test-audit SKILL.md skillA
test-audit from pymodel/jev-judge-mcp is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add pymodel/jev-judge-mcp/test-audit@git:20260924.cd29bfbPins git:20260924.cd29bfb in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- pymodel/jev-judge-mcp
- Path
.agents/skills/test-audit/SKILL.md- Versions recorded
- 2
- Latest version
- git:20260924.cd29bfb, committed Sep 24, 2026
- First version recorded
- Sep 24, 2026
- Size
- 14,715 bytes
- Repository stars
- 48
- License
- MIT
Invoke whenever writing, changing, reviewing, or sweeping tests in jev-judge-mcp. Authoring gate for new tests plus audit workflow for low-value, implementation-coupled, or duplicative tests and the test-only production seams they demand, under this repo's rule that a test is never deleted or weakened to make a failing build pass.
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
# Test Audit Three modes, one value bar. Authoring mode gates every new or changed test at write time. Audit mode runs focused sweeps of tests that re-assert source, duplicate stronger proof, couple behavior to implementation, or keep test-only production seams alive. Run broad audits as separate coherent follow-up branches, one concern each; optimize for confidence, not deletion count. Campaign mode prunes one whole test layer or source package at a time (see Campaign below). ## Authoring gate Before adding any test, answer four questions; a missing answer means do not add it yet: 1. What observable behavior, invariant, or independent contract does it protect? 2. What credible regression makes it fail? 3. Why does existing coverage not already catch that failure? Each contract has one primary test owner at the strongest boundary; another layer needs its own distinct risk, such as a stdio/HTTP transport or lifecycle failure the owner cannot reach. Prefer extending a parametrized case or a shared helper in `tests/support/` over a near-duplicate test; consolidate duplicated setup in the same change (the ADR-0015 loader and ADR-0017 secret checks …
Read the whole file at its exact version.
How to install
mdr add pymodel/jev-judge-mcp/test-audit@sha256:fcb972520ec20278The line at the top of this page pins the label git:20260924.cd29bfb, 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_odbphlksn7u34q6l)
4 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 2 versions of this file, all committed on Sep 24, 2026.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20260924.cd29bfb latest | 2026-09-24 | cd29bfb | 14,715 B | A | view · diff |
| git:20260924.4a0d61a | 2026-09-24 | 4a0d61a | 14,735 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 (14715 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
pymodel/jev-judge-mcp · 48 stars · license MIT · pushed 2026-10-20 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_odbphlksn7u34q6l GET https://markdownregistry.com/api/v1/resolve?ref=pymodel/jev-judge-mcp/test-audit GET https://markdownregistry.com/api/v1/blob/fcb972520ec2027804cd3ba968a18f0fc2961d892ac24b652b431e8a62e7e92a
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 pymodel/jev-judge-mcp
Every file in pymodel/jev-judge-mcp