ContextQMD
Back to Char

Claude Code

apps/web/content/handbook/onboarding/7.claude-code.mdx

latest2.1 KB
Original Source

What it is

Claude Code is an AI assistant that lives in your terminal. You describe what you want in plain English, and it reads files, writes code, runs commands, and makes changes across your project. Think of it as a very capable teammate you can pair-program with.

We use Claude Code for everything from writing features to debugging to content edits.

Prerequisites

Install

bash
npm install -g @anthropic-ai/claude-code

First launch

  1. Open your terminal
  2. Navigate to the Char repo: cd ~/Dev/hyprnote (or wherever you cloned it)
  3. Run: claude
  4. On first launch, it will ask you to authenticate with your Anthropic account

How it works

Once inside a Claude Code session:

  • Describe what you want — "Fix the typo in the homepage header" or "Add a new blog post template"
  • It reads your codebase — Claude Code understands the project structure and can find relevant files
  • It makes changes — You review each change before it's applied
  • It runs commands — It can run tests, builds, and other commands with your permission

Useful commands

/help          — See available commands
/clear         — Clear conversation history

Type your request in natural language. Be specific about what you want — "change the button color to blue" works better than "make it look better".

For non-engineers

Claude Code is powerful even if you don't write code:

  • Edit content — "Update the blog post title to 'Building in Public'"
  • Find things — "Where is the pricing page defined?"
  • Understand code — "Explain what this file does"
  • Make changes — "Add a new section to the handbook about onboarding"

You review every change before it's applied, so you can't accidentally break anything.

Back to checklist

Return to Tooling Checklist