A skills set and methodology for coding agents: clarify the task, plan, write tests, then code. The agent works with more discipline.
Coding agents & CLIanthropics
claude-code-action
A GitHub Action that plugs Claude Code into PRs and issues: it answers mentions, reviews changes and suggests or makes edits right in the repo.
Who it is for
For teams who want AI review and a helper inside GitHub.
How to start
- Open
claudein the terminal inside your repository. - Run
/install-github-appand complete the app and secrets setup. - You need repository admin rights; for Bedrock, Vertex and Foundry see docs/cloud-providers.md.
Steps are taken from the README. Check the current version in the repository before running them.
Stars over the last 30 days
More in «Coding agents & CLI»
An open coding agent for the terminal with a desktop app. It is not tied to one provider: plug in whichever models you have.
Anthropic's coding agent that lives in the terminal: it understands your project, edits files, runs commands and handles git from plain-language requests.
A toolkit for spec-driven development: principles and a spec first, then a plan and tasks, and only then code. Works with several coding agents.
OpenAI's lightweight coding agent that runs in the terminal and works on your project's code. Written in Rust.
Google's open terminal agent: it connects Gemini to your codebase and can edit files, run commands and search the web.
