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 guard-para-apuracao-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/guard-para-apuracao-sbroggioadv)<a href="https://agentmods.dev/skills/thomasmoreai/legal-skills-open/guard-para-apuracao-sbroggioadv"><img src="https://agentmods.dev/badge/skills/thomasmoreai/legal-skills-open/guard-para-apuracao-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/guard-para-apuracao-sbroggioadv"><img src="https://agentmods.dev/badge/skills/thomasmoreai/legal-skills-open/guard-para-apuracao-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 | $0.00262 | $0.01547 |
| Opus 5.5 | $0.00105 | $0.00619 |
| Sonnet 5.5 | $0.00052 | $0.00309 |
| Haiku 4.5 | $0.00026 | $0.00155 |
Grade A, and why
guard-para-apuracao-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 22d 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 — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.
GUARD — pedido de apuração, nunca acusação (trava P2)
Carrega SEMPRE. Transversal a toda a Camada 3: nenhuma peça sai sem passar por esta reescrita. Junto com a P3 (
aviso-cp339-art19-e-ce326a) e a P6 (disclaimer-eleitoral), forma o filtro de postura antes de emitir.
Quando esta skill entra
Sempre que uma skill de C3 — gerador-representacao, gerador-denuncia-camara,
gerador-impugnacao-edital, notícia-crime, consolidador-dossie — for redigir o
corpo de uma peça. Este é o passo P2 das 7 travas de postura.
Anexos obrigatórios (context/)
context/travas-postura.md— a trava P2 e sua base.context/lei-8429-improbidade.md— art. 14 (representação legítima) — grep + faixa.context/freios-penais.md— CP 339 e Lei 8.429 art. 19 (o que a P2 evita).
A distinção que sustenta o produto
A Lei 8.429/92, art. 14 garante o direito:
Art. 14. Qualquer pessoa poderá representar à autoridade administrativa competente para que seja instaurada investigação destinada a apurar a prática de ato de improbidade.
Repare no verbo da própria lei: apurar, investigar. A representação legítima pede que se investigue — não decreta a culpa. Quando o texto afirma como certo um ato ímprobo/crime contra alguém que se sabe (ou se deveria saber) inocente, cruza para o CP art. 339 e a Lei 8.429 art. 19. A P2 mantém toda peça do lado do art. 14.
Reescrita obrigatória — de imputação fechada para apuração
Verbos e fórmulas PROIBIDOS (afirmam culpa / tipificam):
| Proibido (imputação fechada) | Por quê |
|---|---|
| "o gestor desviou recursos" | afirma o fato como provado |
| "é corrupto", "agiu de má-fé" | juízo de valor sobre a pessoa |
| "cometeu crime de peculato / praticou improbidade" | tipificação penal fechada por leigo |
| "fraudou a licitação", "superfaturou" | conclusão, não indício |
| "exijo a condenação / punição de X" | pede pena, não apuração |
Fórmulas SUBSTITUTAS (pedem exame do fato):
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.
- 22d ago First seen · 90 lines · 262 tokens per session scan A d06f8fe2864c
guard-para-apuracao-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 262 tokens to every session and 1,547 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 2026-10-06.
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…