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.
git clone --depth 1 https://github.com/lancewillett/ai-pluginsWrote 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.
[](https://agentmods.dev/commands/lancewillett/ai-plugins/audit-tests)<a href="https://agentmods.dev/commands/lancewillett/ai-plugins/audit-tests"><img src="https://agentmods.dev/badge/commands/lancewillett/ai-plugins/audit-tests/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.
<a href="https://agentmods.dev/commands/lancewillett/ai-plugins/audit-tests"><img src="https://agentmods.dev/badge/commands/lancewillett/ai-plugins/audit-tests.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00023 | $0.00592 |
| Opus 5.5 | $0.00009 | $0.00237 |
| Sonnet 5.5 | $0.00005 | $0.00118 |
| Haiku 4.5 | $0.00002 | $0.00059 |
Grade A, and why
audit-tests scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Audit tests
Run a test quality audit using the unit-tests agent. Reviews existing tests and makes them better—not bigger.
Target: "$ARGUMENTS" (defaults to current directory if empty)
Workflow
1. Determine scope
- If a path argument is provided, audit that specific file or directory
- If no argument, audit the current working directory
- Find all test files using standard patterns:
**/*.test.*,**/*.spec.*,**/__tests__/**(JavaScript)**/tests/**/*Test.php,**/*Test.php(PHP)
2. Launch audit
Use the Agent tool with subagent_type: "unit-tests" to launch the audit with a prompt like:
Audit the test suite at {target path}. Follow your full workflow:
1. Discover all test files
2. Run the existing suite for a baseline
3. Audit each test file against the decision framework and smell catalog
4. Produce the structured audit report
Target: {path}
If the user wants changes applied (not just a report), add:
After producing the audit report, apply the recommended changes:
- Delete tests that should be deleted (with explanations)
- Rewrite tests that have fixable smells
- Add tests only where genuine gaps exist
- Run the suite again to verify all changes pass
3. Present results
Show the structured audit report to the user. Highlight:
- Critical findings—tests that are actively hiding bugs (mock-testing-mocks, constructor drift, dodgers)
- Quick wins—tests to delete that add no value (framework testers, coverage chasers)
- Gaps—missing tests for high-risk code paths
4. Offer next steps
After the report, ask if the user wants to:
- Apply recommended changes (delete/rewrite/add)
- Focus on a specific file or smell type
Usage examples
Audit everything:
/unit-tests:audit-tests
Audit a specific directory:
/unit-tests:audit-tests src/components/__tests__
Audit a specific file:
/unit-tests:audit-tests tests/unit/UserServiceTest.php
What the agent does NOT do
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.
- 1mo ago First seen · 83 lines · 23 tokens per session scan A 115f1356f7cd
audit-tests is a command published in the GitHub repository lancewillett/ai-plugins (3 stars, last pushed 1mo ago), licensed MIT. It adds 23 tokens to every session and 592 once invoked, about $0.0001 per session on Opus 5.5. 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.
Other commands, from other repositories
prototype
You are building a proof-of-concept for the current Grainulator sprint. Read CLAUDE.md for sprint context and claims.json for existing research claims.
qa-changes
This skill should be used when the user asks to "QA a pull request", "test PR changes", "verify a PR works", "functionally test changes", or when an automated workflow triggers QA validation of code changes. Provides a structured methodology for setting up the environment, exercising changed behavior, and reporting…
verify
Run repository verification using the verification-loop skill.
constraints
A command for defining a project's quality standards through a short interview and a written CONSTRAINTS.md file. It records checks, thresholds, exceptions, and commands for enforcing them.
modernize-transform
Transform one legacy module to the target stack — idiomatic rewrite with behavior-equivalence tests.
test-coverage
Analyze test coverage and identify the highest-value gaps to fill.