fix-loop-judge SKILL.md skillA
fix-loop-judge from itsomidkarami/kraft is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add itsomidkarami/kraft/fix-loop-judge@git:20261005.5da2a3dPins git:20261005.5da2a3d in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- itsomidkarami/kraft
- Path
src/kraft/skills/fix-loop-judge/SKILL.md- Versions recorded
- 5
- Latest version
- git:20261005.5da2a3d, committed Oct 5, 2026
- First version recorded
- Sep 22, 2026
- Size
- 2,985 bytes
- Repository stars
- 7
- License
- Apache-2.0
Judges whether a fix loop's next cycle is still worth spending, from the trend of findings across rounds and the budget used, and reports continue, stop_needs_human or stop_downgrade. Use when Kraft asks it after a fix loop's first cycle, before each further one; it neither reviews nor fixes code.
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
# Judging a fix loop mid-run You are not reviewing code and you are not fixing anything. A fix loop (a node with a `fix_loop`, such as `verification` or `merge_request_feedback` in the seeded chain) has already run at least one cycle; before it spends another, you are asked whether that is still a good trade. Your task instruction already carries what you judge from: every round's eligible findings (with a fingerprint stable across rounds -- the same tag reappearing is the same finding, not a new one), and the budget spent so far against the loop's cap. When your task declares the review package, `$KRAFT_REVIEW_PACKAGE` names a file with the change itself -- the whole branch the first time you are asked, then only what changed since your last session. Read it to see whether the code behind a recurring finding actually moved, not to review the change again. Do not go looking for the fix agent's reasoning; it is not evidence about whether the code moved. ## What to weigh - **Shrinking vs recurring vs growing.** Fewer findings each round, even slowly, is progress worth continuing. The same fingerprint surviving two …
Read the whole file at its exact version.
How to install
mdr add itsomidkarami/kraft/fix-loop-judge@sha256:b5dfed1a964383b3The line at the top of this page pins the label git:20261005.5da2a3d, 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_xtgws527l7ocawb5)
1 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 5 versions of this file, between Sep 22, 2026 and Oct 5, 2026, about one every 3 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20261005.5da2a3d latest | 2026-10-05 | 5da2a3d | 2,985 B | A | view · diff |
| git:20261004.8097c6f | 2026-10-04 | 8097c6f | 2,866 B | A | view · diff |
| git:20260923.cb6385c | 2026-09-23 | cb6385c | 2,631 B | A | view · diff |
| git:20260923.e805728 | 2026-09-23 | e805728 | 3,112 B | A | view · diff |
| git:20260922.fcebf63 | 2026-09-22 | fcebf63 | 3,116 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 (2985 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
itsomidkarami/kraft · 7 stars · license Apache-2.0 · pushed 2026-10-21 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_xtgws527l7ocawb5 GET https://markdownregistry.com/api/v1/resolve?ref=itsomidkarami/kraft/fix-loop-judge GET https://markdownregistry.com/api/v1/blob/b5dfed1a964383b300ebf6ae18b6f88fe57c9e9ced352d727c49a84bc9cca445
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.