Top 200 ReposEXPLORER
Browse agents, categories and pages
Back to results
Reported by sourceThe source says this happened. Top 200 Repos has not reproduced it.

Review pull requests automatically with Claude in GitHub Actions

Install the Claude Code GitHub Action so Claude reviews each pull request with inline comments and responds to @claude requests.

Try the promptRead the original (opens in a new tab)

The problem

How it works

The docs describe running `/install-github-app` from Claude Code, or manually installing the Claude GitHub App, adding an API key or OAuth token secret and copying a workflow file. A review workflow runs a code-review plugin skill on opened or updated pull requests and posts inline comments; an interactive workflow answers @claude mentions in issues and PRs.

Results and limitations

Anthropic's docs say Claude posts findings as inline comments, or one summary comment when it finds nothing, and skips drafts and trivial PRs.

Before you try it

Each run uses GitHub Actions minutes and model tokens; the docs suggest turn limits and timeouts to cap cost. The GitHub App asks for broad permissions, and secrets are withheld from fork PRs on public repos. Results depend on your setup and were not independently reproduced by Top 200 Repos.

Tools and repositories

Tools
GitHub Actions · Claude Code · GitHub CLI
Prerequisites
Admin access to the repository and an Anthropic API key or Claude subscription OAuth token stored as a secret.

Try it yourself: Set up PR review for a repository

Fill the fields to adapt the prompt. Empty fields stay as visible [placeholders].

Preview
Set up automatic pull request review with the Claude Code GitHub Action for [Repository]. Explain the GitHub App permissions and the secret it needs, then show me the workflow YAML before committing anything. Trigger reviews on [PR events], cap each run with --max-turns [Turn limit] and a job timeout, and focus the review on [Review focus]. Put review rules in CLAUDE.md rather than the workflow. Commit the workflow to a new branch and open a draft pull request only after I approve; do not touch existing workflows or secrets without asking.

Treat AI review comments as suggestions and keep a human approval requirement on merges.

Related videos

About anthropics/claude-code

About anthropics/claude-code

Independent creators. Listing a video implies no endorsement, sponsorship or partnership.

Sources

  1. Claude Code GitHub Actions (opens in a new tab)

    Project documentation · code.claude.com · Undated · Source checked 9 Nov 2026, 22:25 UTC

    What this source supports
    • Quick setup with /install-github-app or manual workflow setup
    • Review workflow posts inline PR comments via a code-review plugin skill
    • Interactive mode responds to @claude mentions
    • Costs are GitHub Actions minutes plus API tokens; use --max-turns and timeouts
    • Store credentials as GitHub secrets and review changes before merging
Report a problem

Reported by source

Trace a disk-filling production bug from core dumps with an agent

B12 CTO Adam Marcus used Claude Code to analyze gigabyte core dumps filling web server disks and traced them to an RSS endpoint reading an endless radio stream.

blog.marcua.net · 28 Jan 2026anthropics/claude-code
Reported by source

Answer technical questions by letting async agents run experiments

Simon Willison sends research questions to cloud coding agents such as Claude Code for web and Codex Cloud, which write and run experiments in a dedicated repo and open a PR.

simonwillison.net · 6 Nov 2025anthropics/claude-code, openai/codex
Planned, not done

Build a formula-driven Excel model with the Claude xlsx skill

Install Anthropic's xlsx skill in Claude Code so the agent writes live formulas, recalculates the workbook with LibreOffice and checks it for formula errors.

github.comanthropics/skills, anthropics/claude-code
Reported by source

Build an on-call investigation agent from your own alert history

Goutham Veeramachaneni connected Claude Code to Grafana's gcx CLI, his code and runbooks, then trained its skill on two weeks of past pages for his services.

gouthamve.dev · 21 Apr 2026anthropics/claude-code
Reported by source

Get a new OCR model running on unfamiliar GPU hardware with Claude Code in a sandbox

Simon Willison gave Claude Code full permissions inside a Docker container on an NVIDIA Spark and had it get DeepSeek-OCR working; it took four prompts and under 40 minutes, with one nudge from him.

simonwillison.net · 20 Oct 2025anthropics/claude-code, pytorch/pytorch, huggingface/transformers
Reported by source

Let a coding agent run overnight ML training experiments

Point a coding agent at autoresearch so it edits a small GPT training script, runs short timed experiments and keeps what improves.

github.comkarpathy/autoresearch, anthropics/claude-code, openai/codex

More with Claude Code

Reported by source

Run unattended ML training experiments with autoresearch

Red Hat's Roy Belio containerized Karpathy's autoresearch on OpenShift AI with H100 GPUs and let Claude Code run 198 training experiments over 24 hours.

developers.redhat.com · 7 Apr 2026karpathy/autoresearch, anthropics/claude-code
Reported by source

Give Claude your Google Calendar and Gmail through a self-run MCP server

The open-source Google Workspace MCP server exposes Calendar, Gmail and other Workspace tools to Claude Desktop, Claude Code and other MCP clients, using your own OAuth client and optional read-only mode.

github.com
Planned, not done

Let an agent decompile and annotate a binary in Ghidra through GhidraMCP

GhidraMCP exposes Ghidra's decompiler and renaming tools over MCP, so an agent such as Claude Code can list functions, read decompiled code and propose clearer names.

github.comNationalSecurityAgency/ghidra

View all: Claude Code