Skip to main content
Getting Started

Getting Started with Claude Code

Install Claude Code, configure your project, and run your first session.

1. Install Claude Code

Claude Code is a CLI tool that runs in your terminal. Install it with one command:

curl -fsSL https://claude.ai/install.sh | bash

Alternative methods:

  • brew install claude-code (macOS)
  • npm install -g @anthropic-ai/claude-code (Node.js)

You will need a Claude.ai Max subscription or an Anthropic API key (via Claude Console) to authenticate.

2. First Run

Navigate to any project directory and type claude to start an interactive session:

cd my-project
claude

Claude will analyze your project structure and begin an interactive conversation. Try these first commands:

give me an overview of this codebase
what does @src/index.ts do?

3. Configure CLAUDE.md

Create a CLAUDE.md file in your project root to give Claude persistent context. You can auto-generate one:

/init

Or create it manually with the essentials:

# Project: MyApp

## Build & Test
- npm run dev     # start dev server
- npm test        # run tests
- npm run lint    # lint check

## Architecture
- React 18 + TypeScript frontend
- Express API at /api/v1
- PostgreSQL via Prisma ORM

## Conventions
- Functional components with hooks
- Named exports, kebab-case files
- Tests colocated in __tests__/

Keep it concise. For every line, ask: if I remove this, will Claude make a mistake? If not, remove it. See the CLAUDE.md deep guide for advanced patterns.

4. Custom Slash Commands

Define reusable commands in .claude/commands/:

# .claude/commands/review.md
Review the current changes for:
- Potential bugs and edge cases
- Security vulnerabilities
- Performance issues
Suggest fixes inline.

Then invoke with /review in any session. Commands are auto-discovered.

5. Understand Permissions

Claude Code uses a three-level permission system for tool use:

  • Allow — Tool runs automatically (e.g., reading files)
  • Ask — Claude requests your approval before running (default for writes)
  • Deny — Tool is blocked entirely

Use Shift + Tab to cycle between Normal, Auto-accept, and Plan Mode. See Plan Mode for read-only exploration.

Why does CLAUDE.md matter so much?

Context configuration is a core agent-development skill. Understanding how LLMs handle the context window explains why a concise, well-structured CLAUDE.md dramatically improves output quality.

Learn context window fundamentals in Agent Basics

Next Steps