Learn Claude Code by configuring and driving it. Each lesson is a command you run, a key you press, or a file you save — CLAUDE.md, custom commands, skills, subagents, hooks, MCP servers, and automation.
Prerequisites
None are strictly required, but these make the lessons land faster:
Before you start
You will install Claude Code and run it against a real project, so have a terminal and a code repository handy. Install instructions are in the Claude Code docs, and the first lesson walks you through it.
Set Up Claude Code
Install Claude Code, sign in, and run your first session inside a real project. This is the workspace every other lesson builds on.
Driving Claude Code from the CLI
Claude Code is more than an interactive chat — learn the flags that resume past work, pipe it into scripts, and point it at extra folders.
Slash Commands & Shortcuts
The prompt is a control surface. Learn the slash commands and keyboard shortcuts that steer a session — clearing context, rewinding, switching modes, and dropping into bash.
CLAUDE.md: Project Memory
CLAUDE.md is the file Claude reads at the start of every session. Write one so Claude knows your commands, conventions, and guardrails without being told each time.
Plan Mode & Permissions
Control what Claude can do before it does it. Use Plan Mode to review an approach first, and permission rules to pre-approve safe actions while gating risky ones.
Managing Context & Sessions
The context window is finite and you pay for it. Learn to keep sessions lean — compact, clear, rewind, and watch your usage so Claude stays sharp and cheap.
Choosing Models, Thinking & Effort
Match the model to the job. Learn when to reach for Opus, Sonnet, or Haiku, what Opusplan does, and how to ask Claude to think harder on tricky problems.
Custom Slash Commands
Turn a prompt you keep retyping into a reusable command. Save a markdown file and it becomes a /command you and your team can run with arguments.
Skills
Skills teach Claude a repeatable capability — a workflow, a format, a set of best practices — that it loads only when relevant. Build one and watch Claude use it on its own.
Subagents
A subagent is a focused helper with its own prompt, tools, and context window. Build one so Claude can delegate work — like code review — without cluttering the main thread.
Hooks
Hooks run your own shell commands at fixed points in Claude's lifecycle — before a tool, after an edit, when a session starts. Use them to format, guard, and automate deterministically.
Connecting Tools with MCP
MCP lets Claude Code use external tools — your database, GitHub, a browser, internal APIs. Add a server and its tools become available right inside your session.
Customizing the Experience
Make Claude Code yours — change how it talks with output styles, show live info in the status line, and install bundles of commands, agents, and hooks as plugins.
Headless Mode & Automation
Run Claude Code without the interactive UI so you can script it — in CI, in git hooks, across parallel worktrees. Print mode plus JSON output makes Claude a building block.
Security Best Practices
Claude Code edits files and runs commands, so treat it like any powerful tool. Lock down permissions, keep secrets out, guard with hooks, and be careful with untrusted input.