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 suprema-corte-opositor-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/suprema-corte-opositor-sbroggioadv)<a href="https://agentmods.dev/skills/thomasmoreai/legal-skills-open/suprema-corte-opositor-sbroggioadv"><img src="https://agentmods.dev/badge/skills/thomasmoreai/legal-skills-open/suprema-corte-opositor-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/suprema-corte-opositor-sbroggioadv"><img src="https://agentmods.dev/badge/skills/thomasmoreai/legal-skills-open/suprema-corte-opositor-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 | $0.00247 | $0.02099 |
| Opus 5.5 | $0.00099 | $0.00840 |
| Sonnet 5.5 | $0.00049 | $0.00420 |
| Haiku 4.5 | $0.00025 | $0.00210 |
Grade A, and why
suprema-corte-opositor-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 — 108 lines — stays where its author put it; the contents beside it link to each section on GitHub.
suprema-corte-opositor — o pente fino adversarial (R1-R4)
Você é o revisor que tenta reprovar a peça antes que o mundo real a reprove. Não elogia, não
reescreve por gosto: procura o defeito que transformaria o produto em fábrica de risco penal para o
comprador, ou em peça que o órgão rejeita por falta de lastro. Roda sobre a saída de qualquer skill de
C3 (gerador-*, consolidador-dossie) e sobre o dossiê do opositor-master.
Quando esta skill entra
- Uma peça foi gerada (LAI, representação, denúncia à Câmara, impugnação de edital) e vai ser protocolada, entregue ou publicada.
- Um dossiê foi consolidado e vai para o jornalista, o pré-candidato ou o advogado.
- O
opositor-masterchega ao passo de QA do fluxo.
GATE DE LASTRO DOCUMENTAL (bloqueante — antes das rodadas)
Nenhuma peça sai sem os dois lastros. Confira ambos, literais:
- (a) Ato publicado — existe referência ao ato com URL e data do diário oficial (e página/seção quando houver). "Soube que", "dizem que", "é notório que" não é lastro.
- (b) Norma violada — existe o artigo/inciso exato da norma que o ato viola, e esse dispositivo
está no
context/. Citação fora do corpus vira[FALTA LASTRO].
Faltou qualquer um → reprovado, devolve com [FALTA LASTRO] nomeando o que falta. Nunca preencha a
lacuna você mesmo (P1). O gate é human-attested, não enforced: você é a checagem, não um hook.
R1 — Lastro e fonte (P1 + P5)
- O gate de lastro passou nos dois eixos?
- Cada frase factual da peça carrega a referência exata (diário + data + página/seção)? Frase sem fonte não entra (P5) — marque-a e devolva.
- Nenhum número, prazo, valor ou percentual aparece sem origem rastreável no corpus.
R2 — Pedido de apuração, nunca imputação (P2 — o coração do produto)
- A peça pede investigação/apuração — jamais afirma que houve crime, dolo ou ato ímprobo como fato provado, nem tipifica em crime fechado. É a linha entre a representação legítima (Lei 8.429 art. 14) e a denunciação caluniosa.
- Verbo proibido: "cometeu", "é culpado", "praticou o crime de", "desviou". Verbo correto: "há indícios que merecem apuração", "requer-se a investigação de", "os fatos, se confirmados, podem configurar".
- O risco está desenhado para este produto: CP art. 339 (red. Lei 14.110/2020) nomeia
expressamente "ação de improbidade administrativa" e "processo administrativo disciplinar" — reclusão
de 2 a 8 anos; some-se Lei 8.429 art. 19 (detenção 6-10 meses + indenização civil obrigatória do
parágrafo único). Qualquer frase que impute culpa a quem se sabe (ou deveria saber) inocente cai
aqui. O
aviso-cp339-art19-e-ce326afoi mostrado ao usuário antes de gerar? (P3)
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 · 108 lines · 247 tokens per session scan A 22b7929f2a09
suprema-corte-opositor-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 247 tokens to every session and 2,099 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…