Home / Glossary / Claude Code

Definition

Claude Code

Claude Code is Anthropic's terminal-based AI coding agent that operates directly in your development environment. It reads your entire project, writes code across multiple files, runs shell commands, manages git workflows, and iterates on errors autonomously—all from the command line.

How Claude Code works

Claude Code runs as a CLI tool in your terminal. When you start a session, it gains access to your project files, shell, and git history. You describe a task in natural language, and the agent plans a sequence of actions: reading files to understand context, writing code, running tests, and fixing issues. It uses Claude's reasoning capabilities to make multi-step decisions about how to complete your request.

Key features

  • +Full project context: reads and understands your entire codebase before making changes
  • +Terminal execution: runs tests, builds, linters, and any shell command directly
  • +Git automation: creates branches, commits, and pull requests as part of the workflow
  • +CLAUDE.md configuration: project-specific instructions the agent follows automatically
  • +MCP integration: connects to external tools and data sources via the Model Context Protocol
  • +Headless mode: runs without human interaction for CI/CD pipelines and automation
  • +Permission system: fine-grained control over what the agent can read, write, and execute
bash
# Install Claude Code
npm install -g @anthropic-ai/claude-code

# Start a session in your project
cd your-project
claude

# Give it a task
> "Refactor the auth module to use JWT tokens
   and update all tests"

Claude Code requires a Claude Pro, Team, or Enterprise subscription. It uses Claude's latest model and consumes tokens based on the complexity of your tasks.

Is Claude Code free?+
Claude Code is included with Claude Pro ($20/month), Claude Team, and Claude Enterprise subscriptions. Usage is metered based on tokens consumed during coding sessions.
How is Claude Code different from Cursor or Copilot?+
Claude Code is a terminal-native agent, not an IDE plugin. It operates on your actual filesystem and shell, giving it full project context and the ability to run commands. Cursor and Copilot are editor-integrated tools focused on inline suggestions and chat.
Can Claude Code work with any programming language?+
Yes. Claude Code reads source files and runs shell commands regardless of the language. It works with JavaScript, Python, TypeScript, Go, Rust, Java, C++, and any other language you use.
What is CLAUDE.md and why does it matter?+
CLAUDE.md is a configuration file you place in your project root. It contains project-specific instructions—coding conventions, architecture notes, common commands—that Claude Code follows automatically in every session. It acts as persistent memory for the agent.

Related terms

Agentic CodingModel Context Protocol (MCP)CLAUDE.mdHeadless AI Agent

Master Claude Code in days, not months

37 hands-on lessons from beginner to CI/CD automation. Module 1 is free.

START FREE →
← ALL TERMS