hamelsmu

hamelsmu / claude-review-loop

Public

Claude Code plugin: automated code review loop with Codex

528
29
100% credibility
Found Feb 21, 2026 at 215 stars 2x -- GitGems finds repos before they trend. Get early access to the next one.
Sign Up Free
AI Analysis
Shell
AI Summary

A plugin for Claude Code that automates a code review loop, where an AI implements a user task and then addresses feedback from an independent reviewer.

How It Works

1
🔍 Discover the review helper

You hear about a handy tool that makes your AI coding buddy double-check its work for better results.

2
📥 Add the tool easily

In your AI coding session, you simply tell it to grab this review helper from the marketplace.

3
🚀 Start a smart review

You describe your task like 'Build a login page' and kick off the review loop – your AI gets to work!

4
⚙️ AI builds your feature

Your AI helper implements the task, adding code, tests, and everything needed.

5
🔍 Automatic quality check

When done, an independent review happens automatically, spotting any issues like bugs or improvements.

6
✏️ AI fixes the feedback

Your AI reads the review, agrees on fixes, makes changes, and notes what it skips.

🎉 Polished code ready

You end up with high-quality, reviewed code that's secure, well-tested, and ready to use confidently.

Sign up to see the full architecture

5 more

Sign Up Free

Star Growth

See how this repo grew from 215 to 528 stars Sign Up Free
Repurpose This Repo

Repurpose is a Pro feature

Generate ready-to-use prompts for X threads, LinkedIn posts, blog posts, YouTube scripts, and more -- with full repo context baked in.

Unlock Repurpose
AI-Generated Review

What is claude-review-loop?

This Shell plugin for the Claude Code CLI automates a two-phase code review loop in your AI-assisted coding workflow. Kick it off with `/review-loop `, Claude implements the task, then a stop hook triggers an independent Codex review covering code quality, tests, security, docs, and UX—Claude must address feedback before exiting. Cancel anytime with `/cancel-review`; it falls back to self-review if Codex isn't installed, ensuring every change gets a second opinion without manual intervention.

Why is it gaining traction?

It stands out by enforcing structured reviews via claude code agents, blending Claude's implementation speed with Codex's critical eye on OWASP risks, edge cases, and agent harness docs like AGENTS.md. Developers notice fewer regressions in claude code cli sessions, plus outputs like review Markdown files for claude code docs or sharing. The seamless install via `claude plugin marketplace add hamelsmu/claude-review-loop` hooks users experimenting with claude github integration or automated pr reviews.

Who should use this?

Solo devs or small teams using Claude Code CLI for rapid prototyping in Node.js, web apps, or scripts, especially those building auth flows, APIs, or UIs needing solid tests and security. Frontend engineers grinding E2E coverage or backend folks validating inputs will save hours on manual fixes. Ideal for claude code skills training or claude github pr review workflows in private repos.

Verdict

Worth a quick claude code install for Claude Code users—solid docs and graceful fallbacks make it practical despite 44 stars and 1.0% credibility score signaling early maturity. Test on a side project before production; pair with claude code pricing checks for heavy use.

(178 words)

Sign up to read the full AI review Sign Up Free

Similar repos coming soon.