Claude Code Guide: Complete Tutorial & Best Practices

The comprehensive guide to Claude Code — Anthropic's AI coding assistant CLI. From installation to advanced MCP servers, agents, skills, hooks, and CI/CD integration.

Author: Florian BRUNIAUX | Founding Engineer @Méthode Aristote

Contact: LinkedIn

Written with: Claude (Anthropic)

If you find this guide useful, please consider giving it a star! It helps others discover this resource and motivates continued updates.

---

About This Guide

This guide is the result of several months of daily practice and research with Claude Code, Anthropic's AI coding assistant CLI. Whether you're exploring agentic development, LLM-powered coding workflows, or AI pair programming, this resource covers everything from basic setup to advanced MCP server orchestration.

I don't claim to be an "expert" — I'm simply sharing what I've learned along the way, humbly hoping to help my peers and evangelize good practices in AI-assisted development.

A significant source of inspiration for this work was Claudelog.com, which I highly recommend for anyone wanting to go deeper.

Important note: This guide was largely generated with the help of AI. As such, it likely contains errors, inaccuracies, or outdated information. I would be delighted to receive any feedback, corrections, or — even better — pull requests to improve it. Don't hesitate to open an issue or submit a PR!

Windows disclaimer: I work on macOS and have not tested the Windows-specific commands (PowerShell, batch files, paths). Windows instructions were generated with AI assistance. If you encounter issues, please open an issue or PR — contributions from Windows users are especially welcome!

Language: I wrote this guide in English by default to reach a wider audience, but French is my native language. I could easily translate it to French myself, or leverage AI and community contributions for other languages. Let me know if translations would be useful!

If you find value in this guide, have questions, or want to discuss Claude Code practices, feel free to reach out on LinkedIn.

---

What's Inside

File	Description	Reading Time
english-ultimate-claude-code-guide.md	Complete guide (4000+ lines)	~2.5 hours
cheatsheet-en.md	1-page printable daily reference	5 minutes
claude-setup-audit-prompt.md	Self-audit prompt for your setup	~10 minutes
claude-code-ultimate-guide_notebooklm.pdf	Audio Deep Dive (NotebookLM podcast)	~1 hour
claude-code-ultimate-guide_kimi.pdf	PDF version (Kimi export)	~2.5 hours

---

Table of Contents

Jump directly to any section in the full guide:

#	Section	Description
1	Quick Start	Installation, first workflow, essential commands
2	Core Concepts	Context management, Plan Mode, Rewind, Mental Model
3	Memory & Settings	CLAUDE.md files, .claude/ folder, precedence rules
4	Agents	Custom AI personas, Tool SEO, orchestration patterns
5	Skills	Reusable knowledge modules (Security, TDD...)
6	Commands	Custom slash commands, variable interpolation
7	Hooks	Event-driven automation (security, formatting, logging)
8	MCP Servers	Serena, Context7, Sequential, Playwright, Postgres
9	Advanced Patterns	Trinity, CI/CD, feedback loops, vibe coding
10	Reference	Commands, shortcuts, troubleshooting, checklists
A	Appendix	Ready-to-use templates

Quick Links by Topic

Getting Started

• Installation · First Workflow · Essential Commands

Critical Concepts

• Context Management · Plan Mode · Memory Files

Customization

• Creating Agents · Creating Skills · Creating Commands · Creating Hooks

Advanced

• The Trinity Pattern · CI/CD Integration · MCP Configuration

---

Quick Start

# Install Claude Code (all platforms)
npm install -g @anthropic-ai/claude-code

# Or on macOS/Linux only:
curl -fsSL https://claude.ai/install.sh | sh

# Start in your project
cd your-project
claude

Windows Users: Use %USERPROFILE%\.claude\ instead of ~/.claude/ for all paths in this guide.

The 7 Commands You Need

Command	Action
/help	Show all commands
/status	Check context usage
/compact	Compress context (>70%)
/clear	Fresh start
/plan	Safe read-only mode
/rewind	Undo changes
Ctrl+C	Cancel operation

Context Management (Critical!)

Context %	Action
0-50%	Work freely
50-70%	Be selective
70-90%	/compact now
90%+	/clear required

---

The Golden Rules

1. Always review diffs before accepting changes
2. Use /compact before context gets critical (>70%)
3. Be specific in requests (WHAT, WHERE, HOW, VERIFY)
4. Start with Plan Mode for complex/risky tasks
5. Create CLAUDE.md for every project

---

Who Is This For?

• Beginners: Start with Quick Start (15 min) → be productive immediately
• Intermediate: Deep dive into Configuration, Agents, Skills
• Power Users: Advanced Patterns, MCP orchestration, CI/CD integration

---

Learning Paths

Choose your path based on experience and goals:

Junior Developer (45 min to productivity)

1. Quick Start - Installation & first workflow
2. Essential Commands - The 7 commands you need
3. Context Management - Critical concept
4. Memory Files - Create your first CLAUDE.md
5. Cheatsheet - Print and keep nearby

Senior Developer (40 min to mastery)

1. Core Concepts - Mental model & context zones
2. Plan Mode - Safe exploration
3. Agents - Custom AI personas
4. Hooks - Event-driven automation
5. CI/CD Integration - Pipeline automation

Power User (2 hours for full mastery)

1. Read the complete guide end-to-end
2. MCP Servers - Extended capabilities
3. The Trinity Pattern - Advanced workflows
4. Audit your setup - Optimize your configuration
5. Explore examples/ - Ready-to-use templates

Non-Technical / Product Manager (20 min overview)

1. What's Inside - Understand the scope
2. The Golden Rules - Key principles
3. Core Concepts - High-level overview
4. Context Management - Why it matters

---

Contributing

Found an error? Have a suggestion? See CONTRIBUTING.md for guidelines.

---

Audit Your Setup

Want to know if your Claude Code setup follows best practices?

File: claude-setup-audit-prompt.md

How it works:

1. Copy the prompt from the file
2. Run claude --ultrathink in your project
3. Paste the prompt and get a personalized audit report

What it checks:

• Memory files (CLAUDE.md) configuration
• Agents, skills, commands, and hooks setup
• MCP servers configuration
• Context management practices
• CI/CD integration patterns

Output: A prioritized report with health score, quick wins, and ready-to-use templates tailored to your tech stack.

---

Resources

Explore This Guide

• DeepWiki — AI-powered exploration of this repository (ask questions, get summaries)

Official

• Claude Code Documentation — Official Anthropic docs

Community Curated Lists

• awesome-claude-code — Commands, workflows, IDE integrations
• awesome-claude-skills — Custom skills collection
• awesome-claude-code-subagents — Full-stack & DevOps subagents
• awesome-claude — General Claude resources (SDKs, tools)
• awesome-claude-prompts — Prompt templates

Frameworks & Tools

• SuperClaude — Advanced configuration framework with 30+ commands
• Claudelog.com — Tips, patterns & tutorials

Further Reading

• Nick Tune: Coding Agent Development Workflows — Advanced autonomous workflow patterns

---

License

This work is licensed under CC BY-SA 4.0.

You are free to share and adapt this material, provided you give appropriate credit and distribute your contributions under the same license.

---

Last updated: January 2025 | Version 1.0