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-compliance-test-engineergit 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-compliance-test-engineer)<a href="https://agentmods.dev/skills/mikeparcewski/wicked-garden/qe-compliance-test-engineer"><img src="https://agentmods.dev/badge/skills/mikeparcewski/wicked-garden/qe-compliance-test-engineer/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-compliance-test-engineer"><img src="https://agentmods.dev/badge/skills/mikeparcewski/wicked-garden/qe-compliance-test-engineer.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 | $0.00196 | $0.02938 |
| Opus 5.5 | $0.00078 | $0.01175 |
| Sonnet 5.5 | $0.00039 | $0.00588 |
| Haiku 4.5 | $0.00020 | $0.00294 |
Grade A, and why
wicked-garden-qe-compliance-test-engineer scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 25d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
# (child_process.spawn with shell:false), so control templates cannot How it starts
The opening of the file, as written. The whole thing — 265 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Compliance Test Engineer
You produce auditor-ready evidence for regulatory controls. Compliance fails on the thing you didn't capture, not the thing you didn't do — so every control the scenario lists gets a deterministic evidence artifact, even if the artifact is "N/A: this workload is out of scope for PCI". Your output is read by an auditor, not a developer. Be explicit.
Runtime
Script-backed steps use the wicked-garden launcher: wicked-garden run <plugin-root-relative path, e.g. scripts/…> [args]. It is on PATH after npm i -g wicked-garden; otherwise use npx wicked-garden run …; inside a wicked-crew run it is "$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 — frontmatter declares:
framework:one ofsoc2,hipaa,gdpr,pci-dss, or a comma- separated subset. Drives the control catalog.controls:list of control ids exactly as written in the catalog (e.g.SOC2-CC6.1,HIPAA-164.308(a)(1),GDPR-Art-30,PCI-DSS-6.5.1).scope:object with{ systems[], data_classes[], regions[] }so the agent can flag out-of-scope controls without running them.evidence_commands:optional override — maps a control id to a shell command. Without this the agent falls back to the builtin map shipped atlib/compliance/controls.json.
run_id— UUID of the currentrunsrow; definesEVIDENCE_DIR..wicked-qe/config.json—detected_toolingmust include at least one query/execution tool per control (e.g.aws,gcloud,kubectl,gh,opa) — control evidence that requires a missing tool is recorded asunsatisfied: tool-missing, NOT skipped..wicked-qe/evidence/<run_id>/context.md— optional domain rules like "production AWS account is 111-222" or "data class PHI only in eu-west-1".
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.
- 25d ago Changed · +2 lines 9ba57bc49fdd
- 1mo ago Changed · -16 lines · -119 tokens per session 51e7c3f5534e
- 1mo ago Changed · +7 lines a6fee29d0933
- 1mo ago First seen · 272 lines · 315 tokens per session scan A 8b695d14a403
wicked-garden-qe-compliance-test-engineer is a skill published in the GitHub repository mikeparcewski/wicked-garden (9 stars, last pushed today), licensed MIT. It adds 196 tokens to every session and 2,938 once invoked, about $0.0008 per session on Opus 5.5. A static security scan graded it A with 1 finding (runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
launch-gate
Pre-launch production readiness gate. Comprehensive go/no-go checklist covering SLAs, monitoring, backups, load testing, security, accessibility, legal, rollback, and runbook completeness. Runs at any phase boundary — not just final launch. Use when asking "are we ready to ship this phase?".
accessibility-testing
Test for WCAG 2.2 AA compliance with axe-core + Playwright, keyboard navigation audits, screen reader testing, ARIA pattern validation, and legal compliance mapping (ADA, EAA, Section 508). Automated tools catch 30-40% of issues — this skill covers automated and manual testing together. Use when: "accessibility,"…
xcode-workflows
Xcode build system guidance for xcodebuild operations. Use when building iOS projects, running tests, analyzing build failures, or configuring schemes. Covers build/clean/test operations, interpreting xcodebuild output, and troubleshooting common build errors.
accessibility-check
Use when a task changes any screen, form, dialog, menu or control - Lighthouse/axe scan of the changed screens, a keyboard walk, and the thresholds that fail a task.
vibe-rollback-plan
Documents rollback procedures before making risky changes. Covers what's changing, verification steps, rollback procedures, and blast radius assessment. Use before database migrations, breaking API changes, infrastructure or DNS changes, large dependency upgrades, or any change where undo is not obvious.
e2e-testing
End-to-end testing for Falcon Foundry apps using Playwright and @crowdstrike/foundry-playwright. TRIGGER when user asks to "add e2e tests", "add playwright tests", "write end-to-end tests", "test my app", or mentions "e2e", "playwright", or "end-to-end" in the context of testing a Foundry app. DO NOT TRIGGER during…