audit-tests

audit-tests is a skill for Claude Code, Codex from JHostalek/dotclaude. It costs 80 tokens per session (2,969 once invoked), scanned A, original, CC0-1.0.

A review and improvement workflow for an existing automated test suite. It checks whether tests can detect important defects, removes tests that add little value, strengthens weak tests, and adds coverage where it protects real behavior.

In plain words
What is it for?
Use it to audit unit, component, contract, integration, end-to-end, and production-validation tests. It helps match each important system risk with an appropriate test.
Why use it?
It focuses on trustworthy evidence rather than simply increasing the number of tests or the percentage of code covered. This helps expose untested risks while keeping the suite smaller and easier to maintain.

Skill for Claude CodeCodex

Part of the jhostalek-skills plugin — 32 skills, 12 agents 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 skills/jhostalek/dotclaude/audit-tests
Any agent
npx skills add JHostalek/dotclaude --skill audit-tests
Clone the repo
git clone --depth 1 https://github.com/JHostalek/dotclaude

Made for: Claude Code, Codex.

Or install jhostalek-skills, the plugin that ships this one along with the rest of its 32 skills, 12 agents.

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/jhostalek/dotclaude/audit-tests.svg)](https://agentmods.dev/skills/jhostalek/dotclaude/audit-tests)
Your own site
<a href="https://agentmods.dev/skills/jhostalek/dotclaude/audit-tests"><img src="https://agentmods.dev/badge/skills/jhostalek/dotclaude/audit-tests.svg" alt="Measured on agentmods" height="20"></a>
Per session 80 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,969 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 $0.00080 $0.02969
Opus 5 $0.00040 $0.01484
Sonnet 5 $0.00016 $0.00594
Haiku 4.5 $0.00008 $0.00297

Measured 5d ago against content hash c9a04ffe6c4e, 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.

skills/audit-tests/SKILL.md · 159 lines

How it starts

The opening of the file, as written. The whole thing — 159 lines — stays where its author put it; the contents beside it link to each section on GitHub.

!cat "${CLAUDE_SKILL_DIR}/../shared/audit-workflow.md"

Run as the tests dimension. Determine whether the suite gives proportionate, trustworthy evidence that the system preserves intended behavior through change. The goal is not more tests or higher coverage; it is strong defect detection with the smallest maintainable suite.

Work top-down

Start from the system's obligations, not test filenames or coverage reports:

  1. Reconstruct intended behavior and architecture from production code, schemas, configuration, interfaces, migrations, docs, incidents, and tests. Identify critical user journeys, domain invariants, state machines, component and trust boundaries, external contracts, lifecycle transitions, operational modes, and the consequences of failure.
  2. Map each material risk to the cheapest test level that can falsify the relevant claim with realistic collaborators. Trace evidence across unit, component, contract, integration, end-to-end, and production-validation layers rather than assuming one layer is inherently superior.
  3. Evaluate the suite as a system: whether its oracles can detect meaningful defects, its environments exercise the real path, failures are attributable, state is isolated, and important cross-component or temporal behavior survives composition.
  4. Apply the baseline across every applicable boundary and lifecycle. Expand it for domain-specific risks such as financial ledgers, authorization, safety-critical control, distributed workflows, data pipelines, UI accessibility, mobile/offline behavior, infrastructure, or AI systems.

Do not infer protection from a test's name, existence, passing status, coverage line, framework, fixture, mock, snapshot, helper abstraction, or familiar pattern. Verify that the exact production path runs, the oracle would fail for a plausible defect, and the test environment preserves the conditions on which the behavior depends. Collect candidates widely before applying any noise filter.

Mandatory test review baseline

Read the full file on GitHub · 159 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 · 159 lines · 80 tokens per session scan A c9a04ffe6c4e

Subscribe to this mod's changes

audit-tests is a skill published in the GitHub repository JHostalek/dotclaude (11 stars, last pushed today), licensed CC0-1.0. It adds 80 tokens to every session and 2,969 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.