ia-test-audit SKILL.md skillA

ia-test-audit from iliaal/whetstone is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add iliaal/whetstone/ia-test-audit@git:20261019.b33b11a

Pins git:20261019.b33b11a in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
iliaal/whetstone
Path
plugins/whetstone/skills/ia-test-audit/SKILL.md
Versions recorded
2
Latest version
git:20261019.b33b11a, committed Oct 19, 2026
First version recorded
Sep 26, 2026
Size
8,352 bytes
Repository stars
35
License
MIT

Audit whether tests detect regressions in the behavior they claim to protect. Find mocked-away subjects, weak or circular assertions, undiscriminating fixtures, swallowed failures, and tests missing from gates. Use for test-quality audits, suspected false confidence in generated tests, and reviewing new tests. Use ia-writing-tests for writing tests.

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

Find tests that remain green when their claimed behavior breaks. Assess behavior,
not apparent authorship, mock count, assertion count, or a target finding percentage.
Default to a read-only audit. Change tests or production code only when requested.

Adapted from the OpenClaw test-audit skill (MIT).

## What counts as a finding

Evaluate each claimed behavior separately. A test can protect one obligation and miss
another. Use these dispositions:

- **Ineffective for the claim:** the named behavior is replaced, never reached, or
  disconnected from a verdict that can fail.
- **Partially effective:** real behavior is tested, but a specific promised distinction
  is absent from the input or assertions. Preserve the protection that exists.
- **Not enforced:** the test is uncollected, skipped, or absent from a blocking gate.
  Report local collection and CI enforcement separately from assertion quality.
- **Redundant:** another test protects the same behavior at the same boundary under
  equivalent inputs and setup. This requires separate evidence; weakness alone is
  not redundancy.
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add iliaal/whetstone/ia-test-audit@sha256:046e34bca989a709

The line at the top of this page pins the label git:20261019.b33b11a, 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.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_idtoylux6bbgzlmi.svg)](https://markdownregistry.com/a/art_idtoylux6bbgzlmi)

4 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 2 versions of this file, between Sep 26, 2026 and Oct 19, 2026, about one every 23 days.

versioncommittedcommitsizeaudit
git:20261019.b33b11a latest2026-10-19 b33b11a 8,352 BA view · diff
git:20260926.74157bb2026-09-26 74157bb 8,342 BA view

Audit of the latest version

A  17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (8352 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

GitHub

iliaal/whetstone · 35 stars · license MIT · pushed 2026-11-04 · branch master

API

GET https://markdownregistry.com/api/v1/artifacts/art_idtoylux6bbgzlmi
GET https://markdownregistry.com/api/v1/resolve?ref=iliaal/whetstone/ia-test-audit
GET https://markdownregistry.com/api/v1/blob/046e34bca989a7090423b5bd864a67fc5ce626c51ef0c78fba45cacb4f2ff22c

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 iliaal/whetstone

analyze-misfires SKILL.md skill
iliaal/whetstone · .agents/skills/analyze-misfires/SKILL.md · Analyze Whetstone skill injection misfires when asked to investigate overly broad triggers or irrelevant injected…
git:20260907.228ec83 · audit A · 35 stars
announce SKILL.md skill
iliaal/whetstone · .agents/skills/announce/SKILL.md · Draft an X announcement for a Whetstone release when asked to announce that release.
git:20260907.228ec83 · audit A · 35 stars
audit-plugin SKILL.md skill
iliaal/whetstone · .agents/skills/audit-plugin/SKILL.md · Audit Whetstone skills, agents, and commands when asked for a plugin quality or consistency audit.
git:20260907.228ec83 · audit A · 35 stars
diagnose-negatives SKILL.md skill
iliaal/whetstone · .agents/skills/diagnose-negatives/SKILL.md · Investigate negative session feedback for a Whetstone skill when asked to diagnose its failures.
git:20260907.228ec83 · audit A · 35 stars
eval-skills SKILL.md skill
iliaal/whetstone · .agents/skills/eval-skills/SKILL.md · Evaluate Whetstone skills from session evidence when asked to compare procedure-following results or optimization…
git:20260907.228ec83 · audit A · 35 stars
evolve-skill SKILL.md skill
iliaal/whetstone · .agents/skills/evolve-skill/SKILL.md · Revise and evaluate a Whetstone skill when asked to evolve or optimize that skill.
git:20260907.228ec83 · audit A · 35 stars
prune-sync-log SKILL.md skill
iliaal/whetstone · .agents/skills/prune-sync-log/SKILL.md · Prune stale Whetstone sync decision entries when asked to clean the sync log.
git:20260907.228ec83 · audit A · 35 stars
release SKILL.md skill
iliaal/whetstone · .agents/skills/release/SKILL.md · Run the Whetstone release workflow when explicitly asked to release this plugin.
git:20260907.228ec83 · audit A · 35 stars
skillopt SKILL.md skill
iliaal/whetstone · .agents/skills/skillopt/SKILL.md · Prepare or run Whetstone SkillOpt optimization when asked to optimize a process skill using SkillOpt.
git:20260907.228ec83 · audit A · 35 stars
sync-from-repos SKILL.md skill
iliaal/whetstone · .agents/skills/sync-from-repos/SKILL.md · Compare Whetstone with reference repositories when asked to sync cross-repository improvements.
git:20260907.228ec83 · audit A · 35 stars
triage-prs SKILL.md skill
iliaal/whetstone · .agents/skills/triage-prs/SKILL.md · Triage Whetstone pull requests when explicitly asked to group, label, and review open PRs.
git:20260907.228ec83 · audit A · 35 stars
write-skill SKILL.md skill
iliaal/whetstone · .agents/skills/write-skill/SKILL.md · Author a new Whetstone plugin skill when asked to write a skill without upstream skills.sh sources.
git:20260907.228ec83 · audit A · 35 stars

Every file in iliaal/whetstone

Browse by kind, by grade A, or by owner.