Course catalog
Drive the terminal agent with its own commands, files, and config.
Claude Code is an agent that lives in your terminal, and most of what makes it good at your codebase is configuration you write yourself. This course teaches the product concretely: the install, the session UI, `@` file refs and `#` memory lines, the slash commands you reach for daily, and the four files that shape everything — CLAUDE.md, `.claude/settings.json`, `.claude/commands/*.md`, and `.claude/agents/*.md`. You'll add MCP servers, install skills, wire hooks that always run, and drive git and pull requests from a session. It closes with headless runs in CI, rewind, and the context hygiene that keeps a long session cheap.
Section 1
Install Claude Code, launch it in the right directory, read what the screen is telling you, and learn the handful of keys and commands you reach for every day.
Section 2
Teach Claude Code how this repository works: concise CLAUDE.md guidance, enforceable settings, reusable Skills, and a read-only planning mode.
Eligible first-time members can get 7 free days · Cancel anytime
Get startedSection 3
Choose the right extension surface: isolated subagents and worktrees, discoverable Skills, external MCP tools, and deterministic Hooks.
Section 4
Review and ship agent work with independent evidence: inspect diffs, automate bounded runs, recover safely, and manage context deliberately.