The Claude Code course

This is a hands-on course, not a reference. Every lesson takes a problem you’ll actually hit — the agent forgets yesterday’s work, a run goes off the rails, the context window fills mid-task — and shows the exact move that fixes it: what to type, what happens, where it bites, and why it works.

If you want the spec-level “what is this primitive” view, that’s Foundations. This course is the other half: the muscle memory. You can read it start to finish to build up from zero, or drop into any lesson when a specific problem is in front of you.

All chapters live

The full curriculum is written start to finish. Read it in order to build up from zero, or jump straight to the chapter you need. Lessons may still get sharpened over time.

The curriculum

Eleven chapters, in reading order. Each is a self-contained chapter with its own running scenario — start at the top, or pick the problem in front of you.

1 · Getting started Install, authenticate, ship your first reviewed change, and put Claude Code next to the editor you already use.

2 · Sessions & context Resume work across days, reset cleanly, rescue a bad run, branch to try two approaches, and keep the context window from filling out from under you.

3 · Permissions & modes Control when Claude Code asks, run shell inline, accept edits on a leash, lock the agent out of what it shouldn't touch, and run hands-off without handing over the keys.

4 · Planning Make the agent research and propose before it builds, review the decision while it's still cheap, keep plans on disk, and hand a big one to the cloud.

5 · Rules & memory CLAUDE.md from first init to a hierarchy of project, user, and subsystem rules the agent actually follows.

6 · Models & thinking Pick the right model per task and dial reasoning up only when the problem earns it.

7 · Subagents Push noisy work into isolated context and fan out hard problems across parallel workers.

8 · Skills Package a procedure once so the agent runs it itself, every time it applies.

9 · Extending Claude Code MCP servers for external systems, hooks for deterministic gates, plugins to ship a whole setup as one unit.

10 · Automation Run headless, wire it into CI and GitHub, and build your own loops around it.

11 · Daily workflow The small habits and shortcuts that compound once the primitives are second nature.

How to read it

Each module is a chapter — not a stack of disconnected reference cards. A single running scenario flows through it — you’ll follow one real project across a week of work — and the lessons build on each other: each one picks up a problem the last one left you with, adds a move to your repertoire, and hands off to the next.

So you get the most out of a module by reading it in order, like a chapter. But each lesson still stands on its own if you drop in from a search with one specific problem in front of you — you’ll just miss the running story.

What you won’t find is a fixed template stamped onto every lesson. Some need a long worked transcript, some a single command and a warning, some a digression into why the tool behaves the way it does. The shape follows the content, the way a good book varies its chapters.