test-effectiveness-auditor

test-effectiveness-auditor is a skill for Claude Code from wan-huiyan/claude-ecosystem-hygiene. It costs 177 tokens per session (3,730 once invoked), scanned B, original, MIT.

A test-audit method that checks whether automated tests would have caught bugs that previously happened. It replays known bugs against the code before their fixes.

In plain words
What is it for?
Use it to audit a test suite, investigate whether tests catch real bugs, and measure gaps using past incidents and CI results.
Why use it?
It replaces guesses based on test counts or code coverage with evidence from real bugs. This shows where the test suite missed important failures.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the test-effectiveness-auditor plugin — 1 skill shipped together

Good fit Use it to audit a test suite, investigate whether tests catch real bugs, and measure gaps using past incidents and CI results.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/wan-huiyan/claude-ecosystem-hygiene/test-effectiveness-auditor
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 wan-huiyan/claude-ecosystem-hygiene --skill test-effectiveness-auditor
Clone the repo
git clone --depth 1 https://github.com/wan-huiyan/claude-ecosystem-hygiene

Made for: Claude Code.

Or install test-effectiveness-auditor, the plugin that ships this one along with the rest of its 1 skill.

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-effectiveness-auditor

README.md
[![agentmods](https://agentmods.dev/badge/skills/wan-huiyan/claude-ecosystem-hygiene/test-effectiveness-auditor/github.svg)](https://agentmods.dev/skills/wan-huiyan/claude-ecosystem-hygiene/test-effectiveness-auditor)
Your own site
<a href="https://agentmods.dev/skills/wan-huiyan/claude-ecosystem-hygiene/test-effectiveness-auditor"><img src="https://agentmods.dev/badge/skills/wan-huiyan/claude-ecosystem-hygiene/test-effectiveness-auditor/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 test-effectiveness-auditor

Your own site · 80×15
<a href="https://agentmods.dev/skills/wan-huiyan/claude-ecosystem-hygiene/test-effectiveness-auditor"><img src="https://agentmods.dev/badge/skills/wan-huiyan/claude-ecosystem-hygiene/test-effectiveness-auditor.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 177 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,730 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00177 $0.03730
Opus 5 $0.00088 $0.01865
Sonnet 5 $0.00035 $0.00746
Haiku 4.5 $0.00018 $0.00373

Measured 11d ago against content hash 4ffbdefc9614, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade B, and why

test-effectiveness-auditor 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 11d ago.

The scan reads SKILL.md. This mod also ships 3 executable files (scripts/fetch_ci_history.sh, scripts/identify_incidents.py, scripts/replay_incident.sh), 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.

Recursive force deletemediumDestructive command

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

git -C "$PROJECT" worktree remove -f "$WT" 2>/dev/null || rm -rf "$WT"

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

plugins/test-effectiveness-auditor/SKILL.md · 248 lines

How it starts

The opening of the file, as written. The whole thing — 248 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Test Effectiveness Auditor v1.0

Answers the question: how helpful are our automated tests at catching bugs? Not by proxy metrics like coverage percent or test count, but by replaying real bugs that already happened and checking whether the test suite, as it stood just before the fix, actually failed on the buggy commit.

The honest baseline for "are tests worth it" is historical: bugs that made it to production despite the tests are the direct evidence of gaps; CI failures that forced a code change before merge are the direct evidence of catches. Everything else is speculation.

Why this matters

Most teams measure test health by coverage % (e.g. pytest --cov). Coverage tells you which lines executed, not whether any assertion would have failed when the behavior was wrong. A line can be 100% covered by a test that would pass under the bug. This audit inverts the question: take known bugs, rewind to the pre-fix commit, and observe whether the suite catches them.

Two methods, in priority order:

  1. Historical incident replay (primary signal) — for each documented bug, check out the pre-fix SHA in a worktree, run the suite, observe pass/fail, and classify.
  2. CI history analysis (secondary signal) — pull CI runs that forced a pre-merge change, classify by whether the failure represented a real logic/data/integration catch vs. noise (lint, formatting, flaky).

Mutation testing, test-layer ablation, and coverage-delta analysis are deliberately NOT in scope for v1. They're higher-cost methods whose ROI depends on first knowing the Method 1/2 baseline.

When to run

  • On demand when the user asks about test quality or effectiveness
  • After an incident to triage "tests should have caught this" vs "fundamentally hard to catch"
  • Before a test-investment cycle (writing more tests), to target the biggest gaps first
  • Proactively suggest after you notice: a team asking "should we write more tests?", a project with docs/findings/ or docs/issues/ accumulating, or a manager expressing doubt about CI ROI

Read the full file on GitHub · 248 lines

Files

What ships with it

6 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.

  1. 11d ago First seen · 248 lines · 177 tokens per session scan B 4ffbdefc9614

Subscribe to this mod's changes

test-effectiveness-auditor is a skill published in the GitHub repository wan-huiyan/claude-ecosystem-hygiene (1 stars, last pushed 25d ago), licensed MIT. It adds 177 tokens to every session and 3,730 once invoked, about $0.0009 per session on Opus 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 2026-08-31.

Related

Other skills, from other repositories

improve-code-quality

Guided journey from a working-but-untested vibe-coded prototype to a production-ready product with tests, clean structure, a business-rules boundary, and resilience at scale. Orchestrates nine skills phase by phase - working-with-legacy-code, clean-code, refactoring-patterns, software-design-philosophy…

wondelai/skills · 227 tokens

working-with-legacy-code

Safely change and test untested codebases using Feathers' "Working Effectively with Legacy Code". Use when the user mentions "legacy code", "no tests", "untested codebase", "how do I test this", "seams", "characterization tests", "golden master", "sprout method", "afraid to change this code", "monster method"…

wondelai/skills · 188 tokens

cloudflare-workers-testing

Comprehensive testing guide for Cloudflare Workers using Vitest and @cloudflare/vitest-pool-workers. Use for test setup, binding mocks (D1/KV/R2/DO), integration tests, or encountering test failures, mock errors, coverage issues.

secondsky/claude-skills · 57 tokens

api-testing

HTTP API testing for TypeScript (Supertest) and Python (httpx, pytest). Test REST APIs, GraphQL, request/response validation, authentication, and error handling.

secondsky/claude-skills · 39 tokens

bun-jest-migration

Use when migrating from Jest to Bun's test runner, import compatibility, mocks, and config.

secondsky/claude-skills · 25 tokens

bun-test-lifecycle

Use for test lifecycle hooks: beforeAll, afterAll, beforeEach, afterEach, fixtures, preload.

secondsky/claude-skills · 27 tokens