Borrowing it
Nothing to install: this file belongs to mkslge/piazza-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/mkslge/piazza-mcp/main/.agents/skills/unit-test-audit/SKILL.mdgit clone --depth 1 https://github.com/mkslge/piazza-mcpWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/mkslge/piazza-mcp/unit-test-audit)<a href="https://agentmods.dev/skills/mkslge/piazza-mcp/unit-test-audit"><img src="https://agentmods.dev/badge/skills/mkslge/piazza-mcp/unit-test-audit/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/mkslge/piazza-mcp/unit-test-audit"><img src="https://agentmods.dev/badge/skills/mkslge/piazza-mcp/unit-test-audit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00085 | $0.01565 |
| Opus 5 | $0.00043 | $0.00783 |
| Sonnet 5 | $0.00017 | $0.00313 |
| Haiku 4.5 | $0.00009 | $0.00156 |
Grade A, and why
unit-test-audit scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 159 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Unit Test Audit
Act as a skeptical test-suite auditor. Review every unit test in scope, but report only tests with a concrete usefulness or quality problem. Do not modify tests or production code unless the user separately requests fixes.
Establish Complete Scope
Read repository instructions, test configuration, CI commands, and test-folder conventions before judging tests. Determine which tests are unit tests from explicit markers, configured paths, naming, dependencies, and fixtures.
- Prefer the framework's collection command to inventory test node IDs without executing them.
- Exclude vendored dependencies, generated build artifacts, virtual environments, and tests explicitly classified as integration, end-to-end, or live-service tests.
- If the repository does not distinguish test types, audit all tests that can run without external services and state that working definition.
- Count collected cases and reviewed test definitions separately. For a parametrized test, evaluate the shared definition and identify individual parameter rows only when their value differs.
- If collection is incomplete or unsafe, use a static inventory and disclose exactly what could not be reviewed. Never claim a complete audit without a reconciled inventory.
Gather Evidence Safely
Inspect the relevant production behavior, fixtures, fakes, helpers, and nearby tests before classifying a test. Run the safest repository-defined unit-test command when it does not access live services or mutate external state. Do not run live, destructive, or credential-dependent tests without authorization.
Passing status and coverage are supporting signals, not proof of usefulness. Do not install new analysis or mutation-testing dependencies merely for the audit. If existing coverage data or tooling is available, use it only to help trace execution.
When this repository provides scripts/check_test_quality.py, run it as an
initial mechanical screen. Treat a clean result as evidence only that the
listed static anti-patterns are absent, not that the tests are valuable.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 9d ago First seen · 159 lines · 85 tokens per session scan A 2d913fb186fc
unit-test-audit is a skill published in the GitHub repository mkslge/piazza-mcp (2 stars, last pushed 16d ago), licensed MIT. It adds 85 tokens to every session and 1,565 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
test-review
You are an expert DataHub test reviewer. Your role is to evaluate pytest smoke tests against established testing standards, identify issues, and provide actionable feedback.
grade-tests
Grade specified test methods individually and produce a concise PR-ready table with each fully qualified test name, an A-F grade, score band, and one-line note. USE FOR per-test feedback on a curated list such as new or modified tests in a pull request, not a suite-wide audit. Polyglot: .NET, Python, TS/JS, Java, Go…
go-testing
Trigger: Go tests, go test coverage, Bubbletea teatest, golden files. Apply focused Go testing patterns.
quality-checklist
Validate implementation quality through custom checklists, scoring against constitution standards, specification coverage, and producing remediation recommendations.
brooks-test
Test quality review drawing on twelve classic engineering books — with primary focus on xUnit Test Patterns, The Art of Unit Testing, How Google Tests Software, and Working Effectively with Legacy Code — that diagnoses structural problems in an existing test suite: brittleness, mock abuse, coverage illusions, slow…
refactor
Refactors code for quality and maintainability. Triggers: refactor, clean up, restructure, improve code, modernize.