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 dever-de-lastro-documental-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/dever-de-lastro-documental-sbroggioadv)<a href="https://agentmods.dev/skills/thomasmoreai/legal-skills-open/dever-de-lastro-documental-sbroggioadv"><img src="https://agentmods.dev/badge/skills/thomasmoreai/legal-skills-open/dever-de-lastro-documental-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/dever-de-lastro-documental-sbroggioadv"><img src="https://agentmods.dev/badge/skills/thomasmoreai/legal-skills-open/dever-de-lastro-documental-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 | $0.00220 | $0.01528 |
| Opus 5.5 | $0.00088 | $0.00611 |
| Sonnet 5.5 | $0.00044 | $0.00306 |
| Haiku 4.5 | $0.00022 | $0.00153 |
Grade A, and why
dever-de-lastro-documental-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 — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Dever de lastro documental — a porta de toda peça (P1)
Nenhuma peça sai daqui sem prova. Antes de gerar representação, denúncia, impugnação ou pedido, esta
skill checa dois elementos. Falta um → [FALTA LASTRO] e a geração para. Ela nunca inventa o
que falta: não imagina o número do diário, não deduz o artigo violado, não presume o ato. Essa disciplina
é o que mantém o produto do lado da representação legítima e longe da denúncia caluniosa.
Quando esta skill entra
- Sempre, antes de qualquer skill de geração de peça (C3) emitir uma linha.
- Quando o usuário chega com uma acusação sem documento: "ouvi falar", "todo mundo sabe", "o prefeito desviou" — sem ato publicado, não há peça.
- Quando falta a norma violada: há o ato, mas ninguém apontou qual regra ele descumpre.
Os dois elementos obrigatórios
(a) O ATO — publicado, localizável, datado
Uma peça de fiscalização ataca um ato, não um boato. O lastro do ato exige:
- Identificação do ato (nº do contrato, do decreto, do edital, da nomeação, da despesa).
- Onde foi publicado: diário oficial (do ente), data, e página/seção.
- URL ou referência que permita reabrir a fonte.
Sem esse conjunto → [FALTA LASTRO: ato não localizado]. O caminho então é primeiro o pedido LAI
(Lei 12.527 art. 10 — "qualquer interessado", sem motivar) para obter o documento, e só depois a peça.
(b) A NORMA VIOLADA — artigo e inciso
Não basta "isso está errado". A peça precisa dizer qual regra o ato descumpre — por artigo/inciso. As classes de vício da ação popular (Lei 4.717 art. 2º) são o vocabulário de referência:
| Vício (Lei 4.717 art. 2º) | O que caracteriza |
|---|---|
| Incompetência | o ato foge das atribuições legais do agente que o praticou |
| Vício de forma | omissão/observância incompleta de formalidade indispensável |
| Ilegalidade do objeto | o resultado do ato viola lei, regulamento ou outro ato normativo |
| Inexistência dos motivos | o fato/direito que fundamenta o ato é inexistente ou inadequado |
| Desvio de finalidade | o agente busca fim diverso do previsto na regra de competência |
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 · 89 lines · 220 tokens per session scan A 2d333f1dad7a
dever-de-lastro-documental-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 220 tokens to every session and 1,528 once invoked, about $0.0009 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…