audit-tests

audit-tests is a skill for Claude Code, Codex from TalonT-Org/AutoSkillit. It costs 79 tokens per session (4,474 once invoked), scanned A, original, MIT.

A review of a software test suite, which is the collection of automated checks for a codebase. It looks at whether tests genuinely verify the behavior they claim to check and whether they are organized safely.

In plain words
What is it for?
Use it to find useless or duplicate tests, weak assertions, over-mocking, misplaced tests, parallel-run safety problems, and broken test-path filters.
Why use it?
It helps find tests that add little value, make weak checks, rely too heavily on mocks, or are unsafe to run in parallel. It produces an improvement plan instead of changing the tests.

Skill for Claude CodeCodex

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 skills/talont-org/autoskillit/audit-tests
Any agent
npx skills add TalonT-Org/AutoSkillit --skill audit-tests
Clone the repo
git clone --depth 1 https://github.com/TalonT-Org/AutoSkillit

Made for: Claude Code, Codex.

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-tests

README.md
[![agentmods](https://agentmods.dev/badge/skills/talont-org/autoskillit/audit-tests.svg)](https://agentmods.dev/skills/talont-org/autoskillit/audit-tests)
Your own site
<a href="https://agentmods.dev/skills/talont-org/autoskillit/audit-tests"><img src="https://agentmods.dev/badge/skills/talont-org/autoskillit/audit-tests.svg" alt="Measured on agentmods" height="20"></a>
Per session 79 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,474 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 $0.00079 $0.04474
Opus 5 $0.00039 $0.02237
Sonnet 5 $0.00016 $0.00895
Haiku 4.5 $0.00008 $0.00447

Measured 5d ago against content hash bf489fd8aa77, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

audit-tests 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 5d 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.

.claude/skills/audit-tests/SKILL.md · 293 lines

How it starts

The opening of the file, as written. The whole thing — 293 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Test Suite Audit Skill

Audit the test suite to identify useless tests, consolidation opportunities, quality issues, and tests that don't validate what they claim. Produces an actionable improvement plan with explanations.

When to Use

  • User says "audit tests", "audit test suite", "review tests"
  • User wants "test quality check" or "test cleanup"
  • User asks to "find useless tests" or "consolidate tests"

Intended Test Directory Structure

The test suite mirrors the source sub-package hierarchy rather than using a type-based unit/integration split — the project's IL-0–IL-3 layer boundaries already encode isolation levels. Each sub-package gets its own test directory. Cross-cutting concerns go in dedicated directories:

tests/
├── conftest.py          # Shared: MockSubprocessRunner, tool_ctx fixture (wired via make_context)
├── CLAUDE.md            # xdist safety guidelines
├── core/                # IL-0: tests for autoskillit/core/ (io, logging, paths, types, protocols)
├── config/              # IL-1: tests for autoskillit/config/
├── pipeline/            # IL-1: tests for autoskillit/pipeline/ (audit, gate, context, tokens)
├── execution/           # IL-1: tests for autoskillit/execution/ (db, github, headless, process, quota, session, testing)
├── workspace/           # IL-1: tests for autoskillit/workspace/ (cleanup, clone, skills)
├── recipe/              # IL-2: tests for autoskillit/recipe/ (io, loader, schema, validator, rules, smoke)
├── migration/           # IL-2: tests for autoskillit/migration/ (engine, loader, store)
├── server/              # IL-3: tests for autoskillit/server/ (_factory, git, helpers, tools_*)
├── cli/                 # IL-3: tests for autoskillit/cli/
├── arch/                # Cross-cutting: AST architecture enforcement, import contracts, layer rules
├── contracts/           # Cross-cutting: instruction surface, MCP/API surface, version consistency
└── infra/               # Cross-cutting: CI/dev config checks (.pre-commit, .gitleaks, .github/)

Read the full file on GitHub · 293 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. 5d ago First seen · 293 lines · 79 tokens per session scan A bf489fd8aa77

Subscribe to this mod's changes

audit-tests is a skill published in the GitHub repository TalonT-Org/AutoSkillit (5 stars, last pushed 6d ago), licensed MIT. It adds 79 tokens to every session and 4,474 once invoked, about $0.0004 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 2026-08-31.

Related

Other skills, from other repositories

blockchain-testing

Use this skill when asked about testing smart contracts, Foundry tests, Hardhat tests, fuzz testing, invariant testing, property-based testing, formal verification, audit preparation, integration testing for dApps, and blockchain testing patterns. Covers Foundry cheatcodes, Echidna fuzzing, Certora verification…

j4flmao/agent-skills · 117 tokens

badmodel

Generates unit tests for changed functions. Use when the user asks to add tests or mentions coverage for newly written code.

ncoevoet/claude-markdown-health-check · 27 tokens

tester

Generates unit tests for changed functions. Use when the user asks to add tests or mentions coverage for newly written code.

ncoevoet/claude-markdown-health-check · 26 tokens

no-silent-pass

Write Python whose failures are visible and checks that actually fire — distinct sentinels for success and error, filters that narrow to nothing without reading as "all clear", output never discarded on a non-zero exit, and selftest cases proven red before they are trusted (mutate the fix, mutate it the other way too…

AleksandarBisevac/claude-plugins · 143 tokens

package-testing

Use this skill when writing, editing, fixing, or reviewing package tests with Pest 4/5 and Orchestra Testbench, including TDD, feature tests, unit tests, type coverage, arch tests, workbench behavior, commands, routes, config, migrations, and publishable resources.

MrPunyapal/laravel-auditor · 61 tokens

run-helix-tests

Submit and monitor .NET MAUI unit tests on Helix infrastructure. Supports running XAML, Resizetizer, Core, Essentials, and other unit test projects on distributed Helix queues.

dotnet/maui · 45 tokens