A test-quality audit for unit and integration test files. It checks each test against a detailed checklist and known anti-patterns, then assigns a quality tier.

Use it to review test quality across a project, directory, or selected files, including end-to-end tests when requested.

It helps reveal tests that do not cover real behavior, rely on fake or unused mocks, or leave public code untested. This is useful after writing many tests or before a release.

test-audit — Skill for Claude Code by greglas75/zuvo

Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo

git clone --depth 1 https://github.com/greglas75/zuvo

agentmods

npx agentmods add skills/greglas75/zuvo/test-audit

Made for: Claude Code.

Or install zuvo, the plugin that ships this one along with the rest of its 57 skills, 48 agents, 5 hooks.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/greglas75/zuvo/test-audit/github.svg)](https://agentmods.dev/skills/greglas75/zuvo/test-audit)

Your own site

<a href="https://agentmods.dev/skills/greglas75/zuvo/test-audit"><img src="https://agentmods.dev/badge/skills/greglas75/zuvo/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/greglas75/zuvo/test-audit"><img src="https://agentmods.dev/badge/skills/greglas75/zuvo/test-audit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 100 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 12,576 The whole file, excluding the scripts and references it only reads on demand.

Security scan B 1 finding. 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.

Model	Per session	Once invoked
Fable 5.1	$0.00100	$0.12576
Opus 5.5	$0.00040	$0.05030
Sonnet 5.5	$0.00020	$0.02515
Haiku 4.5	$0.00010	$0.01258

Measured 2d ago against content hash 7abcec930d44, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade B, and why

test-audit scanned grade B with 1 finding 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 2d 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.

Recursive force deletemediumDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

rm -rf zuvo/audits/.test-audit-batch

Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.

skills/test-audit/SKILL.md · 752 lines

How it starts

The opening of the file, as written. The whole thing — 752 lines — stays where its author put it; the contents beside it link to each section on GitHub.

zuvo:test-audit — Test Quality Triage

Systematic evaluation of unit and integration test files through the Q1-Q25 binary checklist and AP anti-pattern catalog. Each test file is paired with its production source, scored against behavioral coverage standards, and assigned a tier.

Scope: Unit and integration tests only. E2E tests (*/e2e/*, *.e2e.*) are excluded by default. Use --include-e2e to include them.

When to use: After mass test writing, when test quality is uncertain, before releases, when test failures are hard to diagnose, periodic health check. Out of scope: Single-file code review (use zuvo:review), writing new tests (use zuvo:write-tests), fixing systematic anti-patterns across many files (use zuvo:fix-tests).

Argument Parsing

Argument	Effect
`all`	Audit every test file in the project
`[path]`	Audit test files under a specific directory
`[file]`	Audit a single test file with full evidence (forces deep mode)
`[file file2 …]`	Audit exactly the listed test files (space-separated, forces deep mode) — the form the Test Quality Gate (`../../shared/includes/test-quality-gate.md`, called from build/refactor/execute/write-tests/write-e2e) uses to scope to touched files
`--deep`	Collect evidence and fix recommendations for every file
`--quick`	Binary pass/fail only, skip evidence
`--include-e2e`	Include E2E test files in scope
`--details`	Save per-file reports to `zuvo/audits/test-audit-details/`
`--commit=ask\|auto\|off`	Commit behavior after fix workflow (default: `ask`)
`--base <ref>`	Score Q7/Q11 against the production lines changed since `<ref>` (the Test Quality Gate passes the run's base); branches outside are listed as `Out-of-scope gaps`, not scored. Without it, the whole production file
`--read-only`	Report only: skip Phases 4-6 (coverage.md/backlog.md writes) and Phase 7; no repo mutation beyond the `zuvo/audits/` report

Default: all --quick --commit=ask

Read the full file on GitHub · 752 lines

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.

2d ago Changed · +6 lines 7abcec930d44
8d ago Changed · +8 lines 751e7fd625fe
10d ago Changed · +2 lines a8284dcaeee4
18d ago Changed · +246 lines 9f7a026e8e18
20d ago Changed · -193 lines f602b4d45a34
1mo ago Changed · +35 lines ffca0e9c8799
1mo ago First seen · 648 lines · 100 tokens per session scan B 9c90f587c33c

Subscribe to this mod's changes

test-audit is a skill published in the GitHub repository greglas75/zuvo (8 stars, last pushed today), licensed MIT. It adds 100 tokens to every session and 12,576 once invoked, about $0.0004 per session on Opus 5.5. A static security scan graded it B with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.

Claude Code Code review Code/Test audits E2E testing Testing Unit testing ai-coding claude-code-plugin code-quality codex

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…

hyhmrright/brooks-lint · 161 tokens

testloop

Implementation-test-fix feedback loop.

samibs/skillfoundry · 10 tokens

ai-agent-bench

Compare Claude Code and Codex on the same code task, with isolated worktrees, common checks, time, and cost.

reidemeister94/development-skills · 30 tokens

ring:running-dev-cycle-frontend

Running the frontend (React/Next.js/TS) dev cycle from a plan.md (ring:writing-plans format; legacy tasks.md only for in-flight cycles) or backend handoff: drives frontend agents through Gate 0 TDD plus accessibility/visual/E2E/perf checks, Gate 7 parallel review, and Gate 8 user validation, with rolling-wave phase…

LerianStudio/ring · 114 tokens