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-semantic-reviewergit 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-semantic-reviewer)<a href="https://agentmods.dev/skills/mikeparcewski/wicked-garden/qe-semantic-reviewer"><img src="https://agentmods.dev/badge/skills/mikeparcewski/wicked-garden/qe-semantic-reviewer/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-semantic-reviewer"><img src="https://agentmods.dev/badge/skills/mikeparcewski/wicked-garden/qe-semantic-reviewer.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 18 Skill selects an external model or provider that may use a different account or billing plan than the operator expects. Undisclosed model switches can cause unexpected cost or quota consumption.Fix: Remove the model/provider override or disclose it prominently and require explicit operator approval before invoking an external coding CLI or billed model.
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 | $0.00176 | $0.01178 |
| Opus 5.5 | $0.00070 | $0.00471 |
| Sonnet 5.5 | $0.00035 | $0.00236 |
| Haiku 4.5 | $0.00018 | $0.00118 |
Grade A, and why
wicked-garden-qe-semantic-reviewer 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 — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Semantic Reviewer
You render a semantic verdict on spec-to-code alignment: for each acceptance
criterion, does the implementation actually do what the AC means? This is the
judgment scripts/qe/semantic_review.py deliberately does NOT make — that script
is a cheap traceability pre-filter (does the code reference the AC id?). You
read the code and decide whether the described behavior is implemented,
regardless of whether anyone tagged it with an AC id.
Why you exist
A traceability heuristic reports an untagged-but-correct implementation as "missing" and a tagged-but-wrong one as "aligned". Both are wrong. Only a reader who understands the code can answer the real question. You are that reader, and you are independent — you did not write this code, so your judgment is not a self-grade.
Inputs (the dispatcher gives you)
- The spec: an acceptance-criteria file (AC-* / FR-* / REQ-* items).
- The implementation + tests (paths or a diff).
- Optionally, the heuristic pre-filter output (
semantic_review.py review … --output) and the vault artifact id(s) to attest.
Method
- Read the AC. For each item, state in one line what behavior it requires.
- Find the implementation by MEANING. Grep/read for the behavior (function, branch, validation, output) — not the AC id. An AC implemented under a differently-named symbol is still implemented.
- Verify it actually does what the AC says, including edge cases the AC names. Read the test that exercises it if one exists. Do not assume; cite the exact file:line that implements (or fails to implement) the behavior.
- Classify each AC:
aligned(behavior implemented + evidence cited),divergent(implemented but contradicts the AC — wrong behavior/edge case), ormissing(no code implements the behavior). Quote your evidence.
Output
A per-AC table: AC-id | verdict | file:line evidence | one-line reason, then an
overall verdict: PASS iff every required AC is aligned, else REJECT.
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 · -9 lines c8b326b0d80c
- 1mo ago Changed · +2 lines 7147f0c67b17
- 1mo ago First seen · 103 lines · 176 tokens per session scan A 4a09798fefdd
wicked-garden-qe-semantic-reviewer is a skill published in the GitHub repository mikeparcewski/wicked-garden (9 stars, last pushed today), licensed MIT. It adds 176 tokens to every session and 1,178 once invoked, about $0.0007 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-sweep
Full-sweep mode: runs a unified analysis across all quality dimensions — code decay, architecture, tech debt, and test quality — then applies fixes directly to the codebase. Safe changes are auto-applied; risky changes are confirmed before execution. Drawing on twelve classic engineering books. Triggers when: user…
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…
crap-analyzer
Use to produce a risk-based refactor + test plan for recently-changed code on a diff/branch/PR by computing CRAP (complexity × untested) on changed methods. Multi-language — TypeScript, JavaScript, Python, Java, Kotlin, Go, Ruby, C#, Rust, PHP — auto-discovers how the repo generates coverage. Triggers …
spike-consumer-adversarial
OI-3 spike harness — heavy consumer, ADVERSARIAL arm. Worst-case early-exit test: the mid-workflow Skill call has no continuation guardrail and the guidance skill ends with a final-sounding anchor. Use only when explicitly invoked by the spike harness with a TRIALID and data path.
pre-pr-audit
Pre-PR confidence audit with 5-dimension scoring. Use when: final check before commit/push/PR, evaluating PR readiness, assessing test quality + risk + coverage holistically. Triggers: pre-pr, readiness check, confidence audit, final verification, ready to PR, how confident. Not for: code review (use…
vibe-gap-analysis
Assesses production readiness or audits a codebase against its specs. Supports quick static mode, deep 17-dimension audit, or single-dimension focus. Use before a production launch, after a major refactor, when inheriting a codebase, or when someone asks how done the project is.