# anthropics/claude-code-action

Repository: https://github.com/anthropics/claude-code-action
Canonical: https://ross.abutalabs.com/products/claude-code-action
Language: TypeScript
License: MIT
License Family: permissive
Last push: 2026-08-25T22:34:06+00:00

## Health v2 (maintenance only)
Score: 82/100 (v2, computed 2026-09-03T02:39:23.370411+00:00)
- activity 99, release rhythm 87, longevity 33
- inputs: {"age_days": 471, "days_push": 8, "days_rel": 7, "gap_med": 1.0, "n_releases_24m": 271}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 8729, forks 2094 (observed 2026-08-28T04:10:24.449133+00:00)

## What it is
A GitHub Action that runs Claude Code on pull requests and issues, answering questions, reviewing code, and implementing changes triggered by @claude mentions or workflow events. It supports multiple LLM providers including Anthropic API, Amazon Bedrock, Google Vertex AI, and Microsoft Foundry, and runs entirely on your own GitHub runners.

## Use cases
- automate code review on pull requests
- answer questions about codebase from GitHub comments
- let an AI agent implement small fixes and features in PRs
- trigger AI automation on issue assignment
- review changes from external contributors automatically
- run path-specific reviews when critical files change

## When to choose
- you want AI-assisted PR review and issue triage inside GitHub workflows
- you need to run Claude on your own infrastructure with a choice of cloud LLM providers
- you want structured JSON outputs from AI automation in CI

## When to avoid
- you need a standalone CLI coding agent outside GitHub
- you don't use GitHub Actions or GitHub-hosted workflows
- you need fully offline AI code review without an LLM API

## Facets
- artifact type: plugin
- maturity: active
- function: agent-framework, code-review, workflow-automation, llm-inference, developer-tools
- domain: developer-tools, version-control, large-language-models
- platform: cloud
- tags: github-actions, claude, pull-request-review, issue-automation, ci-cd, anthropic, automation, ai-agents, nodejs, typescript

## Member repositories
- anthropics/claude-code-action (main) score 82

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:10:24.449133+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T17:25:19.660640+00:00, confidence not recorded.
  - readme: https://github.com/anthropics/claude-code-action (fetched 2026-08-28T04:10:24.449133+00:00, sha 2784078b1742)
- Data as of 2026-08-30T08:39:29.467469+00:00.