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 pwdev-solucoes/pwdev-claude-marketplace --skill qa-specialist-metricsgit clone --depth 1 https://github.com/pwdev-solucoes/pwdev-claude-marketplaceWrote 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/pwdev-solucoes/pwdev-claude-marketplace/qa-specialist-metrics)<a href="https://agentmods.dev/skills/pwdev-solucoes/pwdev-claude-marketplace/qa-specialist-metrics"><img src="https://agentmods.dev/badge/skills/pwdev-solucoes/pwdev-claude-marketplace/qa-specialist-metrics/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/pwdev-solucoes/pwdev-claude-marketplace/qa-specialist-metrics"><img src="https://agentmods.dev/badge/skills/pwdev-solucoes/pwdev-claude-marketplace/qa-specialist-metrics.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 | $0.00030 | $0.03238 |
| Opus 5.5 | $0.00012 | $0.01295 |
| Sonnet 5.5 | $0.00006 | $0.00648 |
| Haiku 4.5 | $0.00003 | $0.00324 |
Grade A, and why
qa-specialist-metrics 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 — 108 lines — stays where its author put it; the contents beside it link to each section on GitHub.
QA metrics specialist
Use this specialist when a QA workflow needs measurements that remain traceable to an identified target and contract. This specialist does not execute a workflow, tests, reports, or stored commands and cannot grant authorization. Read workflow, safety, and artifacts before advising the calling workflow.
Inputs
- Target, contract, complete criterion and case catalogs, preserved IDs/text, and applicable authorization.
- Normalized case and criterion results using only
PASS,FAIL,BLOCKED,NOT_RUN, andNOT_APPLICABLE, with stated reasons for non-applicability. - The question each metric answers, its population, observation window or build snapshot, and the records eligible for numerator and denominator.
- Current defects, evidence references, limitations, collection provenance, and known gaps.
Procedure
- Preserve the target, contract, catalogs, results, and authorization supplied by the caller. Do not infer a complete population from a partial result set.
- Define each metric before calculating it: name the question, numerator, denominator, population, observation window or immutable build snapshot, unit, and treatment of every result state. Never publish a bare percentage.
- Count
PASSin a pass-rate numerator. Count every applicablePASS,FAIL,BLOCKED, andNOT_RUNitem in that rate's denominator. ExcludeNOT_APPLICABLEonly with its recorded reason. A different metric may use different counts only when it states that definition. - If the denominator is zero, return
BLOCKEDwith the zero count and population; do not divide, emit100%, or implyPASS. Missing or incomplete population, window, or state treatment is alsoBLOCKED. - Requirements coverage is not source-line coverage. Test counts, line coverage, defect counts, and pass rates answer different questions and must not substitute for one another.
- Link included and excluded records to their IDs and evidence provenance. Expose stale data, sampling bias, unresolved defects, and other limitations beside the metric.
- Return the metric and its limitations to the calling workflow. A metric is an observation, not a global verdict, risk acceptance, or release approval.
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 First seen · 108 lines · 30 tokens per session scan A 782838132dd8
qa-specialist-metrics is a skill published in the GitHub repository pwdev-solucoes/pwdev-claude-marketplace (3 stars, last pushed 10d ago), licensed Apache-2.0. It adds 30 tokens to every session and 3,238 once invoked, about $0.0001 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 2026-09-16.
Other skills, from other repositories
research-engineer
An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal implementation across any required technology.
tika-eval-compare
Compare extracts from two Tika builds over a corpus to detect regressions in content, encoding, exceptions, and embedded-document handling. Use for "compare before/after extracts", "eval this change against the corpus".
cua-driver
Use Cua Driver for desktop or browser tasks that are awkward or unavailable through Bash/APIs, or when the user explicitly wants GUI interaction: app testing, visual bug reproduction, form filling, calendar entry, screenshots, and demo recording. Also covers Cua setup; not OpenAI Codex Computer Use or web research.
jetson-validate-image
Use after jetson-flash-image to run static BSP checks, on-target smoke/regression tests on a flashed DUT, or both. Not for build or flash steps. Triggers: validate bsp, on-target validation.
atmos-validation
Validate Atmos projects, components, arbitrary JSON Schema inputs, EditorConfig, and GitHub Actions; use affected-file selection and native CI annotations.
skill-benchmark
Benchmark AI skill effectiveness by measuring implementation quality against legacy constraints.