Installation
Getting Claude Code Running in 5 Minutes
Video Lesson Coming Soon
A video walkthrough for this module is in production. For now, dive into the written content below.
What You'll Learn
- ✓ System requirements
- ✓ Three ways to install
- ✓ Authentication and account linking
- ✓ Your first conversation
- ✓ The /init command
- ✓ Understanding permission prompts
In this module 6 sections
Before You Start
Install Claude Code
There are three ways to install Claude Code. Pick whichever matches your setup. All three give you the same tool — the only difference is how you install and update it.
# Option 1: Native install (recommended — auto-updates)
# macOS / Linux / WSL:
curl -fsSL https://claude.ai/install.sh | bash
# Windows PowerShell:
irm https://claude.ai/install.ps1 | iex
# Option 2: Homebrew (macOS/Linux)
brew install --cask claude-code
# Option 3: WinGet (Windows)
winget install Anthropic.ClaudeCodeThe native install is the best choice for most people. It auto-updates in the background, so you always have the latest version. Homebrew and WinGet require manual updates.
Authenticate Your Account
Open any terminal application — Terminal on macOS, PowerShell on Windows, or your preferred terminal emulator on Linux.
Type claude and press Enter. The first time you run it, Claude Code will open your browser for authentication.
Sign in with the Anthropic account that has your Pro, Max, or Teams subscription. The browser will confirm the connection.
Once authenticated, your terminal shows the Claude Code welcome screen. Your login token is saved locally — you will not need to authenticate again unless the token expires.
Your First Conversation
Now let us run Claude Code inside a real project. Navigate to any folder that contains source code and start a conversation.
# Navigate to your project
cd ~/my-project
# Start Claude Code
claude
# Try these first prompts:
# "Explain the structure of this project"
# "What does the main entry point do?"
# "Find any TODO comments in the codebase"The /init Command
The single most important setup step is running /init. This command creates a CLAUDE.md file in your project root — a file that tells Claude Code about your project's conventions, tech stack, and preferences.
Without CLAUDE.md, Claude Code still works. But with it, every conversation starts smarter. Claude Code knows your preferred language, your testing framework, your coding style, and your project structure before you type a single word.
You will learn how to write an effective CLAUDE.md in Module 4. For now, just run /init and let Claude Code generate a starter file.
# Inside a Claude Code session, type:
/init
# Claude Code will:
# 1. Scan your project structure
# 2. Identify your tech stack
# 3. Generate a CLAUDE.md with sensible defaults
# 4. Save it to your project rootUnderstanding Permission Prompts
When Claude Code wants to edit a file or run a shell command, it asks for your permission first. You will see a prompt like:
"Claude wants to edit src/app.ts. Allow?"
This is a safety feature, not a limitation. You stay in control of what changes. You can approve once, approve for the rest of the session, or deny the action.
In Module 6, you will learn how to configure permissions to match your comfort level — from strict approval for everything to automatic approval for safe operations.
Key Takeaways
Claude Code installs with a single command — the native installer auto-updates and is recommended for most users
Authentication happens through your browser and saves a token locally so you only log in once
Running /init creates a CLAUDE.md file that teaches Claude Code about your project conventions
Permission prompts keep you in control — Claude Code always asks before editing files or running commands