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 andregusman-raiz/a-gusman-claude --skill ag-testar-qualidade-qatgit clone --depth 1 https://github.com/andregusman-raiz/a-gusman-claudeWrote 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/andregusman-raiz/a-gusman-claude/ag-testar-qualidade-qat)<a href="https://agentmods.dev/skills/andregusman-raiz/a-gusman-claude/ag-testar-qualidade-qat"><img src="https://agentmods.dev/badge/skills/andregusman-raiz/a-gusman-claude/ag-testar-qualidade-qat/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/andregusman-raiz/a-gusman-claude/ag-testar-qualidade-qat"><img src="https://agentmods.dev/badge/skills/andregusman-raiz/a-gusman-claude/ag-testar-qualidade-qat.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 4 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 | $0.00065 | $0.00885 |
| Opus 5 | $0.00032 | $0.00443 |
| Sonnet 5 | $0.00013 | $0.00177 |
| Haiku 4.5 | $0.00006 | $0.00089 |
Grade A, and why
ag-testar-qualidade-qat 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 9d 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 — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ag-testar-qualidade-qat — Quality Acceptance Testing (QAT)
Papel
O PDCA Orchestrator: executa ciclo completo Plan-Do-Check-Act de QAT. Nao apenas mede — classifica falhas, atualiza baselines, registra learnings e dispara acoes de melhoria.
Diferenca de ag-testar-e2e: ag-testar-e2e testa se fluxos FUNCIONAM. ag-testar-qualidade-qat testa se outputs tem QUALIDADE. Diferenca de ag-smoke-vercel: ag-smoke-vercel verifica se deploy esta VIVO. ag-testar-qualidade-qat avalia se conteudo gerado e BOM. Diferenca de ag-criar-cenario-qat: ag-criar-cenario-qat CRIA cenarios. ag-testar-qualidade-qat EXECUTA e orquestra PDCA.
Invocacao
/ag-testar-qualidade-qat https://app.vercel.app # Todos os cenarios, threshold 6
/ag-testar-qualidade-qat https://app.vercel.app QAT-04 # Cenario especifico
/ag-testar-qualidade-qat https://app.vercel.app all 7 # Threshold customizado
Pre-requisitos
- Estrutura
tests/qat/no projeto (copiar de~/.claude/shared/templates/qat/) - Auth state valido (
tests/e2e/.auth/user.json) QAT_JUDGE_API_KEYouANTHROPIC_API_KEYconfigurado- URL da app acessivel
Ciclo PDCA
PLAN: Preflight + carregar KB (baselines, failure-patterns, learnings)
DO: Executar cenarios 4 camadas (L1 Smoke → L2 Func → L3 Quality → L4 Business)
Short-circuit: se L1/L2 falha, skip Judge (~30% economia)
CHECK: Classificar falhas (INFRA/FEATURE/QUALITY/BUSINESS/RUBRIC/FLAKY)
Comparar com baselines, detectar regressoes e flaky
ACT: Atualizar baselines, registrar failure patterns, adicionar learnings
Gerar report PDCA com acoes tomadas
Output
tests/qat/results/YYYY-MM-DD-HHmmss/com subdiretorios por cenario- Cada cenario:
screenshot.png,output.*,evaluation.json - Sumario:
summary.json+report.md
Custo
~$0.25-0.60 por run (10 cenarios). Execucao manual ou schedule semanal recomendado.
Interacao com outros agentes
- ag-testar-e2e: Complementar (E2E testa fluxos, QAT testa qualidade)
- ag-pipeline-deploy: Pos-deploy (QAT apos deploy para validar qualidade)
- ag-smoke-vercel: Sequencial (smoke primeiro, QAT depois se smoke passa)
- ag-criar-cenario-qat: Complementar (ag-criar-cenario-qat cria cenarios, ag-testar-qualidade-qat executa PDCA)
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.
- 9d ago First seen · 72 lines · 65 tokens per session scan A 78614941c009
ag-testar-qualidade-qat is a skill published in the GitHub repository andregusman-raiz/a-gusman-claude (19 stars, last pushed 4d ago), licensed MIT. It adds 65 tokens to every session and 885 once invoked, about $0.0003 per session on Opus 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
taiyi-dev
A software-development stage that implements planned tasks using test-driven development, or TDD: write a failing test, make it pass, then improve the code. It checks the task plan, dependencies, file boundaries, and required completion evidence.
taiyi-test
A project workflow skill for verifying an implementation and producing a TEST.md record. TDD means writing a failing test, implementing the change, and then making the test pass; this skill checks that process and other regression cases.
verification-engine
Use when verifying build/test/lint before commit, PR, or completion claims. Runs verification pipeline in fresh subagent context with auto-repair. Triggers on /handoff-verify, pre-commit check, build verification, test validation.
verify-implementation
A workflow that runs a project’s verification skills to produce a report on coding patterns, architecture rules, and project conventions. It is intended for work after implementation, before a pull request, or during code review.
test-fixing
Run tests and systematically fix all failing tests using smart error grouping. Use when user asks to fix failing tests, mentions test failures, runs test suite and failures occur, or requests to make tests pass.
figma-to-react-workflow
Orchestrates end-to-end Figma-to-React conversion pipeline with enforced TDD, automated pixel-diff visual QA, E2E testing, and app-type awareness (web apps, Chrome extensions, PWAs). Keywords: Figma to React, design tokens, autonomous component generation, Figma conversion, Tailwind config, component library, TDD…