The Claude Code Handbook

Most people use Claude Code the way they’d use autocomplete: type a request, take what comes back, move on. That works, and it leaves most of the tool on the table.

This handbook is the other path. Twenty-three chapters, worked end to end, on how Claude Code actually behaves — what it’s allowed to do and why, what it remembers and what it forgets, how to hand it new abilities, how to make it obey rules it cannot ignore, and how to run several of it at once without the whole thing collapsing into noise.

Every chapter stands alone. Read top to bottom and you’ll finish an expert.

Part 1 — Foundations

What the thing is, how you talk to it, and how to stop it doing something you’ll regret.

  1. What Claude Code Actually Is — the execution model: a text-to-text model with no I/O, the harness that supplies tools, the gather/act/verify loop, the full tool table, and session state on disk.
  2. Three Ways to Talk to Claude Code — the three input channels, a full flag and command reference, shell-mode semantics and its cost change in v2.1.186, input handling, and voice dictation.
  3. Permission Modes — the six modes and what each auto-approves, the auto-mode classifier’s block and allow lists, its 3-in-a-row circuit breaker, and the protected and critical paths no mode will approve.
  4. Permissions & Sandboxing

Part 2 — Context Engineering

The context window is the budget everything else spends. This part is about spending it well.

  1. Settings: the Control Panel
  2. CLAUDE.md
  3. Rules & Auto Memory
  4. The Context Window
  5. Sessions, Checkpoints & Rewind

Part 3 — Teaching Claude New Tricks

Turning your preferences into capabilities, and your hopes into guarantees.

  1. Output Styles
  2. Skills
  3. Hooks
  4. Plugins & Marketplaces

Part 4 — Connecting Claude to the World

Claude knows your code. This part is about everything else it needs to know.

  1. MCP Fundamentals
  2. MCP in Practice
  3. GitHub, GitLab & CI

Part 5 — Agents & Autonomy

One agent is a pair programmer. Several are a team.

  1. Sub-Agents
  2. Agent Teams & Parallel Work
  3. Automation & Scheduling
  4. Claude Code Everywhere

Part 6 — Running It for Real

What it costs, how it’s secured, and what to do at 2am when it won’t behave.

  1. Cost, Monitoring & Security
  2. When It Goes Wrong

Closing

  1. Becoming an Expert

How to read this handbook

Read the first section of a chapter, then stop and try the thing on your own project before continuing. Every chapter has something you can run in under a minute.

Every diagram opens full screen — click it, then scroll or pinch to zoom. Every chapter with an interactive piece is meant to be played with rather than read past; that’s usually where the idea actually lands.

Chapters are verified against the official documentation as they’re written. Where the docs and this handbook disagree, the docs win — and I’d like to know, so tell me.