Claude Code

Overview

Claude Code is a rapidly iterating terminal-native AI coding tool from Anthropic. Unlike traditional IDE completion plugins, it works like a pair programmer sitting in your terminal: it can read an entire codebase, understand context, autonomously edit multiple files, run commands, execute tests, and complete complex cross-file tasks as an Agent. Between February and the end of March, Anthropic shipped 73 product features in succession—an astonishing update cadence—making it the primary development tool for many teams.

Core features: terminal-native, agentic autonomous coding, deep codebase understanding, and extensibility via the MCP protocol.

Installation

Claude Code is installed globally via npm and requires Node.js (18+ recommended). Run the following command in your terminal to install it globally, then verify with --version.

# Install Claude Code globally
npm install -g @anthropic-ai/claude-code

# Verify the installation
claude --version
# Output looks like: 2.3.1 (Claude Code)

To install a specific version (e.g. a pinned enterprise version): npm install -g @anthropic-ai/[email protected]

Basic Usage

Once installed, run the claude command in any project directory to start an interactive session. On first use you need to sign in to an Anthropic account or configure an API key. After launch, simply describe your needs in natural language and Claude will analyze, edit files, and run commands autonomously.

# Enter the project directory
cd my-project

# Start a Claude Code interactive session
claude

# Run a one-off task (non-interactive mode)
claude -p "Add type annotations to every function"

# Resume the previous session
claude --continue

Type /help in a session to see all commands, /clear to reset context, and press Ctrl+C twice to exit.

Tips

Claude Code's power lies in its agentic workflow. A well-crafted CLAUDE.md project memory file helps it understand your project conventions; the MCP protocol lets it connect to databases, browsers, external APIs, and other tools; and /undo lets you safely roll back unsatisfactory changes. We recommend using it inside a Git repository—every change is auto-committed, making it easy to track and revert.

# Create a memory file in the project root so Claude remembers your conventions
echo "# Project conventions
- Use TypeScript strict mode
- Functions must have JSDoc" > CLAUDE.md

# Specify a model
claude --model claude-sonnet-4

# View session history
claude --history

Tip: Break complex tasks into smaller steps for better results; run git commit before important changes to save the current state.

Configuration

Claude Code is configured through CLI flags, environment variables, and the CLAUDE.md project memory file. Set ANTHROPIC_API_KEY to authenticate non-interactively, use --model to pick a model, and manage MCP servers in ~/.claude.json or a project-level .mcp.json. A CLAUDE.md file in the project root is auto-loaded as persistent project context that the agent follows on every task.

# Authenticate via environment variable
export ANTHROPIC_API_KEY="sk-ant-..."

# Pick a model for the session
claude --model claude-sonnet-4

# Project memory file (loaded automatically)
# ./CLAUDE.md
# - Use TypeScript strict mode
# - Functions must have JSDoc

# MCP config (~/.claude.json or .mcp.json)
{
  "mcpServers": {
    "filesystem": {
      "command": "npx",
      "args": ["-y", "@modelcontextprotocol/server-filesystem", "/path"]
    }
  }
}

# Open the in-session settings panel
/config

Keep CLAUDE.md concise—treat it like a README of conventions the agent must follow on every task.

FAQ

Common questions cover API access, cost control, model selection, MCP setup, and how CLAUDE.md shapes behavior. Claude Code bills through your Anthropic account or API key, so costs scale with token usage; picking a cheaper model for routine edits and reserving the strongest model for planning helps control spend. MCP is optional but unlocks databases, browsers, and external APIs.

Q: Do I need a paid Anthropic plan?
A: Claude Code works with an Anthropic Console API key (pay-as-you-go) or a
   supported Claude subscription; check the official pricing page for current tiers.

Q: How do I reduce token costs?
A: Use a smaller/cheaper model for simple edits, keep CLAUDE.md lean, run
   /clear between unrelated tasks, and let the agent work in focused steps.

Q: Can I use my own API key?
A: Yes—set ANTHROPIC_API_KEY or sign in interactively on first launch.

Q: How does CLAUDE.md work?
A: It is auto-loaded from the project root (and parent dirs) as persistent
   context, so put coding conventions and project notes there.

Q: How do I add external tools?
A: Configure MCP servers in ~/.claude.json or .mcp.json; the agent can then
   call databases, browsers, filesystems, and more.

Run /help inside a session to see every available command and slash option.