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 pgu-e-estrutura-da-agu-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/pgu-e-estrutura-da-agu-sbroggioadv)<a href="https://agentmods.dev/skills/thomasmoreai/legal-skills-open/pgu-e-estrutura-da-agu-sbroggioadv"><img src="https://agentmods.dev/badge/skills/thomasmoreai/legal-skills-open/pgu-e-estrutura-da-agu-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/pgu-e-estrutura-da-agu-sbroggioadv"><img src="https://agentmods.dev/badge/skills/thomasmoreai/legal-skills-open/pgu-e-estrutura-da-agu-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 | $0.00282 | $0.02943 |
| Opus 5.5 | $0.00113 | $0.01177 |
| Sonnet 5.5 | $0.00056 | $0.00589 |
| Haiku 4.5 | $0.00028 | $0.00294 |
Grade A, and why
pgu-e-estrutura-da-agu-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 — 142 lines — stays where its author put it; the contents beside it link to each section on GitHub.
pgu-e-estrutura-da-agu — resolver a atribuição antes de escrever a peça
Advocacia pública federal não é um órgão só. É uma instituição com órgãos de direção superior, de
execução e vinculados, cada um com um perímetro escrito em lei. Esta skill entrega o mapa e a
pergunta que ele responde: quem tem atribuição neste caso? Texto verbatim em
context/lc-73-agu.md; nada aqui sai de memória. Este produto atende a União.
⚠️ TV7 — a trava que dá origem a esta skill
A PGFN não é a AGU inteira. Ela é um órgão da AGU com competência específica: dívida ativa da União de natureza tributária e representação em causas de natureza fiscal (art. 12). A defesa não-fiscal da União é da Advocacia da União / PGU; a consultoria ao Presidente e ao Executivo é da Consultoria-Geral da União e das Consultorias Jurídicas; a representação das autarquias e fundações federais é dos órgãos jurídicos dessas entidades, campo da PGF. Escrever "a PGFN defende a União" fora da matéria fiscal é erro de escopo, e é o que esta skill impede.
Quando esta skill entra
- Antes de qualquer peça federal — é a primeira pergunta, não a última.
- Quando a matéria mistura crédito e não-crédito e não se sabe qual órgão conduz.
- Quando a causa envolve autarquia ou fundação e não a União diretamente.
- Quando é preciso saber perante qual instância cada órgão atua.
1. A instituição e a sua composição
Art. 1º: "A Advocacia-Geral da União é a instituição que representa a União judicial e extrajudicialmente." Parágrafo único: cabem-lhe as atividades de consultoria e assessoramento jurídicos ao Poder Executivo.
Art. 2º — a composição:
| Grupo | Órgãos |
|---|---|
| I — direção superior | a) o Advogado-Geral da União; b) a Procuradoria-Geral da União e a da Fazenda Nacional; c) a Consultoria-Geral da União; d) o Conselho Superior; e) a Corregedoria-Geral da Advocacia da União |
| II — execução | a) as Procuradorias Regionais da União e as da Fazenda Nacional, as Procuradorias da União e as da Fazenda Nacional nos Estados e no DF e as Procuradorias Seccionais; b) a Consultoria da União, as Consultorias Jurídicas dos Ministérios, da Secretaria-Geral e demais Secretarias da Presidência e do Estado-Maior das Forças Armadas |
| III — assistência direta | o Gabinete do Advogado-Geral da União |
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 · 142 lines · 282 tokens per session scan A 44526f21619b
pgu-e-estrutura-da-agu-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 282 tokens to every session and 2,943 once invoked, about $0.0011 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…