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 agents/lancewillett/ai-plugins/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 | $0.04586 |
| Opus 5 | $0.00024 | $0.02293 |
| Sonnet 5 | $0.00010 | $0.00917 |
| Haiku 4.5 | $0.00005 | $0.00459 |
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 yesterday.
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 — 318 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 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.
- yesterday First seen · 318 lines · 48 tokens per session scan A 803ebe77a5cf
unit-tests is an agent published in the GitHub repository lancewillett/ai-plugins (2 stars, last pushed 16d ago), licensed MIT. It adds 48 tokens to every session and 4,586 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 agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.