Claude Code | LLM CLI Training

What is Claude Code?

Claude Code is Anthropic’s command-line AI agent. It runs in your terminal, reads your entire project, and can plan, write, edit, and debug code across multiple files autonomously.

Key features:

Understands your full codebase through long context (200K tokens)
Creates, edits, and deletes files
Runs commands and tests
Iterates on errors automatically
Respects your project’s style and conventions

Installation

Step 1: Install Claude Code

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

Verify it installed:

claude --version

You should see a version number.

Step 2: Authenticate

Run Claude Code for the first time:

claude

It will walk you through authentication. You have two options:

Option A — Anthropic Console (API key):

Go to console.anthropic.com
Create an account if you don’t have one
Go to API Keys and create a new key
When Claude Code asks, paste your key

Option B — Claude Pro/Max subscription: If you have a Claude Pro or Max subscription at claude.ai, Claude Code can use that directly. Follow the prompts to log in with your Anthropic account.

ℹAuthentication

Claude Code requires authentication with an Anthropic account. Your instructor will provide access details. You can authenticate via an API key or through a Claude Pro/Max subscription.

💡Authenticating over SSH or on a remote server

If you’re working on a remote server (SSH, VS Code Remote), the browser-based login won’t work directly. Instead, use Option A (API key) — set the key as an environment variable before starting Claude:

export ANTHROPIC_API_KEY="sk-ant-your-key-here"
claude

This bypasses browser auth entirely. You can also add the export to your ~/.bashrc so it persists across sessions.

Your first interaction

Let’s do a “hello world” — the simplest possible task to make sure everything works.

Step 1: Create a project folder

mkdir hello-claude && cd hello-claude

Step 2: Start Claude Code

claude

Step 3: Give it a task

Type this into Claude Code:

Create a simple HTML page that says "Hello from Claude Code!" with a
dark background and centered white text. Make it look clean and modern.

Watch what happens:

Claude plans what to create
It creates an index.html file
It writes the HTML, CSS, and content
It tells you what it did

Step 4: Check the result

ls                    # See the file(s) Claude created
cat index.html        # Look at the contents

Open the file in your browser:

open index.html

If you’re in WSL, open it with:

explorer.exe index.html

Or if you’re in VS Code, right-click the file in the Explorer panel and select “Open with Live Server” or “Reveal in File Explorer.”

Open the file in your browser:

xdg-open index.html

If you’re on a remote server (SSH), use VS Code’s file explorer to preview, or copy the file to your local machine. If you used VS Code Remote, just click the HTML file and it opens locally.

You should see a clean webpage with your message. You just built a website by describing what you wanted in plain English.

Useful Claude Code commands

Once inside a Claude Code session, these are helpful:

Command	What it does
`/help`	Show available commands
`/clear`	Clear the conversation
`/cost`	Show how much this session has cost
`Ctrl+C`	Exit Claude Code

Tips for effective use

Start in your project directory. Always cd into your project folder before running claude. This gives it access to your files.
Be specific. “Make it look nice” → vague. “Use a dark theme with #09090b background, rounded corners, and subtle border” → specific and predictable.
Iterate. Don’t try to get everything right in one prompt. Start with the basic structure, then refine: “Now add a navigation bar” → “Make the nav sticky” → “Add a mobile hamburger menu.”
Let it run. Claude Code will often plan multiple steps and ask for confirmation. When it asks “Should I proceed?”, say yes unless something looks wrong.

KNOWLEDGE CHECK

What's the best practice when starting Claude Code for a project?