructions in SKILL.md that hijack agent behavior

Claude Code vs GitHub Copilot vs Cursor

How does this AI coding assistant compare to alternatives?

Feature Claude Code GitHub Copilot Cursor
Interface Terminal CLI IDE Extension Full IDE (VS Code fork)
Agentic Mode Multi-file, autonomous Agent Mode (VS Code) Composer mode
Context Window 200K tokens (up to 1M) 64K-128K tokens 32K-200K tokens
Project Memory CLAUDE.md files ~ Repo embeddings .cursorrules
Custom Agents Agent SDK + Skills ~ MCP configs ~ MCP integrations
MCP Integration Native client/server Via Agent Mode Docs integration
Shell Execution Native terminal Agent Mode Integrated
Hooks System Event-driven hooks
Best For Terminal power users, automation IDE-integrated coding Visual IDE users

Each tool has its strengths. Claude Code excels at autonomous multi-file operations and deep code generation from the terminal. This guide helps you master its unique capabilities.

Community & Resources

Contribute to the Guide

The guide repo is open-source. Found an error? Have a better template?

Contributing Guide →

Star on GitHub

If this guide saved you time, show your support.

GitHub Repository →
Florian BRUNIAUX - Claude Code Guide author, Founding Engineer at Methode Aristote

By Florian BRUNIAUX

Founding Engineer @ Methode Aristote

11+ years in tech as CTO, VP Engineering & Founding Engineer. Fullstack developer (TypeScript, Ruby, Python) with a passion for solving problems through technology. Leadership driven by transparency, building teams with loyalty, ambition & benevolence.