Skip to main content
Editorial content

All our articles

Explore our editorial guides in MDX format. Each article is self-contained and can be read independently.

Les articles éditoriaux du Claude Codex sont des guides autonomes qui traitent chacun d'un sujet précis. Contrairement aux pages de documentation structurées par section (MCP, Skills, Prompting), ces contenus abordent des thèmes transversaux : sécurité, coûts réels, bonnes pratiques et mythes à déconstruire.

Chaque article est rédigé pour être lu en 5 à 15 minutes. Vous pouvez les lire dans n'importe quel ordre. Si vous débutez, commencez par "Qu'est-ce que Claude Code" dans la section Démarrer, puis revenez ici pour approfondir les sujets qui vous intéressent.

Articles

Available guides

Click an article to read it. Content is sorted by progression order.

Discovery

Getting started with Claude Code

Complete guide to get started with Claude Code: from installation to your first project. Everything you need to know to begin with Anthropic's AI assistant.

MCP

Complete MCP guide

Complete guide to the Model Context Protocol (MCP): understand, install, and use MCP servers with Claude Code. From basics to advanced usage.

Skills

Claude Code Skills: complete guide (concept, create, examples)

Everything about Claude Code Skills: concept, step-by-step creation, real examples, official library. Automate your workflows and teach new talents to Claude.

Prompting

Prompting guide

Complete guide to prompting with Claude Code: learn to write effective prompts, master communication techniques, and get the best results from AI.

Vision

Vision and future of Claude Code

The future of Claude Code and AI-assisted development: upcoming features, industry trends, and how to prepare for the future of programming.

Budget

The real costs of Claude Code

Transparent analysis of Claude Code costs: subscriptions, API pricing, hidden costs, and tips to optimize your spending. Make an informed choice.

Truth

Myths and misconceptions about Claude Code

Debunking the most common myths about Claude Code: what it really can and can't do, realistic expectations, and honest answers.

Security

Claude Code Security: 8 best practices + copy-paste checklist

Least privilege, MCP vetting, sandboxed config profiles, secrets scanning: 8 best practices with a ready-to-use checklist to secure Claude Code in teams.

Security

Leaked Anthropic API key? Step-by-step recovery (2026)

Your Anthropic API key sk-ant was leaked in a commit, screenshot, or log? Revoke it now, rotate it, audit the damage. Step-by-step recovery guide.

New

Claude Design vs Figma: who wins the AI design race in 2026?

Claude Design (Anthropic Labs, April 2026) takes on Figma AI directly. Honest comparison: conversation vs canvas, iteration, brand system, dev handoff.

Security

Never give Claude Code your API keys or vault files: what can actually go wrong

Sharing an API key or vault file with Claude Code can lead to exfiltration, log leaks, or public commits. Practical guide to proper isolation.

Security

CI/CD and cybersecurity in 2026: why it's now non-negotiable with AI agents

With the explosion of AI-generated code, a robust CI/CD is no longer a bonus: it's the defense line. Practical guide with Red Team, Blue Team and Purple Team.

Understanding Claude Code internals through leaks

What leaked system prompts reveal about Claude Code's internal architecture, and what we can transfer to write sharper CLAUDE.md files and skills.

Garry Tan's gstack: a critical review after one month of use

Critical review of Garry Tan's Claude Code stack (YC CEO). 35 commands, solo-founder philosophy, what works and what falls flat outside SF.

Karpathy-Style CLAUDE.md: Analysis and FR Adaptation

A close read of the so-called Karpathy CLAUDE.md: four principles against Claude Code drift, what transfers to a team setting, and a ready-to-paste French template.

GUIDE

Plan mode vs Thinking mode in Claude Code: the key differences

Plan mode makes Claude propose a plan before touching code. Thinking mode makes Claude reason longer internally. Two distinct levers, two different goals.