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-referencia-qualidadegit 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-referencia-qualidade)<a href="https://agentmods.dev/skills/andregusman-raiz/a-gusman-claude/ag-referencia-qualidade"><img src="https://agentmods.dev/badge/skills/andregusman-raiz/a-gusman-claude/ag-referencia-qualidade/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-referencia-qualidade"><img src="https://agentmods.dev/badge/skills/andregusman-raiz/a-gusman-claude/ag-referencia-qualidade.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00036 | $0.00611 |
| Opus 5.5 | $0.00014 | $0.00244 |
| Sonnet 5.5 | $0.00007 | $0.00122 |
| Haiku 4.5 | $0.00004 | $0.00061 |
Grade A, and why
ag-referencia-qualidade 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 2mo 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 — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Quality Gates (Minimos)
Antes de declarar qualquer tarefa como concluida:
| Gate | Criterio | Comando Tipico |
|---|---|---|
| Build | Sem erros | bun run build |
| TypeCheck | 0 erros | bun run typecheck ou bunx tsc --noEmit |
| Lint | 0 erros novos | bun run lint |
| Tests | 0 falhas novas | bun run test ou pytest |
| Security | 0 vulnerabilidades criticas | bun run audit |
| UX Render | 0 L1 failures (quando configurado) | /ag-testar-ux-qualidade --layers=L1 |
| UX Compliance | WCAG AA + Lighthouse >= 90 | /ag-testar-ux-qualidade --layers=L4 |
Teste Focado (durante desenvolvimento)
Preferir execucao de teste individual para feedback rapido:
bunx vitest run path/to/test.test.ts # Um arquivo
bunx vitest run --reporter=verbose # Suite completa (somente no final)
NUNCA rodar bun run test durante desenvolvimento iterativo — somente para validacao final.
Checklist Minimo Pos-Execucao
bun run typecheck && bun run lint && bun run test
Regras Anti-Teatralidade (Obrigatorias)
Ao escrever ou revisar testes:
- Cada expect() DEVE poder FALHAR em cenario real
- NUNCA:
.catch(() => false),|| true, conditional sem else, expect always-true - SEMPRE: hard-code valores esperados, testar ambos paths (sucesso + falha)
- SEMPRE: mutation mental antes de declarar done ("se eu introduzir bug, este teste falha?")
- Ver detalhes:
.claude/rules/test-quality-enforcement.md
Metricas de Qualidade (CI)
- Theatrical scan: CI bloqueia merge se anti-patterns detectados (test-quality job)
- Mutation testing: Stryker roda semanalmente (mutation-testing.yml), target 80%
- DORA metrics: Change Fail Rate, Lead Time, Deploy Frequency (dora-metrics.yml)
- Quality gates: TS budget, ESLint budget, file size, bun run audit (quality-gates.yml)
- Audit local:
bash .claude/scripts/test-quality-audit.sh [path]
Compaction Preservation
Ao executar /compact, SEMPRE incluir instrucao:
"Preserve: lista de arquivos modificados, task atual, comandos de teste, erros encontrados"
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.
- 2mo ago First seen · 56 lines · 36 tokens per session scan A 96a0d62daae8
ag-referencia-qualidade is a skill published in the GitHub repository andregusman-raiz/a-gusman-claude (18 stars, last pushed 1mo ago), licensed MIT. It adds 36 tokens to every session and 611 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 2026-08-30.
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.