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-flaky-test-huntergit 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-flaky-test-hunter)<a href="https://agentmods.dev/skills/mikeparcewski/wicked-garden/qe-flaky-test-hunter"><img src="https://agentmods.dev/badge/skills/mikeparcewski/wicked-garden/qe-flaky-test-hunter/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-flaky-test-hunter"><img src="https://agentmods.dev/badge/skills/mikeparcewski/wicked-garden/qe-flaky-test-hunter.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 | $0.00240 | $0.03114 |
| Opus 5.5 | $0.00096 | $0.01246 |
| Sonnet 5.5 | $0.00048 | $0.00623 |
| Haiku 4.5 | $0.00024 | $0.00311 |
Grade A, and why
wicked-garden-qe-flaky-test-hunter scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 17d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 272 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Flaky Test Hunter
Flaky tests are worse than no tests — they train everyone to ignore failures. You find them, classify them by root cause, and either fix them or quarantine them with an owner and a deadline. You never propose "add retry" as a fix. Retry masks the bug; you name the bug.
Runtime
Script-backed steps use the wicked-garden launcher: wicked-garden run <plugin-root-relative path, e.g. scripts/…> [args]. It is on PATH after npm i -g wicked-garden; otherwise use npx wicked-garden run …; inside a wicked-crew run it is "$WICKED_GARDEN_ROOT/scripts/wicked-garden".
If none of these is available, or Python 3 is missing, skip the script-backed step, say so, and follow the manual alternative where one is given next to it — never invent the script's output.
Relative paths in this skill are relative to the directory that contains this SKILL.md.
1. Inputs
- Scenario file path OR
scenario_id(UUID) — you accept either. If only the path is given, resolve the id from DomainStore (store.search("scenarios", { source_path: <path> })→ pick most recent). run_id— currentrunsrow; definesEVIDENCE_DIR..wicked-qe/wicked-qe.db— historicalverdictsrows. Read-only via the oracle pattern (see §2). Do not read it unless it exists..wicked-qe/evidence/<run_id>/context.md— optional; may declare a custom window (flake_window_days: 30) or a quarantine policy override.- Repeat-count — default 100 for local repro; lowered to 25 if the
scenario's frontmatter declares
timeout: > 60s(compute budget).
2. Tool invocation
Historical query (read-only via sqlite3 CLI)
# 14-day verdict history for this scenario — mirrors the oracle's
# last_verdict_for_scenario pattern but windowed. Uses sqlite3's
# .parameter mechanism so the scenario id is bound, not interpolated.
sqlite3 -json ".wicked-qe/wicked-qe.db" <<EOF > "${EVIDENCE_DIR}/verdict-history.json"
.parameter set :id "${SCENARIO_ID}"
SELECT v.verdict, v.reason, v.created_at, r.status AS run_status
FROM verdicts v
JOIN runs r ON v.run_id = r.id
JOIN scenarios s ON r.scenario_id = s.id
WHERE s.id = :id
AND v.created_at >= datetime('now', '-14 days')
AND v.deleted = 0
ORDER BY v.created_at DESC;
EOF
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.
- 17d ago Changed · +2 lines 10828d54f5a4
- 1mo ago Changed · -5 lines 0bf8c3a4cdca
- 1mo ago Changed · +7 lines 627e42c79ea6
- 1mo ago First seen · 268 lines · 240 tokens per session scan A 294b895bed64
wicked-garden-qe-flaky-test-hunter is a skill published in the GitHub repository mikeparcewski/wicked-garden (9 stars, last pushed today), licensed MIT. It adds 240 tokens to every session and 3,114 once invoked, about $0.0010 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
fix-bug
Diagnoses and fixes bugs using a test-first workflow (reproduce, diagnose, fix). Use this skill whenever the user reports a bug, describes unexpected behavior, or asks to investigate or fix a defect. Even if the user says "something's broken", "this isn't working", "fix this bug", or "why does X happen", load this…
Vitest Mock Isolation Review
Detects Vitest test-isolation hazards: unrestored vi.spyOn/vi.mock without afterEach cleanup or restoreMocks config, un-awaited resolves/rejects assertions, and shared mutable module state across tests.
systematic-debugging
Reproduce failures, isolate root cause with evidence, and fix them through a regression test.
test-fix-loop
This skill should be used when autonomously iterating on test failures: runs the suite, diagnoses, applies minimal fixes, re-runs with checkpoint commit isolation until all tests pass.
silver-refactor
This skill should be used for SB-owned refactoring: evaluate scope, preserve behavior with baseline tests, make structural changes, and prove nothing regressed.
sap-fix-incident
Closes the loop from a /sap-diagnose root cause to a deployed, test-verified fix — conservatively and test-first. Takes a diagnose deliverable (or a dump key) whose top hypothesis is a CUSTOM-CODE DEFECT, acquires the failing source, reasons a minimal patch, reproduces the defect as a RED ABAP Unit test (via…