← Tracker · Coding agent

Claude Code

BuildersCoding agentAnthropic

Agentic coding tool that runs in the terminal and IDEs, reads a codebase and makes multi-file edits.

Best for / Not for

Best for

  • Developers working in large existing codebases
  • Multi-file refactors and test-fixing loops
  • Teams that want an agent in the terminal, IDE and desktop

Not for

  • People who never touch a terminal or code
  • Teams that cannot send code to a cloud model

3 concrete use cases

  1. Fix failing tests: "Run the test suite, find why the auth tests fail, fix the root cause and re-run until green. Explain the change."
  2. Explain an unfamiliar repo: "Give me a map of this codebase: main modules, data flow, and where payments are handled."
  3. Connect your tools via MCP: Add a server with claude mcp add --transport http notion https://mcp.notion.com/mcp, then: "Implement the spec in the Notion page Onboarding v2."

Pros and cons

Pros

  • Works across many files and runs commands itself
  • Extensible with MCP servers, plugins and hooks
  • Available in terminal, IDEs and desktop

Cons

  • Needs a paid Claude plan or API usage
  • Agentic runs can consume a lot of usage
  • You must review changes; it can be confidently wrong

How to get started with Claude Code in 10 minutes

  1. Install: curl -fsSL https://claude.ai/install.sh | bash (macOS/Linux) or the PowerShell command in the docs on Windows
  2. Open a new terminal, cd into a project and run claude
  3. Sign in when prompted
  4. Ask: "What does this project do?"
  5. Ask for one small change and review the diff before accepting

Playbooks using Claude Code

Comparisons

Claude Code alternatives

Recent changes

Weekly updates for Claude Code will be logged here as they appear in issues.

Get changes in your inbox