piazza-mcp: Skill for Codex

.agents/skills/unit-test-audit/SKILL.md

unit-test-audit is a skill for Codex from mkslge/piazza-mcp. It costs 85 tokens per session (1,565 once invoked), scanned A, original, MIT.

A review process for judging whether unit tests are useful and trustworthy. Unit tests check small pieces of code in isolation.

In plain words
What is it for?
Use it to audit an existing unit-test suite and produce an evidence-based list of tests to remove, rewrite or combine.
Why use it?
It finds tests that are useless, duplicated, misleading, fragile or too weak, so the test suite gives clearer evidence about the code.

Skill for Codex

Written for Codex: agents/openai.yaml present. Also seen: installed under .agents/ (shared by several agents).

This is mkslge/piazza-mcp's own configuration. It tells Codex how to work on piazza-mcp itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything piazza-mcp configures →

Reuse

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.

Copy the file
curl -O https://raw.githubusercontent.com/mkslge/piazza-mcp/main/.agents/skills/unit-test-audit/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/mkslge/piazza-mcp

Made for: Codex.

Wrote 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.

agentmods badge for unit-test-audit

README.md
[![agentmods](https://agentmods.dev/badge/skills/mkslge/piazza-mcp/unit-test-audit/github.svg)](https://agentmods.dev/skills/mkslge/piazza-mcp/unit-test-audit)
Your own site
<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.

agentmods 80×15 button for unit-test-audit

Your own site · 80×15
<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>
Per session 85 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,565 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce 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

Measured 9d ago against content hash 2d913fb186fc, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

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.

.agents/skills/unit-test-audit/SKILL.md · 159 lines

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.

Read the full file on GitHub · 159 lines

Files

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.

Changes

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.

  1. 9d ago First seen · 159 lines · 85 tokens per session scan A 2d913fb186fc

Subscribe to this mod's changes

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.

Related

Other skills, from other repositories