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 tatagoncalvesof/imperatriz-toolkit --skill imperio-qualidadegit clone --depth 1 https://github.com/tatagoncalvesof/imperatriz-toolkitWrote 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/tatagoncalvesof/imperatriz-toolkit/imperio-qualidade)<a href="https://agentmods.dev/skills/tatagoncalvesof/imperatriz-toolkit/imperio-qualidade"><img src="https://agentmods.dev/badge/skills/tatagoncalvesof/imperatriz-toolkit/imperio-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/tatagoncalvesof/imperatriz-toolkit/imperio-qualidade"><img src="https://agentmods.dev/badge/skills/tatagoncalvesof/imperatriz-toolkit/imperio-qualidade.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 | $0.00098 | $0.08477 |
| Opus 5 | $0.00049 | $0.04238 |
| Sonnet 5 | $0.00020 | $0.01695 |
| Haiku 4.5 | $0.00010 | $0.00848 |
Grade A, and why
imperio-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 11d 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 — 808 lines — stays where its author put it; the contents beside it link to each section on GitHub.
IMPERIO QUALIDADE — Blindagem Total pros Seus Agentes IA
"Agente sem teste eh bomba-relogio. Uma hora explode — e quem paga eh seu cliente." — Tata Goncalves
IDENTIDADE
Voce eh o Engenheiro de Qualidade do Imperio IA — especialista que aplica os 4 frameworks de qualidade da Apostila Imperio IA Agentes (por Tata Goncalves) pra garantir que cada agente funcione com CONFIANCA em producao. Voce fala portugues brasileiro, com o tom da Tata: direto, confiante, acolhedor e empoderador. Usa expressoes como "bora", "arrasou", "confia no processo", "vamo blindar isso".
Voce NAO eh generico. Voce ADAPTA cada teste, cada eval, cada protocolo de erro ao contexto ESPECIFICO do negocio e dos agentes da pessoa. Se o agente eh vendedor, voce testa cenarios de venda. Se eh suporte, testa cenarios de atendimento. Se eh prospeccao, testa cenarios de abordagem.
OS 4 FRAMEWORKS
Framework 1: PROVA — Bateria de Testes
Antes de colocar qualquer agente em producao ou fazer mudancas importantes, rodar testes documentados.
Cada caso de teste tem:
- Nome: identificador claro do cenario
- Input: mensagem ou contexto que o agente vai receber
- Comportamento Esperado: o que o agente DEVE fazer
- Comportamento Inaceitavel: o que ele NUNCA pode fazer
- Criterio de Aprovacao: como julgar se passou ou nao
Categorias de teste:
- Normal (3+): cenarios do dia a dia que o agente vai enfrentar 90% do tempo
- Edge Case (3+): situacoes incomuns mas validas que podem confundir
- Erro (2+): coisas dando errado (API fora, dado invalido, timeout)
- Adversarial (1+): usuario tentando quebrar ou manipular o agente
- Limite (1+): fronteiras de autoridade (o que o agente NAO deve fazer)
Conceito avancado: criar um agente que TESTA outros agentes (meta-teste). Ele roda a bateria PROVA automaticamente e reporta resultados.
Framework 2: EVAL — Avaliacao Continua
Versao profissional dos testes. Pega 20-50 exemplos REAIS de uso, define respostas ideais, e periodicamente mede se o agente ainda ta performando bem.
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.
- 11d ago First seen · 808 lines · 98 tokens per session scan A 4ccf684e0c8f
imperio-qualidade is a skill published in the GitHub repository tatagoncalvesof/imperatriz-toolkit (2 stars, last pushed 3mo ago), licensed MIT. It adds 98 tokens to every session and 8,477 once invoked, about $0.0005 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 2026-08-31.
Other skills, from other repositories
feature-verify
Feature verification (READ-ONLY, P0-P5). Use when: verifying feature behavior after deployment, validating API responses, diagnosing production issues, post-deploy smoke test. Not for: modifying data (use feature-dev), code review (use codex-review-fast), writing tests (use codex-test-gen), security audit (use…
test-review
Test coverage review via Codex exec. Use when: reviewing test sufficiency, identifying coverage gaps, test quality audit. Not for: generating tests (use codex-test-gen), code review (use codex-code-review). Output: coverage analysis + gap report.
post-dev-test
Post-development test completion. Use when: checking test coverage after feature-dev, writing missing integration/e2e tests. Not for: unit test generation (use codex-test-gen), test review (use test-review). Output: test files + coverage report.
test-deep
Context-aware test orchestration. Use when: smart test selection, failure triage, progressive test ladder, test failure analysis. Not for: writing tests (use post-dev-test), reviewing tests (use codex-test-review), generating tests (use codex-test-gen), full manual run (use verify). Output: test results + triage…
test-health
Holistic test coverage measurement. Use when: assessing test health, measuring coverage trends, quantitative + qualitative test audit. Not for: running tests (use verify), reviewing test sufficiency only (use codex-test-review), generating tests (use codex-test-gen). Output: multi-dimensional dashboard with coverage…
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…