Claude Code Agent

Claude Code is Anthropic's agentic coding tool. It reads your codebase, edits files across it, runs commands and tests, and works directly with git: staging changes, writing commit messages and opening pull requests. It runs in the terminal, in VS Code and JetBrains, in a desktop app and on the web, and it connects to other tools through MCP servers. A CLAUDE.md file in your project gives it standing instructions at the start of every session. On macOS, Linux or WSL the recommended install is: curl -fsSL https://claude.ai/install.sh | bash. Homebrew users can run brew install --cask claude-code. Then change into a project and run claude; you sign in on first use. Most surfaces need a Claude subscription or an Anthropic Console account. It is worth using when a change spans more than one file and has to be checked: describe the feature, let it plan the approach, write the code, run the tests and fix what fails, then review the diff before it is committed. It also runs non-interactively with claude -p, which is how it gets used in scripts and CI. The security docs are clear about who is responsible. In Manual mode it starts with read-only permissions and asks before editing files or running commands, but you are responsible for reviewing proposed code and commands before approving them. Anthropic also notes that no system is completely immune to prompt injection, and recommends reviewing commands and avoiding piping untrusted content into it.