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 skills add mikeparcewski/wicked-garden --skill qe-coverage-archaeologistgit clone --depth 1 https://github.com/mikeparcewski/wicked-gardenWrote 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/skills/mikeparcewski/wicked-garden/qe-coverage-archaeologist)<a href="https://agentmods.dev/skills/mikeparcewski/wicked-garden/qe-coverage-archaeologist"><img src="https://agentmods.dev/badge/skills/mikeparcewski/wicked-garden/qe-coverage-archaeologist/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/skills/mikeparcewski/wicked-garden/qe-coverage-archaeologist"><img src="https://agentmods.dev/badge/skills/mikeparcewski/wicked-garden/qe-coverage-archaeologist.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 | $0.00072 | $0.00407 |
| Opus 5.5 | $0.00029 | $0.00163 |
| Sonnet 5.5 | $0.00014 | $0.00081 |
| Haiku 4.5 | $0.00007 | $0.00041 |
Grade A, and why
wicked-garden-qe-coverage-archaeologist 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.
What it actually says
Coverage Archaeologist
Legacy code accumulates untested paths. You dig through the layers and surface what's both untested and important.
Signals
- Coverage — lines not hit by any test
- Blame age — code that's been there >2 years with no recent touches often has no tests because it was written before tests mattered
- Call-graph fan-in — untested code that many callers depend on
- Complexity — cyclomatic complexity + untested = high risk
- Error-path — try/catch blocks whose
catchis never exercised - Feature flag dead-ends — both sides of a flag should be tested
Prioritization
Rank findings by impact × exposure:
- Impact: revenue path, auth, data integrity, security
- Exposure: fan-in × traffic (library call count; HTTP path qps if known)
Top 10 findings beat 500 findings. Noise hides signal.
Process
- Ingest coverage report (lcov / cobertura / native)
- Annotate with
git blameage - Annotate with call-graph (tree-sitter or language server)
- Rank by the heuristic above
- Produce a top-N list with one-line rationale each
Output
A ranked list: file:line | reason | suggested test | effort (S/M/L).
Hand off to wicked-garden-qe-test-automation-engineer for the follow-up.
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 Changed · -7 lines d8be5eb08789
- 1mo ago Changed · +2 lines 2570fbf8b39e
- 1mo ago First seen · 53 lines · 72 tokens per session scan A 51107d86ddae
wicked-garden-qe-coverage-archaeologist is a skill published in the GitHub repository mikeparcewski/wicked-garden (9 stars, last pushed today), licensed MIT. It adds 72 tokens to every session and 407 once invoked, about $0.0003 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 2026-09-03.
Other skills, from other repositories
brooks-test
Test quality review drawing on twelve classic engineering books — with primary focus on xUnit Test Patterns, The Art of Unit Testing, How Google Tests Software, and Working Effectively with Legacy Code — that diagnoses structural problems in an existing test suite: brittleness, mock abuse, coverage illusions, slow…
testing-laravel
Writes Laravel tests using PHPUnit. Use when "write tests", "add tests", "phpunit", "laravel test", "feature test", "unit test", "mock", "factory", or testing controllers, models, services, actions, jobs, artisan commands, or API endpoints.
testing-react
Writes React/TypeScript tests using Vitest and React Testing Library. Use when "write react tests", "vitest", "component test", "hook test", "RTL", "testing library", "snapshot test", or testing React components, hooks, and utilities.
write-tests
Write tests for existing production code. Processes ONE file at a time through a full pipeline: analyze, inventory (frozen BEFORE writing), write, executable coverage gate, verify, blind coverage audit, adversarial review, log. Uses CodeSift for discovery and analysis when available. Modes: [path] (specific target)…
Component Test Scaffold (Next.js)
Generate React/Next.js component test skeletons (RTL) from specifications.
Test Scaffold (Laravel/PHPUnit)
Generate PHP/Laravel (PHPUnit) test skeletons from specifications.