auto-review-loop SKILL.md skillA
auto-review-loop from wanshuiyin/auto-claude-code-research-in-sleep is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add wanshuiyin/auto-claude-code-research-in-sleep/auto-review-loop@git:20261024.f455879Pins git:20261024.f455879 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- wanshuiyin/auto-claude-code-research-in-sleep
- Path
skills/skills-codex/auto-review-loop/SKILL.md- Versions recorded
- 9
- Latest version
- git:20261024.f455879, committed Oct 24, 2026
- First version recorded
- Jul 13, 2026
- Size
- 32,654 bytes
- Repository stars
- 18,383
- License
- MIT
Autonomous multi-round research review loop. Uses a fresh Codex agent or selected Gemini, Grok, or Claude Code reviewer, implements fixes, and re-reviews until positive assessment or max rounds reached. Use when user says "auto review loop", "review until it passes", or wants autonomous iterative improvement.
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
# Auto Review Loop: Autonomous Research Improvement
> **Codex assurance:** the default same-family reviewer result records
> `review_independence: same-family` and `acceptance_status: provisional` in its
> trace/state artifact. A positive provisional verdict may drive fixes and stop
> the loop, but is never cross-family accepted. A selected reviewer earns
> cross-family acceptance only from its actual models and completed in-scope
> positive review. Reviewer failure emits BLOCKED.
Autonomously iterate: review → implement fixes → re-review, until the external reviewer gives a positive assessment or MAX_ROUNDS is reached.
## Context: $ARGUMENTS
## Constants
- MAX_ROUNDS = 4
- POSITIVE_THRESHOLD: score >= 6/10 AND verdict ∈ {"ready", "almost"} — both must hold, matching the operative STOP CONDITION below. Verdict vocabulary is {"ready", "almost", "not ready"}. (Earlier wording used "or" + a stale verdict set; the AND form is authoritative.)
- REVIEW_DOC: `review-stage/AUTO_REVIEW.md` (cumulative log) *(fall back to `./AUTO_REVIEW.md` for legacy projects)*
- **OUTPUT_DIR = `review-stage/`** — All review-stage outputs go here. Create the directory if it doesn't exist.
…Read the whole file at its exact version.
How to install
mdr add wanshuiyin/auto-claude-code-research-in-sleep/auto-review-loop@sha256:1ddf0c256958151eThe line at the top of this page pins the label git:20261024.f455879, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
[](https://markdownregistry.com/a/art_ftu5cuaw7vwi7gmf)
2 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 9 versions of this file, between Jul 13, 2026 and Oct 24, 2026, about one every 13 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20261024.f455879 latest | 2026-10-24 | f455879 | 32,654 B | A | view · diff |
| git:20261019.8fdc2d5 | 2026-10-19 | 8fdc2d5 | 32,655 B | A | view · diff |
| git:20260928.ced1951 | 2026-09-28 | ced1951 | 29,127 B | A | view · diff |
| git:20260928.5a8c4e3 | 2026-09-28 | 5a8c4e3 | 29,564 B | A | view · diff |
| git:20260906.0472e53 | 2026-09-06 | 0472e53 | 28,720 B | A | view · diff |
| git:20260821.861f87f | 2026-08-21 | 861f87f | 28,720 B | A | view · diff |
| git:20260811.90a65e2 | 2026-08-11 | 90a65e2 | 28,034 B | A | view · diff |
| git:20260715.ed233c2 | 2026-07-15 | ed233c2 | 24,898 B | A | view · diff |
| git:20260713.c725573 | 2026-07-13 | c725573 | 24,786 B | A | view |
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (32654 bytes)
- pass: No zero-width or bidi control characters
- pass: No instruction hidden inside an HTML comment
- pass: No link to an exfiltration or paste host
- pass: No credential-shaped string
- pass: No instruction to send local credentials anywhere
- pass: No text hidden with inline styles
- pass: No prompt-injection phrasing
- pass: No curl or wget piped into a shell
- pass: No recursive delete of root, home or parent
- pass: No instruction to read or print local credentials
- pass: No base64 blob over 200 characters
- pass: No link to a raw IP address
- pass: No script tag
Source
wanshuiyin/auto-claude-code-research-in-sleep · 18,383 stars · license MIT · pushed 2026-11-01 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_ftu5cuaw7vwi7gmf GET https://markdownregistry.com/api/v1/resolve?ref=wanshuiyin/auto-claude-code-research-in-sleep/auto-review-loop GET https://markdownregistry.com/api/v1/blob/1ddf0c256958151ed330852044c0cf2d4595fa8842ef79ff71dfc7ac590402ec
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.
More from wanshuiyin/auto-claude-code-research-in-sleep
Every file in wanshuiyin/auto-claude-code-research-in-sleep