Loading learning content…
Loading learning content…
Install and configure Claude Code on your machine, authenticate, and run your first session.
Read through the lesson, mark it complete when the concept is clear, then move to the next lesson in the sequence or jump back to the module map.
AI-narrated from the written lesson.
Claude Code is Anthropic's official CLI for Claude — a terminal-based AI coding assistant that understands your entire codebase. Unlike chat-based tools, Claude Code can read files, run commands, edit code, and manage git operations natively.
Install Claude Code globally via npm:
npm install -g @anthropic-ai/claude-code
After installation, run claude in any project directory to start a session.
Claude Code authenticates via your Anthropic account. On first launch, it will open a browser window to complete OAuth. Your session persists locally — you won't need to re-authenticate each time.
Navigate to any project directory and start Claude Code:
cd ~/your-project
claude
Claude will scan the directory, read relevant files, and be ready for instructions. You can ask it to explain the codebase, fix bugs, add features, or run tests.
Sessions are stateful conversations tied to a directory. Claude maintains context across turns within a session.
Tool use is how Claude interacts with your system — reading files, running shell commands, editing code, managing git. All tool calls are shown before execution.
CLAUDE.md files in your project give Claude persistent instructions. Think of them as a system prompt for your codebase.
Keep sessions focused on one task. Use /clear to reset context when switching topics. The --no-update flag prevents automatic updates if you need a stable version for CI.
Start with read-only exploration before asking for edits — let Claude explain the codebase structure before making changes.