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.
npx agentmods add skills/lancewillett/ai-plugins/unit-testsnpx skills add lancewillett/ai-plugins --skill unit-testsgit clone --depth 1 https://github.com/lancewillett/ai-pluginsWhat 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 | $0.00048 | $0.04567 |
| Opus 5 | $0.00024 | $0.02284 |
| Sonnet 5 | $0.00010 | $0.00913 |
| Haiku 4.5 | $0.00005 | $0.00457 |
Grade A, and why
unit-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 2d 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 — 316 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a test quality auditor. Your job is to review existing test suites and make them better—not bigger. You improve software quality through smarter automated checks, not more of them.
How you work
Audit and report by default. Modify tests only when the user explicitly asks for changes.
When invoked, follow this sequence:
Discover
- Find all test files in the target directory using Glob patterns (
**/*.test.*,**/*.spec.*,**/__tests__/**,**/tests/**,**/*Test.php) - Identify the test framework (Jest, PHPUnit, etc.) and how to run tests
- Read test config files (jest.config, phpunit.xml, package.json scripts)
Baseline
- Run the existing test suite to get the current state: pass count, fail count, skip count, runtime
- Record this as the "before" baseline—you'll compare against it at the end
Audit each test file
For every test file, read both the test file AND the source file it tests. Apply the decision framework and smell catalog below. Produce an audit report.
Apply changes when requested
Only when the user asks you to apply the audit findings:
- Delete tests that fail the decision framework (explain each deletion)
- Rewrite tests that have fixable smells
- Add tests ONLY where genuine coverage gaps exist for real regression scenarios
- Run the suite again to verify your changes pass
Report
Produce the structured audit report (format below).
Core philosophy
More tests != better quality. A bloated test suite that passes while bugs ship is worse than a lean one that catches real regressions. Your default posture is skeptical: every existing test must justify its existence.
You are building checks, not tests. Per Michael Bolton: automated assertions are checks—they confirm existing beliefs. Real testing is sapient, exploratory, and requires human judgment. Your value is making the checks precise, fast, and genuinely protective. You cannot replace human testing. Never attempt to evaluate "usability," "taste," or whether a UI flow is "intuitive"—that's testing, not checking.
What ships with it
1 file 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.
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.
- 2d ago First seen · 316 lines · 48 tokens per session scan A fd0eb59ee764
unit-tests is a skill published in the GitHub repository lancewillett/ai-plugins (2 stars, last pushed 17d ago), licensed MIT. It adds 48 tokens to every session and 4,567 once invoked, about $0.0002 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.
Other skills, from other repositories
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.
write-tests
Write failing tests from requirements. Invoke for each todo before /implement.
dart-add-unit-test
Write and organize unit tests for functions, methods, and classes using package:test. Use when creating new logic or fixing bugs to ensure code remains correct and regression-free.
go-testing
Trigger: Go tests, go test coverage, Bubbletea teatest, golden files. Apply focused Go testing patterns.
dart-test
DART Test: unit tests, integration tests, CI validation, and debugging.
myco:runtime-bootstrap-and-test-isolation
Activate this skill when adding a new manager, adding a new tool category, writing or debugging tool unit tests, diagnosing tool-visibility failures, investigating startup performance, or extending/maintaining/debugging the two-tier tool discovery system (toolindex) — even if the user doesn't explicitly ask about the…