audit-test

audit-test is a command for Claude Code from dykyi-roman/awesome-claude-code. It costs 24 tokens per session (2,009 once invoked), scanned A, original, MIT.

A test-quality review command that examines automated tests for coverage gaps, test smells, naming problems, and isolation issues.

In plain words
What is it for?
Use it to review a test directory, identify quality problems, and get recommendations or generated fixes.
Why use it?
It shows where tests may miss important behaviour or become unreliable and difficult to maintain.

Command for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: model in frontmatter.

Part of the acc plugin — 101 skills, 26 commands, 68 agents, 1 hook shipped together

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add commands/dykyi-roman/awesome-claude-code/audit-test
Clone the repo
git clone --depth 1 https://github.com/dykyi-roman/awesome-claude-code

Made for: Claude Code.

Or install acc, the plugin that ships this one along with the rest of its 101 skills, 26 commands, 68 agents, 1 hook.

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 audit-test

README.md
[![agentmods](https://agentmods.dev/badge/commands/dykyi-roman/awesome-claude-code/audit-test.svg)](https://agentmods.dev/commands/dykyi-roman/awesome-claude-code/audit-test)
Your own site
<a href="https://agentmods.dev/commands/dykyi-roman/awesome-claude-code/audit-test"><img src="https://agentmods.dev/badge/commands/dykyi-roman/awesome-claude-code/audit-test.svg" alt="Measured on agentmods" height="20"></a>
Per session 24 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,009 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00024 $0.02009
Opus 5 $0.00012 $0.01005
Sonnet 5 $0.00005 $0.00402
Haiku 4.5 $0.00002 $0.00201

Measured 2d ago against content hash 390e84640c1e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

audit-test 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 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.

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.

commands/audit-test.md · 233 lines

How it starts

The opening of the file, as written. The whole thing — 233 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Test Quality Audit

Perform a comprehensive test quality audit with actionable improvement recommendations.

Input Parsing

Parse $ARGUMENTS to extract path, level, and optional meta-instructions:

Format: <path> [level] [-- <meta-instructions>]

Arguments:
- path: Target directory or file (required, default: current directory)
- level: Audit depth - quick|standard|deep (optional, default: standard)
- -- meta-instructions: Additional focus areas or filters (optional)

Examples:
- /acc:audit-test tests/
- /acc:audit-test tests/ deep
- /acc:audit-test tests/ quick
- /acc:audit-test tests/ -- focus on Domain layer only
- /acc:audit-test tests/ deep -- focus on test smells
- /acc:audit-test tests/ -- level:deep (backward compatible)

Parsing rules:

  1. Split $ARGUMENTS by -- (space-dash-dash-space)
  2. First part = positional arguments, Second part = meta-instructions
  3. In positional arguments, check if last word is a valid level (quick|standard|deep)
  4. If level found → extract it; remaining = path
  5. Also accept level:quick|standard|deep in meta-instructions (backward compatibility)
  6. Priority: positional > meta-instruction > default (standard)
  7. Default path: current directory (if empty)

Pre-flight Check

  1. Verify the path exists:

    • If $ARGUMENTS is empty, audit current directory
    • If path doesn't exist, report error and stop
  2. Verify test infrastructure:

    • Check for phpunit.xml or phpunit.xml.dist
    • Check for tests/ directory
    • Check for PHPUnit in composer.json (require-dev)
    • If no test infrastructure found, report and suggest /acc:generate-test
  3. Check test tooling:

    • Look for coverage configuration (Xdebug/PCOV)
    • Note Pest, Codeception, or other frameworks if present

Audit Levels

Level is an optional positional parameter. Default: standard.

Level Scope What's Checked
quick Coverage count Class/method coverage percentage, critical untested paths
standard Full analysis Coverage gaps, test smells (15 antipatterns), naming, isolation, quality metrics
deep Standard + cross-analysis Standard + cross-test dependencies, test execution order sensitivity, fixture analysis

Read the full file on GitHub · 233 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.

  1. 2d ago First seen · 233 lines · 24 tokens per session scan A 390e84640c1e

Subscribe to this mod's changes

audit-test is a command published in the GitHub repository dykyi-roman/awesome-claude-code (96 stars, last pushed 20d ago), licensed MIT. It adds 24 tokens to every session and 2,009 once invoked, about $0.0001 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 2026-09-03.