Start Here
Three guided reading paths through the guides and essays on this site. Pick one, read in order, and check off what you finish — progress stays in your browser.
New to Claude Code
0 of 7From first install to a tool that fits your hand. Set up the CLI, learn the moves that matter, then decide how it stacks up against the alternative.
-
Configuration Claude Code CLI 2026 : démarrage rapide en 5 minutes
Install the CLI, authenticate, and finish your first working session in about five minutes.
-
Claude Code Cheat Sheet
Keep this open in a tab: every command, shortcut, and flag on a single page.
-
Guide Claude Code
The complete reference. Skim the basics now, come back for the deep sections as you need them.
-
Patterns AGENTS.md : ce qui change réellement le comportement des agents
Your instructions file is the highest-leverage config you have. These patterns actually change behavior.
-
Tutoriel Hooks Claude Code : 5 hooks de production créés de zéro
Build five working hooks from scratch. This is the step from using the tool to shaping it.
-
Créer des Skills personnalisés pour Claude Code : un tutoriel complet
Package your own workflows as skills that switch on exactly when they are needed.
-
Claude Code vs Codex CLI 2026 : référence de décision
You know the tool now. See how it compares to its main rival, and when each one wins.
Agentic Engineering
0 of 7How to build, run, and trust AI agents that do real engineering work: the harness, the economics, the failure modes, and where the discipline is heading.
-
Le filtre de la preuve
Start with the working discipline: never accept “it should work” from an agent. Require proof.
-
Architecture d'agents
The complete playbook for building an agent harness: skills, hooks, memory, subagents, and orchestration.
-
Ingénierie à intérêts composés : une base de code qui accélère
Why harness work pays compound interest: each feature you ship makes the next one cheaper.
-
Loop Engineering: Loops Win Where Verification Is Cheap
The rule that decides what to automate: loops win only where checking the result is cheap.
-
Ce qui casse réellement quand vous faites tourner des agents IA sans supervision
Seven ways agents fail when nobody is watching, and the signal that catches each one early.
-
Le guide de l'opérateur d'agents : superviser ce que l'on ne voit pas
Running agents is a role of its own. What supervision looks like when you cannot read every line.
-
Les agents supplantent le relecteur, pas la relecture
Where this is heading: the reviewer role is dissolving while the review itself moves into the pipeline.
iOS with Agents
0 of 7Ship Apple-platform apps with AI agents doing the heavy lifting, from wiring Claude Code into Xcode to the on-device models your app can ship.
-
Développement d'agents iOS
The end-to-end playbook for building iOS apps with agents. Start here and branch out.
-
Deux serveurs MCP ont fait de Claude Code un système de build iOS
Wire Claude Code into Xcode so it can build, run tests, and read crash logs on its own.
-
Hooks pour le développement Apple : des patterns qui sauvent le projet
An agent working near your signing keys needs guardrails. Four patterns that bound the damage.
-
Xcode 27 passe en mode agentique
What Apple ships natively: Xcode 27's built-in agents, and where they fit next to your CLI.
-
Workflow agentique Foundation Models : LLM in-app vs outillage
Two AIs touch your app: the agent writing the code and the model shipping inside it. Keep their jobs straight.
-
Foundation Models LLM on-device : le protocole Tool
Put Apple's on-device model to work inside your app, starting with the Tool protocol.
-
Foundation Models dans iOS 27 : le contrôle de l'appel d'outils
Control how the on-device model uses tools, with iOS 27's calling modes and built-in readers.