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 swarmgit 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/swarm)<a href="https://agentmods.dev/skills/mikeparcewski/wicked-garden/swarm"><img src="https://agentmods.dev/badge/skills/mikeparcewski/wicked-garden/swarm/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/swarm"><img src="https://agentmods.dev/badge/skills/mikeparcewski/wicked-garden/swarm.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 116 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00198 | $0.02106 |
| Opus 5.5 | $0.00079 | $0.00842 |
| Sonnet 5.5 | $0.00040 | $0.00421 |
| Haiku 4.5 | $0.00020 | $0.00211 |
Grade A, and why
wicked-garden-swarm 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.
How it starts
The opening of the file, as written. The whole thing — 144 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Swarm — parallel verification swarm
Orchestrate N units of work in parallel (one scoped subagent per unit), then independently verify every result with a separate wave of agents that re-derive "done" from a clean state. The swarm's value is not the parallelism — it's that no agent grades its own work. A claimed "tests pass" / "done" that can't be re-derived from receipts is rejected.
Swarm vs council.
jam:councilgets independent multi-model opinions on one decision (different vendors answer the same scaffold). Swarm gets parallel multi-agent execution + verification over many units. Use council to decide; use swarm to execute-and-prove. They compose: run a council inside the verify wave for a high-stakes verdict (seerefs/independent-verification.md).
Compose, don't reinvent
This skill is orchestration prose. Every primitive it needs already exists in the garden — reference these, do not duplicate them:
| Need | Use (existing garden piece) |
|---|---|
| Per-unit implementer subagent | a worker following wicked-garden-governed-worker Creator — the repo's checks run in-tree with exit codes pasted, generated artifacts regenerated, evidence in the output |
| Per-unit recon subagent | a worker following wicked-garden-governed-worker Neutral — read-only: analyse, plan, name files and risks, never implement |
| Independent semantic verdict | wicked-garden-qe-semantic-reviewer worker skill (skills/qe-semantic-reviewer/) — independent-by-construction; refuses to attest its own work |
| Fallback reviewer | a worker following wicked-garden-governed-worker Evaluator — output-only, evaluator ≠ creator, verdict with file:line reasons |
| Re-derive a claim (the receipt) | wicked-garden-prove (run + freeze evidence + gate; fail-closed) |
| Hard-gate independent sign-off | wicked-garden-prove --with-attestations → wicked-vault attest (evaluator ≠ creator, G10) |
| Blast-radius / scope lens | wicked-garden:deliberate (lens 2 + 3) and wicked-garden-search blast-radius |
| Per-unit isolation + commit hygiene | wicked-garden:worktrees (dangling-commit trust-but-verify) |
| Phase shape per unit | wicked-garden:archetype refs (build / review / migrate) |
| Multi-model verdict in a wave | wicked-garden:jam:council |
What ships with it
5 files 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.
- 1mo ago Changed · +10 lines b308e51199db
- 1mo ago Changed · -1 lines 191b1b3177b2
- 1mo ago Changed · +2 lines fea1cab5e5a0
- 1mo ago First seen · 133 lines · 198 tokens per session scan A 8262542824a2
wicked-garden-swarm is a skill published in the GitHub repository mikeparcewski/wicked-garden (9 stars, last pushed today), licensed MIT. It adds 198 tokens to every session and 2,106 once invoked, about $0.0008 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
acceptance-criteria-gwt
Use when writing acceptance criteria for a task - express each as an observable Given/When/Then that QA can execute, including negative cases.
pm-uat-review
Use when a task is in pmuat - verify every acceptance criterion and the human's comments yourself in the browser, on a device, or over a loopback HTTP request, record a verdict per criterion, then move to humanuat or needrevision.
qa-verify-before-verdict
Use before any reviewcriterion approval or column move - the evidence each verdict needs, how to treat skipped, blocked and intermittent cases, and which exit a blocker takes.
retest-after-revision
Use when the task came back to QA after needrevision - what to re-run, what may carry over, and how to keep old passes from approving new code.
vibe-workstream-orchestration
Runs a multi-phase project from an orchestrating main thread that plans, routes and verifies but does not build. Defines a few long-lived workstreams, each owning a file area end to end in its own worktree, and routes every follow-up to the owning agent instead of spawning a one-off. Covers base-SHA recording…
vibe-requirements-validator
Validates PRD, user stories, or feature requirements against SMART criteria. Use when reviewing requirements to catch vagueness before it causes expensive rework.