Back to directory

Claude Code Action

A general-purpose GitHub Action that runs Claude Code against pull requests and issues, answering questions, reviewing changes and implementing fixes when triggered by mentions, assignments or automation.

Claude Code Action

Claude Code Action is a general-purpose GitHub Action that runs Claude Code against pull requests and issues. It detects when to activate based on workflow context, such as an @claude mention, an issue assignment, or an automation task with an explicit prompt, and supports authentication through the direct Anthropic API, Amazon Bedrock, Google Vertex AI or Microsoft Foundry.

It can answer questions about code and architecture, review a pull request's changes and suggest improvements, and implement simple fixes, refactoring or new features, working through GitHub comments and PR reviews. It shows visual progress indicators as it completes tasks, can return validated JSON that becomes an action output for further automation, and runs entirely on the caller's own GitHub runner, with only the model API calls going to the chosen provider.

It is written in TypeScript and released under the MIT license.

More in Coding agents

See all 793
  • The City

    github.com

    A native macOS app that shows Claude Code runs as a city, with each project as a building, each team as a floor of robots, and every animation driven by a real event from the claude CLI's stream.

  • rig

    tryrig.ai

    A small, single-binary agent runtime that points at any OpenAI-compatible model, local or hosted, reads and edits a repository's code, runs its tests and remembers what it learned, with a loop implemented in a few hundred lines.

  • Jauvex

    jauvex.reindent.com

    An Electron desktop app that puts Claude Code, Codex and Grok coding-agent sessions side by side and lets you steer them by voice, with a small model handling fast routing decisions.