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 improbidade-defesa-e-autoria-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/improbidade-defesa-e-autoria-sbroggioadv)<a href="https://agentmods.dev/skills/thomasmoreai/legal-skills-open/improbidade-defesa-e-autoria-sbroggioadv"><img src="https://agentmods.dev/badge/skills/thomasmoreai/legal-skills-open/improbidade-defesa-e-autoria-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/improbidade-defesa-e-autoria-sbroggioadv"><img src="https://agentmods.dev/badge/skills/thomasmoreai/legal-skills-open/improbidade-defesa-e-autoria-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 | $0.00185 | $0.02655 |
| Opus 5.5 | $0.00074 | $0.01062 |
| Sonnet 5.5 | $0.00037 | $0.00531 |
| Haiku 4.5 | $0.00018 | $0.00265 |
Grade A, and why
improbidade-defesa-e-autoria-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 — 145 lines — stays where its author put it; the contents beside it link to each section on GitHub.
improbidade-defesa-e-autoria — os dois lados da mesma lei
Este produto atende o Estado. A improbidade é a única matéria desta camada em que a procuradoria pode estar nos dois polos: propondo a ação em nome do ente, ou defendendo o agente e o ente quando a ação vem de fora. Esta skill trata as duas posições sem confundir a régua.
TV1 — a trava que entra em toda saída, sem exceção
As ADIs 7156 e 7236 foram julgadas pelo STF em 01/07/2026. No retrato oficial pós-julgamento, o Tribunal invalidou a redução pela metade do prazo prescricional prevista na reforma e preservou a exigência de dolo e o rol taxativo de condutas.
Consequência literal, imposta por context/travas-defasagem.md (TV1): não tratar as ADIs como
pendentes e não converter a notícia oficial em conclusões que ela não contém. O produto pode usar
o resultado acima; alcance, modulação, marco temporal ou consequência específica que dependa do
acórdão integral sai [VERIFICAR]. Toda análise, parecer ou peça desta skill carrega este
snapshot pós-julgamento; sem ele, o suprema-corte-fazendaria reprova pelo gate de defasagem (R3).
O eixo prático: dolo específico
Com lastro (vigência ✅ conferida no Planalto): a redação da Lei 14.230/2021 exige dolo específico. É o divisor que reorganiza os dois papéis:
- Culpa não basta. Negligência, imperícia e imprudência do gestor não sustentam improbidade sob a redação vigente.
- Erro não basta. Interpretação equivocada da norma, decisão administrativa malsucedida ou resultado ruim não são, por si, ato ímprobo.
- Dano ao erário, sozinho, não basta. Prejuízo é elemento de algumas hipóteses, não substituto do elemento subjetivo.
- O que sustenta é a demonstração de que o agente quis o resultado ilícito — vontade livre e consciente dirigida ao fim vedado, comprovada, não presumida do resultado.
O ente como AUTOR — quando propor
A pergunta não é "houve irregularidade?", é "há prova de dolo específico?". Roteiro de decisão, nesta ordem:
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 · 145 lines · 185 tokens per session scan A b66ef7b4c4f8
improbidade-defesa-e-autoria-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 185 tokens to every session and 2,655 once invoked, about $0.0007 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…