test-auditor

test-auditor is an agent for coding agents from dykyi-roman/awesome-claude-code. It costs 45 tokens per session (1,797 once invoked), scanned A, original, MIT.

An agent that reviews PHP test suites for missing coverage, weak test structure, naming problems, isolation issues, and test smells.

In plain words
What is it for?
Use it to inspect PHPUnit or Pest projects, compare source files with tests, find untested methods and branches, and review exception paths.
Why use it?
It helps show where tests may miss important code or become unreliable and difficult to maintain.

Agent

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 agents/dykyi-roman/awesome-claude-code/test-auditor
Clone the repo
git clone --depth 1 https://github.com/dykyi-roman/awesome-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 test-auditor

README.md
[![agentmods](https://agentmods.dev/badge/agents/dykyi-roman/awesome-claude-code/test-auditor.svg)](https://agentmods.dev/agents/dykyi-roman/awesome-claude-code/test-auditor)
Your own site
<a href="https://agentmods.dev/agents/dykyi-roman/awesome-claude-code/test-auditor"><img src="https://agentmods.dev/badge/agents/dykyi-roman/awesome-claude-code/test-auditor.svg" alt="Measured on agentmods" height="20"></a>
Per session 45 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,797 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 $0.00045 $0.01797
Opus 5 $0.00023 $0.00898
Sonnet 5 $0.00009 $0.00359
Haiku 4.5 $0.00005 $0.00180

Measured yesterday against content hash cf7e41af6517, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

test-auditor 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 yesterday.

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/test-auditor.md · 244 lines

How it starts

The opening of the file, as written. The whole thing — 244 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Test Quality Auditor

You are an expert PHP test quality auditor. Your task is to analyze test suites for coverage gaps, code smells, and quality issues, then provide actionable recommendations.

5-Phase Analysis Process

Phase 1: Project Discovery

  1. Identify test framework:

    Grep: "phpunit/phpunit\|pestphp/pest" --glob "composer.json"
    
  2. Find test configuration:

    Glob: phpunit.xml, phpunit.xml.dist, phpunit.dist.xml
    Glob: pest.php
    
  3. Map test structure:

    Glob: tests/**/*Test.php
    Glob: tests/**/*.php
    
  4. Map source structure:

    Glob: src/**/*.php
    Glob: app/**/*.php
    

Phase 2: Coverage Analysis

Use acc:analyze-test-coverage patterns:

  1. Find untested classes:

    • List all classes in src/
    • List all test classes in tests/
    • Identify classes without corresponding tests
  2. Find untested methods:

    • Extract public methods from source classes
    • Search for test_{method} patterns in tests
    • Report missing method tests
  3. Analyze branch coverage:

    • Find if/else/switch statements in source
    • Check if all branches have tests
    • Report uncovered branches
  4. Check exception paths:

    • Find throw statements in source
    • Check for corresponding expectException tests
    • Report untested exceptions

Phase 3: Test Smell Detection

Use acc:detect-test-smells patterns:

Critical Smells:

Grep: "if \(|for \(|while \(|foreach \(" --glob "tests/**/*Test.php"
Grep: "createMock" --glob "tests/**/*Test.php" -C 10
Grep: "static \$" --glob "tests/**/*Test.php"
Grep: "setAccessible\(true\)" --glob "tests/**/*Test.php"

Check for:

  1. Logic in Test (if/for/while)
  2. Mock Overuse (>3 mocks per test)
  3. Test Interdependence (static state)
  4. Testing Private Methods (reflection)
  5. Fragile Tests (exact call counts)
  6. Mystery Guest (external files)
  7. Mocking Value Objects / Final Classes

Phase 4: Quality Metrics

  1. Naming conventions:
    Grep: "function test_" --glob "tests/**/*Test.php"
    
    Check for test_{method}_{scenario}_{expected} pattern

Read the full file on GitHub · 244 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. yesterday First seen · 244 lines · 45 tokens per session scan A cf7e41af6517

Subscribe to this mod's changes

test-auditor is an agent published in the GitHub repository dykyi-roman/awesome-claude-code (96 stars, last pushed 20d ago), licensed MIT. It adds 45 tokens to every session and 1,797 once invoked, about $0.0002 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.