anthropics/claude-code-action

Claude Code Action is a GitHub Actions workflow automation tool that integrates Claude AI to answer questions, review code, and implement changes in pull...

Owned by Anthropic

View on GitHub ↗Jump to charts ↓Open shareable report →

anthropics/claude-code-action has 9.5k+ stars and 2k+ forks on GitHub, is written in TypeScript, and was last pushed on Oct 18, 2026. Data as of . Signed-in members get hourly updates — create a free account.

Summary Information

Updated 29 minutes ago
Type:Plugin / ExtensionCategory(s):AI Coding AgentsCI/CD & ReleaseAI Agents & LLM Apps
Added to GitGenius on August 31st, 2026
Created on May 19th, 2025
Open Issues & Pull Requests: 832 (+0)
GitHub issues: Enabled
Number of forks: 2,214
Total Stargazers: 9,565 (+0)
Total Subscribers: 58 (+0)

Repository Insights (GitGenius)

Median issue/PR response: 18.6 hours
Mean response time: 16.1 days
90th percentile: 44.9 days
Tracked items: 614

Maintainer activity

2 people did triage or write work on this repository in the last 12 months.

Counts unlabeled, assigned, unassigned, milestoned, demilestoned, locked, unlocked over the last 12 months. These are issue and pull request events that require triage or write permission. Commits and code review are not counted. labeled and renamed are excluded because GitHub issue forms record the issue author as the actor. Figures from October 18, 2026. This count is not comparable across projects: each project's automation decides which of these events a person emits. How this is counted.

How this project is maintained

Roughly one issue in three opened in the past year never receives a reply. 99% of open issues come from outside the core team, so the backlog reflects real-world use rather than internal planning. Work labelled "dev-experience" is answered fastest, typically in about 7 hours, while "feature-request" waits about 3 days. 67% of tracked open issues have had no activity in three months, so the open count overstates what is actively being worked. Only 35% of issues opened in the past year have been closed.

Charts & Analytics

Fetching additional details & charts...

Issue Activity (beta)

Open issues: 480
New in 7 days: 5
Closed in 7 days: 0
Avg open age: 204 days
Stale 30+ days: 448
Stale 90+ days: 323

Recent activity

Opened in 7 days: 4
Closed in 7 days: 0
Comments in 7 days: 14
Events in 7 days: 41

Top labels

  • bug (493)
  • p2 (310)
  • p3 (186)
  • enhancement (130)
  • p1 (111)
  • provider:1p (94)
  • area:permissions (78)
  • feature-request (78)

Most active issues this week

Sign in to see which issues are moving.
Sign in

Detailed Description

Claude Code Action is a GitHub Actions workflow automation tool that integrates Claude AI to answer questions, review code, and implement changes in pull requests and issues.

The tool solves the problem of automating code review and assistance tasks by embedding Claude directly into GitHub workflows. It works by detecting context automatically—whether a user mentions @claude, assigns an issue, or triggers an explicit prompt—and then selecting the appropriate execution mode. The action can analyze pull request changes to suggest improvements, answer architectural questions, implement fixes and refactoring, and track progress with visual indicators. It supports multiple authentication paths including direct Anthropic API access, Amazon Bedrock, Google Vertex AI, and Microsoft Foundry, so teams can route API calls through their preferred provider while the action itself runs on their GitHub runners.

Teams should adopt this tool if they want to automate code review workflows or provide AI-assisted development within their GitHub processes. It suits repositories where maintainers want Claude to handle routine reviews, triage issues, or implement straightforward changes without manual intervention. The action requires repository admin access for initial setup and works best when integrated through the provided quickstart flow or configured via the unified prompt and claude_args inputs.

The project maintains a substantial adopter base, with nearly all open issues coming from external users rather than the core team. Maintainers typically respond to new issues and pull requests within a day. Work in the issue tracker centers on bug reports and priority-level issues, indicating active maintenance focused on stability and incremental improvements.