crucible-audit SKILL.md skillA
crucible-audit from nxtg-ai/forge-plugin is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add nxtg-ai/forge-plugin/crucible-audit@git:20261014.f30514dPins git:20261014.f30514d in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- nxtg-ai/forge-plugin
- Path
plugins/nxtg-forge/skills/crucible-audit/SKILL.md- Versions recorded
- 5
- Latest version
- git:20261014.f30514d, committed Oct 14, 2026
- First version recorded
- Mar 7, 2026
- Size
- 13,370 bytes
- Repository stars
- 6
- License
- MIT
Optional convenience, no accuracy claim: a structured test-quality review prompt that looks for hollow assertions, coverage-omit gaming, mock proliferation, dead/gated tests, untested entry points, and README badge inflation. Use when asked to "run a CRUCIBLE audit", "check/audit test quality", "find silent failures", "find hollow tests", "audit assertions/mocks/coverage config", "why do tests pass but nothing works", or before any release gate (pre-publish/pre-deploy) when a high test count…
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
# CRUCIBLE Test Quality Audit ## Overview > **Optional convenience. No accuracy claim.** This is a structured review prompt. It finds what the model finds when it reads the project, and nothing more. On two deliberately seeded public cases ([forge-done-fixture](https://github.com/nxtg-ai/forge-done-fixture), [forge-done-fixture-2](https://github.com/nxtg-ai/forge-done-fixture-2)), a plain review prompt found the same defects at roughly a third to a quarter of this command's cost (fixtures 1 and 2, 24 runs). A clean report is not evidence that nothing is wrong. The CRUCIBLE Audit skill provides a checklist for reviewing test suites. It looks for **test fraud** — the pattern where test count and coverage numbers look healthy but the tests prove nothing about whether the software actually works. **Origin**: Wolf's forensic audit of Podcast-Pipeline (2026-03-07). 1,601 tests, 77% claimed coverage — actual coverage ~15%, nothing worked when a human used it. ## Language Matrix (read this BEFORE running any detection command) …
Read the whole file at its exact version.
How to install
mdr add nxtg-ai/forge-plugin/crucible-audit@sha256:0bc5cfb1f479db65The line at the top of this page pins the label git:20261014.f30514d, 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_y2iya5hdlqsow2hq)
3 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 5 versions of this file, between Mar 7, 2026 and Oct 14, 2026, about one every 55 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20261014.f30514d latest | 2026-10-14 | f30514d | 13,370 B | A | view · diff |
| git:20260714.4fd0952 | 2026-07-14 | 4fd0952 | 12,850 B | A | view · diff |
| git:20260714.061716b | 2026-07-14 | 061716b | 7,715 B | A | view · diff |
| git:20260308.688ea23 | 2026-03-08 | 688ea23 | 7,691 B | A | view · diff |
| git:20260307.b3f3879 | 2026-03-07 | b3f3879 | 7,691 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 (13370 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
nxtg-ai/forge-plugin · 6 stars · license MIT · pushed 2026-10-15 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_y2iya5hdlqsow2hq GET https://markdownregistry.com/api/v1/resolve?ref=nxtg-ai/forge-plugin/crucible-audit GET https://markdownregistry.com/api/v1/blob/0bc5cfb1f479db657df6447d38e2d5d24096329a4330ee8caad9f07900583a95
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.