A test-suite review process that checks whether tests genuinely test behavior, including whether they overuse mocks. It uses code-structure analysis and several review stages to produce an audit and may rewrite tests when quality checks fail.

Use it to audit test quality, detect mock-related violations, review test effectiveness, validate tests before merging, or inspect tests after they are written.

A test suite can look large while checking only mocked responses or missing important behavior. This identifies those weaknesses and applies its quality gates.

test-audit — Skill for Claude Code by QBall-Inc

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.

Any agent

npx skills add QBall-Inc/the-bulwark --skill test-audit

Clone the repo

git clone --depth 1 https://github.com/QBall-Inc/the-bulwark

Made for: Claude Code.

Or install the-bulwark, the plugin that ships this one along with the rest of its 30 skills, 17 agents, 6 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/qball-inc/the-bulwark/test-audit/github.svg)](https://agentmods.dev/skills/qball-inc/the-bulwark/test-audit)

Your own site

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

Per session 0 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 5,660 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. Third-party audits

NVIDIA SkillSpector warn 7 Sept 2026

SkillSpector: 1 finding, up to medium

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

medium MCP Rug Pull · line 523
npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.

Fix: Pin the version: npx @scope/[email protected]

How audits are shown

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	$0.00000	$0.05660
Opus 5	$0.00000	$0.02830
Sonnet 5	$0.00000	$0.01132
Haiku 4.5	$0.00000	$0.00566

Measured 10d ago against content hash 8279564b3c6f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

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 10d ago.

The scan reads SKILL.md. This mod also ships 4 executable files (scripts/data-flow-analyzer.ts, scripts/integration-mock-detector.ts, scripts/skip-detector.ts, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

skills/test-audit/SKILL.md · 556 lines

How it starts

The opening of the file, as written. The whole thing — 556 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Test Audit

User-facing entry point for test suite quality auditing. Orchestrates classification, mock detection, and synthesis stages to identify T1-T4 violations and trigger automatic rewrites when required.

When to Use This Skill

Load this skill when the user request matches ANY of these patterns:

Trigger Pattern	Example User Request
Test quality audit	"Audit my tests", "Check test quality", "Review test suite"
Mock detection	"Find mock violations", "Check for T1 violations", "Are my tests over-mocked?"
Test effectiveness	"How effective are my tests?", "Are my tests real or mocked?"
After writing tests	"I just wrote tests for X, can you audit them?"
CI/CD integration	"Add test audit to pipeline", "Validate tests before merge"

DO NOT use for:

Running tests (use just test)
Writing new tests (implement directly)
General code review (use code-review skill)
Debugging test failures (use issue-debugging skill)

Pre-Flight Gate (BLOCKING)

STOP. Before ANY analysis, you MUST acknowledge what this skill requires.

This skill uses a multi-stage pipeline with sub-agents. You are the orchestrator, NOT the executor.

What You MUST Do

Run Stage 0 AST scripts before any LLM stages:
- just verify-count {target} → /tmp/claude/ast-verify-count.json
- just skip-detect {target} → /tmp/claude/ast-skip-detect.json
- just ast-analyze {target} → /tmp/claude/ast-data-flow.json
Select mode based on file count and threshold (default 5)
Spawn sub-agents for each applicable stage:
- Stage 1 (Scale mode only): Classification → Task(subagent_type="general-purpose", model="haiku", ...)
- Stage 2: Mock Detection → Task(subagent_type="general-purpose", model="sonnet", ...)
- Stage 3: Synthesis → Task(subagent_type="general-purpose", model="sonnet", ...)
Write outputs to logs/:
- logs/test-classification-{YYYYMMDD-HHMMSS}.yaml (Scale mode only)
- logs/mock-detection-{YYYYMMDD-HHMMSS}.yaml
- logs/test-audit-{YYYYMMDD-HHMMSS}.yaml
- logs/diagnostics/test-audit-{YYYYMMDD-HHMMSS}.yaml

Read the full file on GitHub · 556 lines

Files

What ships with it

14 files 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.

10d ago First seen · 556 lines · 0 tokens per session scan A 8279564b3c6f

Subscribe to this mod's changes

test-audit is a skill published in the GitHub repository QBall-Inc/the-bulwark (8 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 5,660 tokens. 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.

Claude Code Code review TDD Testing ai-coding-assistant ai-governance anthropic claude-code-plugin claude-code-skills

enterprise-forge

Adversarial code review with mechanical checks, contract probing, and 5 adversarial lenses. Bugs recycle to contract for full TDD treatment. 3-fail circuit breaker prevents infinite loops. Use after enterprise-review.

anotherben/claude-harness · 48 tokens

uw-code-review

Pre-commit code quality review for Unity C# code. Checks against Rules, CODINGSTANDARDS.md, NAMINGCONVENTIONS.md, and GDD Gherkin test coverage. Use when code has been written and tests are passing but before committing. Runs automatically at Step 8.5 of /uw-cmd-implement-feature. Triggers on "review this code"…

IdoCohen560/claude-unity-game-studio · 124 tokens

Pair Programming

AI-assisted pair programming with multiple modes (driver/navigator/switch), real-time verification, quality monitoring, and comprehensive testing. Supports TDD, debugging, refactoring, and learning sessions. Features automatic role switching, continuous code review, security scanning, and performance optimization with…

airmcp-com/mcp-standards · 61 tokens

test-audit