runbook-review-loop SKILL.md skillA
runbook-review-loop from agent-runbooks/skills is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add agent-runbooks/skills/runbook-review-loop@git:20261013.3723552Pins git:20261013.3723552 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- agent-runbooks/skills
- Path
skills/agent-runbook-authoring/references/runbook-review-loop/SKILL.md- Versions recorded
- 6
- Latest version
- git:20261013.3723552, committed Oct 13, 2026
- First version recorded
- Oct 3, 2026
- Size
- 9,739 bytes
- Repository stars
- 2
- License
- MIT
One code change in a git repository. A coder implements a brief, a reviewer reads the changes and runs the checks, and the coder fixes the findings until none are left or the fix rounds run out, every step a subagent of this session. Inputs brief, repo, optional checks and maxFixRounds. Leaves the changes uncommitted.
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
# Review loop Leaves the brief implemented in a repository, uncommitted, with a report: the last `review.md` of the run says what the changes do and lists the findings still open, if any. Commit and PR happen outside. Every step runs as a subagent through this session's own subagent tool, the Agent tool in Claude Code. No MCP server is needed. ## Inputs - `brief`: the change to make, as text. The orchestrator saves it to `<run>/brief.md` and passes `"brief": "brief.md"` to `start` - `repo`: absolute path of the git repository, the directory this session started in unless the human names another - `checks`: the shell command that checks the project, run from `repo`, e.g. `python3 -m unittest` or `pnpm test`. Optional: when it is omitted, the executors use the checks the repository's `AGENTS.md` or `CLAUDE.md` names - `maxFixRounds`: integer, default 2. One round is one fix and the review after it. When the rounds are spent and findings remain, the human is asked, and may grant one more round or several - `run-id`: given only to resume an interrupted run …
Read the whole file at its exact version.
How to install
mdr add agent-runbooks/skills/runbook-review-loop@sha256:2892e6d616c97095The line at the top of this page pins the label git:20261013.3723552, 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_7uxcjutgewzig3da)
2 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 6 versions of this file, between Oct 3, 2026 and Oct 13, 2026, about one every 2 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20261013.3723552 latest | 2026-10-13 | 3723552 | 9,739 B | A | view · diff |
| git:20261012.e372ef7 | 2026-10-12 | e372ef7 | 9,197 B | A | view · diff |
| git:20261004.dfba32b | 2026-10-04 | dfba32b | 8,893 B | A | view · diff |
| git:20261004.96bc69e | 2026-10-04 | 96bc69e | 8,342 B | A | view · diff |
| git:20261003.473b917 | 2026-10-03 | 473b917 | 7,492 B | A | view · diff |
| git:20261003.a8efdcb | 2026-10-03 | a8efdcb | 7,462 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 (9739 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
agent-runbooks/skills · 2 stars · license MIT · pushed 2026-10-18 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_7uxcjutgewzig3da GET https://markdownregistry.com/api/v1/resolve?ref=agent-runbooks/skills/runbook-review-loop GET https://markdownregistry.com/api/v1/blob/2892e6d616c97095d4538cdd39dd863bd580b3ab51d285c986ba08f0bdb2f852
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.