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 ThomasMoreAI/legal-skills-open --skill gerador-representacao-sbroggioadvgit clone --depth 1 https://github.com/ThomasMoreAI/legal-skills-openWrote 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/thomasmoreai/legal-skills-open/gerador-representacao-sbroggioadv)<a href="https://agentmods.dev/skills/thomasmoreai/legal-skills-open/gerador-representacao-sbroggioadv"><img src="https://agentmods.dev/badge/skills/thomasmoreai/legal-skills-open/gerador-representacao-sbroggioadv/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/thomasmoreai/legal-skills-open/gerador-representacao-sbroggioadv"><img src="https://agentmods.dev/badge/skills/thomasmoreai/legal-skills-open/gerador-representacao-sbroggioadv.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 | $0.00246 | $0.01659 |
| Opus 5.5 | $0.00098 | $0.00664 |
| Sonnet 5.5 | $0.00049 | $0.00332 |
| Haiku 4.5 | $0.00025 | $0.00166 |
Grade A, and why
gerador-representacao-sbroggioadv 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 19d 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 — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Gerador de representação (TCE / TCU / MP)
Quando esta skill entra
Quando o roteador-vicio-orgao aponta representação como peça, ou o usuário pede para
denunciar a um Tribunal de Contas ou ao Ministério Público. Exige lastro completo (P1): o
ato publicado (URL/data do diário) e a norma específica violada (artigo/inciso). Sem os
dois, devolve [FALTA LASTRO] — nunca inventa a lacuna.
Antes de gerar — o aviso obrigatório (P3)
Esta skill não emite nada antes de o aviso-cp339-art19-e-ce326a mostrar ao usuário o
texto literal do CP art. 339 (denunciação caluniosa — red. Lei 14.110/2020, que nomeia
"ação de improbidade administrativa"; reclusão de 2 a 8 anos) e do art. 19 da Lei
8.429/92 (representação por improbidade contra quem se sabe inocente — detenção de 6 a 10
meses + multa) e o usuário confirmar que os fatos são verdadeiros e documentados. Na janela
eleitoral ou com alvo candidato 2026, soma-se o disclaimer-eleitoral (CE 326-A). Ver
freios-penais.md.
Escolha do órgão (a chave da origem da verba)
- Verba federal repassada → TCU (CF art. 74 §2º nomeia cidadão, partido, associação e sindicato como legitimados). Verba própria estadual/municipal → TCE/TCM (extensão pela CF art. 75). A regra é a origem do dinheiro, não o ente (TV7). Na dúvida, LAI antes.
- Ministério Público: quando há indício de dano ao erário (Lei 8.429 art. 10) ou de crime — representação/notícia-crime para apuração. A representação por improbidade tem base na Lei 8.429 art. 14: "Qualquer pessoa poderá representar à autoridade administrativa competente para que seja instaurada investigação destinada a apurar a prática de ato de improbidade."
Estrutura da peça (pedido de apuração)
- Endereçamento — ao Presidente do TCE/TCU ou ao Promotor de Justiça competente.
- Qualificação do representante (Lei 8.429 art. 14 §1º: forma escrita, assinada, com qualificação, informações sobre o fato e sua autoria, e indicação das provas).
- Dos fatos — o que foi publicado, onde e quando. Cada frase factual carrega a fonte exata: diário, data, página/seção (P5). Descreve o ato sem adjetivar a intenção.
- Do direito — a norma violada, artigo e inciso, citada só do
context/. Ex.: dispensa fora de hipótese (Lei 14.133), aditivo acima do limite, nomeação sem concurso (referida à norma que a exige), estouro de gasto com pessoal (LRF). Se a improbidade for a tese, lembrar que pós-2021 exige dolo específico (Lei 8.429 art. 1º §§1º-2º — TV4): a peça pede que se apure o dolo, não o afirma. - Do pedido — requer a instauração de procedimento de apuração dos fatos, a análise das contas/atos e as providências cabíveis. Verbos de pedido: "requer que se apure", "que se verifique", "que se investigue". Nunca "o gestor desviou / fraudou / cometeu".
- Provas — lista dos documentos anexados (print/PDF do diário, extrato, portaria).
- Fecho — data, local, assinatura.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 19d ago First seen · 85 lines · 246 tokens per session scan A 12a408ca239f
gerador-representacao-sbroggioadv is a skill published in the GitHub repository ThomasMoreAI/legal-skills-open (95 stars, last pushed 15d ago), licensed Apache-2.0. It adds 246 tokens to every session and 1,659 once invoked, about $0.0010 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 2026-10-09.
Other skills, from other repositories
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…