Overview
auto-review-loop is an open-source data skill for Codex and GitHub Copilot, published by wanshuiyin. Its author describes it as: “Autonomous multi-round research review loop. In Copilot CLI it defaults to the native complementary rubber-duck subagent with host-event model evidence; elsewhere it uses Codex, while explicit external reviewer overri…”. The project has 15k stars on GitHub and is available under the MIT license. Add it to your setup with `git clone https://github.com/wanshuiyin/Auto-claude-code-research-in-sleep ~/.claude/skills/auto-review-loop`.
What auto-review-loop does
> 🔒 **Do not wrap this skill in `/loop`, `/schedule`, or `CronCreate`.** It > already loops internally (review → fix → re-review) and the reviewer carries > round-to-round memory in one `threadId` (`codex-reply`). An external timer > re-enters from the top each tick — fresh `threadId`, reviewer memory reset — > firing the verdict on wall-clock time instead of on artifact change: zero new > signal, full token cost. If you want to schedule something, schedule the > *external wait that precedes it* (experiments done → then run this once). See > `shared-references/external-cadence.md`.
What’s inside
The SKILL.md for auto-review-loop is organised into these sections:
- Context: $ARGUMENTS
- Constants
- Reviewer Calling Convention
- State Persistence (Compact Recovery)
- Append-Only External-Finalizer Receipt
- Output Protocols
- Workflow
- Initialization
- Loop (repeat up to MAXROUNDS)
- Termination
- Key Rules
- Prompt Template for Round 2+
Installation
Add auto-review-loop to your agent with:
git clone https://github.com/wanshuiyin/Auto-claude-code-research-in-sleep ~/.claude/skills/auto-review-loopReview a skill’s source before installing it — skills can instruct your agent to run commands. This command comes from the skill’s public repository, which is the source of truth for setup steps. New to skills? Read how to install Claude Code skills.
Supported agents
- Claude Code — declared in the repository topics
- Codex — named in the skill.md
- GitHub Copilot — named in the skill.md
License
auto-review-loop is published under the MIT license.
Strengths
- Clear MIT license — safe to read and adapt within its terms
- Ships in wanshuiyin/Auto-claude-code-research-in-sleep, an established project with 14,858 GitHub stars
- Works with Claude Code, Codex, GitHub Copilot
- Actively maintained — repository updated in the last 90 days
Author
Topics
Frequently asked questions
- What does auto-review-loop do?
- Autonomous multi-round research review loop. In Copilot CLI it defaults to the native complementary rubber-duck subagent with host-event model evidence; elsewhere it uses Codex, while explicit external reviewer overrides remain available. Implements fixes and re-reviews until a policy-approved positive assessment or max rounds is reached.
- How do I install auto-review-loop?
- Run git clone https://github.com/wanshuiyin/Auto-claude-code-research-in-sleep ~/.claude/skills/auto-review-loop in your agent, then reload your skills. Review the source at https://github.com/wanshuiyin/Auto-claude-code-research-in-sleep before installing.
- Is auto-review-loop free to use?
- Yes. auto-review-loop is free and open source under the MIT license, so you can read, run, and adapt it within that license's terms.
- Which agents does auto-review-loop work with?
- auto-review-loop lists Claude Code, Codex, and GitHub Copilot — named in its SKILL.md, its plugin marketplace or its repository topics. Skills use the portable SKILL.md format, so other agents that read that format may load it too.
- Where does auto-review-loop come from?
- auto-review-loop ships inside wanshuiyin/Auto-claude-code-research-in-sleep, a repository that contains 41 catalogued skills in total. The repository's 14,858 GitHub stars apply to that whole collection, not to this skill on its own.