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 emidio-trancoso/advocacia-aberta --skill 3.2-diagramar-pecagit clone --depth 1 https://github.com/emidio-trancoso/advocacia-abertaWrote 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/emidio-trancoso/advocacia-aberta/3.2-diagramar-peca)<a href="https://agentmods.dev/skills/emidio-trancoso/advocacia-aberta/3.2-diagramar-peca"><img src="https://agentmods.dev/badge/skills/emidio-trancoso/advocacia-aberta/3.2-diagramar-peca/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/emidio-trancoso/advocacia-aberta/3.2-diagramar-peca"><img src="https://agentmods.dev/badge/skills/emidio-trancoso/advocacia-aberta/3.2-diagramar-peca.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00076 | $0.01363 |
| Opus 5 | $0.00038 | $0.00681 |
| Sonnet 5 | $0.00015 | $0.00273 |
| Haiku 4.5 | $0.00008 | $0.00136 |
Grade A, and why
diagramar-peca 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 12d 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 — 115 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Diagramar Peça — Legal Design simples
Pega uma peça já redigida (em .md ou texto) e gera um PDF diagramado usando
Typst e um template enxuto que acompanha esta skill. Serve para qualquer peça:
petição, contestação, recurso, parecer, contrato, notificação extrajudicial,
alegações finais.
⚠ Regra absoluta
Não inventa, não adiciona, não parafraseia. O conteúdo jurídico é exatamente o que está na peça original. O que muda é só a forma visual — onde cada trecho fica mais legível (um destaque, uma citação em bloco, uma linha do tempo). Nunca crie fatos, números, citações de lei ou jurisprudência que não estejam no texto original.
Pré-requisito
Esta skill usa o Typst para gerar o PDF. Verifique se está instalado com
typst --version. Se não estiver:
- macOS:
brew install typst - outros sistemas: ver https://github.com/typst/typst (há instaladores prontos)
Se o usuário não tiver e não quiser instalar, você ainda pode entregar a peça formatada em Markdown limpo — mas o resultado bonito é o PDF.
Instrução
Considere <arquivo-da-peca> o caminho relativo informado pelo usuário (ex.:
casos/meu-caso/pecas/contestacao-v1.md). Se não tiver sido informado, pergunte qual
peça deve ser diagramada.
Passo 1 — Ler a peça inteira
Leia o arquivo do início ao fim. Identifique os dados de cabeçalho (juízo/destinatário, partes, título da peça) e, para cada bloco do texto, que tipo de conteúdo é:
| Conteúdo no texto | Componente do template |
|---|---|
| O ponto-chave, a tese central, um alerta | #destaque[...] |
| Citação literal (transcrição, doutrina, artigo de lei, cláusula) | #citacao(fonte: "...")[...] |
| Lei ou jurisprudência usada como fundamento | #fundamento(tipo: "...", ref: "...")[...] |
| Sequência de fatos com datas | #cronologia((("data", "evento"), ...)) |
| Título de seção | = Título (nível 1) e == Subtítulo (nível 2) |
| Texto argumentativo comum | parágrafo normal |
| Etiqueta curta para guiar a leitura (ex.: PEDIDO) | #marcador("PEDIDO") |
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.
- 12d ago First seen · 115 lines · 76 tokens per session scan A ef676837adfd
diagramar-peca is a skill published in the GitHub repository emidio-trancoso/advocacia-aberta (49 stars, last pushed 5d ago), licensed MIT. It adds 76 tokens to every session and 1,363 once invoked, about $0.0004 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 2026-08-30.
Other skills, from other repositories
patent-reader
A plain-language reader for Chinese patents that turns a publication number or PDF into notes, diagrams, and an Obsidian entry. Obsidian is a note-taking app that stores linked Markdown files.
meta-pdf-reformat-pipeline
Modernize a legacy PDF: structural extraction → natural-language rewrite of problem pages → audit summary → re-merge into the final PDF.
software-copyright-materials
A workflow for creating Chinese application materials for software copyright registration from a real software project.
ectd-xml-compiler
Automatically convert uploaded drug application documents (Word/PDF) into XML skeleton structure compliant with eCTD 4.0/3.2.2 specifications.
audit-export
Export the full CocoAudit trail as a stakeholder-ready compliance document.
software-certificate-skill
An automated workflow for preparing Chinese software-copyright registration materials from a real software project. It produces application information, an operation manual, and source-code documents with evidence from the project.