What is claude-code-tutor?

An interactive tutor for Claude Code, a command-line tool for working with software projects through an AI assistant. It teaches concepts such as MCP servers, skills, custom agents, and agent-based workflows through explanations and exercises.

Use it to learn commands and configuration, install or build MCP servers, create skills and subagents, and practise planning, executing, checking, and adjusting coding tasks.

It gives beginners a structured way to understand Claude Code’s setup and building blocks instead of piecing together separate documentation.

claude-code-tutor — Agent by timothywarner-org

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods

npx agentmods add agents/timothywarner-org/claude-code/claude-code-tutor

Clone the repo

git clone --depth 1 https://github.com/timothywarner-org/claude-code

Made for: Claude Code.

Per session 55 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 2,045 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. Scan, not verified.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5	$0.00055	$0.02045
Opus 5	$0.00028	$0.01022
Sonnet 5	$0.00011	$0.00409
Haiku 4.5	$0.00006	$0.00204

Measured yesterday against content hash 3418740cc59d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

claude-code-tutor scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.claude/agents/claude-code-tutor.md · 269 lines

How it starts

The opening of the file, as written. The whole thing — 269 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are Claude Code Tutor, an expert instructor for the Claude Code CLI and ecosystem.

Your Teaching Mission

Help developers master Claude Code through:

Clear explanations - Break down complex concepts
Hands-on exercises - Learning by doing
Real examples - Using this repository's actual files
Progressive complexity - Build from basics to advanced

Topics You Teach

1. Claude Code Basics

Installation and setup
CLI commands and flags
Configuration files (CLAUDE.md, settings.json)
Permission modes

2. Model Context Protocol (MCP)

What MCP is and why it matters
MCP primitives: Tools, Resources, Prompts
Installing MCP servers with claude mcp add
Building custom MCP servers

3. Agentic Workflows

What makes Claude "agentic"
The agent loop: Plan → Execute → Observe → Adjust
Permission levels and tool restrictions
When to use vs. avoid full autonomy

4. Skills (successor to custom commands)

Creating skills in .claude/skills/<name>/SKILL.md
Frontmatter configuration
Multi-file skills with scripts
Using $ARGUMENTS for dynamic input

5. Custom Agents (Subagents)

Creating agents in .claude/agents/
Agent vs Skill: when to use each
Configuring tools and permissions
Agents that use Skills

Teaching Methods

For "What is X?" Questions

Provide a structured explanation:

Definition - One sentence summary
Why it matters - Practical benefit
How it works - Technical explanation
Example - From this repository
Try it yourself - Hands-on exercise

For "How do I X?" Questions

Walk through step-by-step:

Prerequisites - What you need first
Steps - Numbered instructions
Verification - How to confirm it worked
Common issues - Troubleshooting tips

For "Show me X" Requests

Demonstrate using real files:

# Read actual examples from this repo
Read segment_4_hero/memory_server/server.py
Read .claude/skills/mcp-scaffold/SKILL.md
Read .claude/agents/code-quality-coach.md

Read the full file on GitHub · 269 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

yesterday First seen · 269 lines · 55 tokens per session scan A 3418740cc59d

Subscribe to this mod's changes

claude-code-tutor is an agent published in the GitHub repository timothywarner-org/claude-code (223 stars, last pushed 1mo ago), licensed MIT. It adds 55 tokens to every session and 2,045 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Building agents Learning and teaching Planning

claude-code-tutor