Meet Pip
Claude Code Quest opens in your browser, beside your terminal. Read a step, try it in Claude Code, and the app checks your work. When it passes, Pip cheers.
Do a step, and when it passes, Pip cheers with you.
Miss one, and he encourages you to try again. The help fades as you get the hang of each skill, from every command, to hints, to only the goal, until you do it on your own.
Try it now
You need a Claude subscription (Pro, Max, Ultra, Team or Enterprise), a Claude Console account, or access through a supported cloud provider (Quickstart), plus Node.js LTS and git.
-
Make your practice copy. Open claude-code-practice, select Use this template > Create a new repository, and clone your copy. Or open your copy in a Codespace.
-
Start the app in your copy:
npm run learn
-
Keep a terminal beside it. Claude Code Quest opens in your browser (in a Codespace, open the address it prints). It tells you what to type in the terminal and checks each step.
Claude Code Quest has no AI in it and changes none of your work. Prefer to read? Every lesson works from its page alone.
Already have a practice copy?
If you made your copy before the app moved to the browser, run these in your copy’s folder, in a terminal or in PowerShell. The fetch saves the template’s latest version as FETCH_HEAD, and --no-overlay replaces checks/, capstone/ and learn/ as wholes:
git fetch https://github.com/wesammustafa/claude-code-practice main
git checkout --no-overlay FETCH_HEAD -- checks capstone learn
git checkout FETCH_HEAD -- .github/workflows/progress.yml .gitattributes
node checks/upgrade.mjs
The template’s progress.yml workflow and .gitattributes replace yours. Your work moves into project/, with every file’s contents kept (an untracked file left in checks/, capstone/ or learn/ moves to .practice/upgrade-kept/), and your saved progress stays where it is, so npm run learn opens where you left off. Run checks from project/ now: cd project, then npm run check -- b-1. Review the change with git status, then commit it.
Pick your level
Three levels take you from your first session to a setup your team shares. Start where you are and climb: every core lesson earns a Badge, and each level ends with a capstone that puts it all together. Not sure where you fit? Each level page opens with a “You’re ready for this level if you can” list.
Beginner
Start here if you’re new to Claude Code.
You’ll learn to start Claude Code safely, plan before it changes things, take one change from request to commit, and give your project a memory.
You’ll finish by fixing a reported bug, from plan to commit.
Badges: Explorer · Planner · Builder · Navigator · Keeper · Beginner
5 lessons · a capstone · 3 Electives · about 2½ hours
Start Beginner
Start here if you can do what Beginner teaches.
You’ll learn to shape Claude Code to your own project with skills, memory, permissions, hooks, subagents, MCP servers and plugins.
You’ll finish by getting a repository ready for a new teammate.
Badges: Crafter · Organizer · Tuner · Guardian · Enforcer · Delegator · Connector · Curator · Intermediate
8 lessons · a capstone · 4 Electives · about 4 hours
Start Intermediate
Advanced
Start here if you can do what Intermediate teaches.
You’ll learn to run sessions in parallel, run Claude Code unattended in scripts and CI, share a setup with your team, and keep autonomous runs within limits you set.
You’ll finish by adding CI review your team can share.
Badges: Brancher · Strategist · Orchestrator · Scripter · Automator · Steward · Warden · Advanced
7 lessons · a capstone · 5 Electives · about 4 hours, plus run time
Start Advanced
Finish a level, and Pip throws a party.
Everything in the guide
Every page, by level
Beginner: Level index · Install, sign in and look around · Permission modes and plan mode · Your first change, from request to commit · Keep a session on track · Project memory with CLAUDE.md · Capstone
Beginner Electives: IDE extensions · Screenshots and images · The built-in teachers
Intermediate: Level index · Turn a repeated workflow into a skill · Organize project memory and see what loaded · Pick the model and effort · Permissions, settings scopes and the sandbox · Enforce a rule with a hook · Delegate to a custom subagent · Connect a tool with MCP · Install and manage plugins · Capstone
Intermediate Electives: Skill patterns · Claude in Chrome · The status line · Fast mode
Advanced: Level index · Parallel sessions with worktrees · Choose an orchestration pattern · Run and save a dynamic workflow · Script Claude Code with claude -p · GitHub Actions · Share your setup with a team · Put bounds on autonomous runs · Capstone · Beyond this guide
Advanced Electives: Agent teams · Agent view · /loop and cloud scheduled tasks · Testing and publishing a plugin · Dev containers
Topics: All topics · Permissions and safety · Memory and context · Models, effort and cost · Skills · Hooks · Subagents and parallel work · MCP · Plugins · Automation
Reference: Reference index · Models and effort · Commands by level · Feature map · Further learning · Glossary · Changelog
Examples: How to use the examples
How the guide stays current
- Every lesson page carries a Stamp: the Claude Code
stable version its claims were checked against, and the date (The stamp).
- The checks are tested too: CI builds a fresh practice copy from this repo and shows every check failing on it and passing after a full replay of the lessons (Guide checks).
- Scheduled checks keep watch between editions: external links and new
stable releases weekly, and expiry markers daily. Each opens a tracking issue (Maintainer routine).
- The examples are inert until you copy them into a project, and they follow a safety contract: local only (apart from the MCP lesson’s pinned server), least privilege, and a smoke test that runs without Claude.
Followed a link from an earlier edition?
The previous edition’s README sections moved:
评论