loop-engineering-audit SKILL.md skillA
loop-engineering-audit from eagerworks/skills is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add eagerworks/skills/loop-engineering-audit@v1.1.0Pins v1.1.0 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- eagerworks/skills
- Path
skills/loop-engineering-audit/SKILL.md- Versions recorded
- 2
- Latest version
- v1.1.0, committed Sep 12, 2026
- First version recorded
- Aug 28, 2026
- Size
- 13,036 bytes
- Repository stars
- 15
- License
- MIT
Audits a repository for loop-engineering readiness — whether an AI coding agent can pick up a task, implement it, verify it with local checks, and hand off a PR in an unattended loop — and returns a graded report, the ordered list of work needed to get there, and an advisory map of which parts of the delivery workflow could be automated plus the specific agent loops this project could create and maintain, each with its risk level, its guardrails, and what to configure to run it. Use when asked…
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
# Loop Engineering Audit Skill **Loop engineering** is developing a codebase through autonomous agent loops: an agent takes a well-defined task, implements it, runs the project's own checks until they pass, and opens a PR — with no human in the inner loop. A loop only works when the project gives the agent four things: **context** it can read, **verification** it can run, **guardrails** that make unattended mistakes cheap, and **room to run more than one loop at once**. This skill audits a repo for those things across eight dimensions and produces the **ordered work plan** that closes the gaps — plus, as advisory output, which parts of the workflow could be automated and which loops the project could actually run. The audit is **read-only with exactly one write**: the finished report is printed in chat **and** saved to `docs/loop-engineering-audit.md` at the audited repo's root (`docs/` is created if missing; the file is overwritten on re-run so the project keeps one current audit). Nothing else is created, edited, committed, or pushed. ## Discovery — Do This First …
Read the whole file at its exact version.
How to install
mdr add eagerworks/skills/loop-engineering-audit@sha256:e13c630513bd9a0aThe line at the top of this page pins the label v1.1.0, 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_v6adbkfble6jvkfw)
3 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 2 versions of this file, between Aug 28, 2026 and Sep 12, 2026, about one every 15 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| v1.1.0 latest | 2026-09-12 | 1c337e2 | 13,036 B | A | view · diff |
| v1.0.0 | 2026-08-28 | 8a024a7 | 8,548 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 (13036 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
eagerworks/skills · 15 stars · license MIT · pushed 2026-09-12 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_v6adbkfble6jvkfw GET https://markdownregistry.com/api/v1/resolve?ref=eagerworks/skills/loop-engineering-audit GET https://markdownregistry.com/api/v1/blob/e13c630513bd9a0a9fade333d073cd2d5aa51e193a96c59e11549ee504582ef9
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.