representacoes-cautelares

representacoes-cautelares is a skill for Claude Code, Codex from ThomasMoreAI/legal-skills-open. It costs 126 tokens per session (1,279 once invoked), scanned A, original, Apache-2.0.

A Portuguese-language drafting workflow for police submissions and court requests for investigative measures, such as preventive detention, searches, and access to phone, online, banking, or tax records. It organizes facts, evidence, legal grounds, and clearly limited requests.

In plain words
What is it for?
Use it to prepare a court-facing request that identifies targets, places, accounts, devices, addresses, objects, and time periods, with each requested measure supported by concrete case facts.
Why use it?
It helps turn investigation material into a structured court filing while addressing necessity, proportionality, scope, and the risk of overly broad requests. It is meant for precautionary requests, not a final investigation report.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions Codex.

Good fit Use it to prepare a court-facing request that identifies targets, places, accounts, devices, addresses, objects, and time periods, with each requested measure supported by concrete case facts.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/thomasmoreai/legal-skills-open/representacoes-cautelares
Install

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.

Any agent
npx skills add ThomasMoreAI/legal-skills-open --skill representacoes-cautelares
Clone the repo
git clone --depth 1 https://github.com/ThomasMoreAI/legal-skills-open

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for representacoes-cautelares

README.md
[![agentmods](https://agentmods.dev/badge/skills/thomasmoreai/legal-skills-open/representacoes-cautelares/github.svg)](https://agentmods.dev/skills/thomasmoreai/legal-skills-open/representacoes-cautelares)
Your own site
<a href="https://agentmods.dev/skills/thomasmoreai/legal-skills-open/representacoes-cautelares"><img src="https://agentmods.dev/badge/skills/thomasmoreai/legal-skills-open/representacoes-cautelares/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.

agentmods 80×15 button for representacoes-cautelares

Your own site · 80×15
<a href="https://agentmods.dev/skills/thomasmoreai/legal-skills-open/representacoes-cautelares"><img src="https://agentmods.dev/badge/skills/thomasmoreai/legal-skills-open/representacoes-cautelares.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 126 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,279 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00126 $0.01279
Opus 5 $0.00063 $0.00639
Sonnet 5 $0.00025 $0.00256
Haiku 4.5 $0.00013 $0.00128

Measured 12d ago against content hash 527b9e48fc63, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

representacoes-cautelares 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.

br/criminal/skills/representacoes-cautelares/SKILL.md · 103 lines

How it starts

The opening of the file, as written. The whole thing — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Representacoes Cautelares

Redija pecas cautelares dirigidas ao Juizo, com foco em necessidade, adequacao, proporcionalidade e delimitacao objetiva dos pedidos. Use esta skill para pedir medida investigativa ou constritiva. Nao use como template de relatorio final de inquerito.

Fluxo de trabalho

  1. Identificar a medida principal e as medidas acessorias.
  2. Montar a base fatico-probatoria minima antes de redigir.
  3. Delimitar alvos, locais, contas, linhas, aparelhos, IPs, e-mails, objetos e periodo.
  4. Fundamentar cada medida com requisitos proprios e elementos concretos dos autos.
  5. Formular pedidos objetivos, executaveis e individualizados.
  6. Revisar risco de nulidade, excesso ou pedido generico.
  7. Gerar a versao final em .docx, salvo se o usuario pedir expressamente apenas texto.

Escolha da variante

  • Para prisao preventiva, busca e apreensao, medidas cautelares diversas ou peca combinada, ler references/modelo-prisao-busca-cautelares.md.
  • Para quebra de sigilo telefonico, telematico, bancario ou fiscal, ler references/modelo-quebra-sigilo.md.
  • Para decidir a estrutura da peca e quando combinar capitulos, ler references/variantes.md.
  • Para geracao e padrao visual do Word, ler references/formatacao-docx.md.
  • Antes de entregar, ler references/checklist-qualidade.md.
  • Se precisar de pedidos secundarios recorrentes, ler references/pedidos-acessorios.md.

Estrutura base da peca

Adote, em regra, esta sequencia:

  1. Enderecamento ao Juizo competente.
  2. Identificacao do procedimento, investigados, vitima e tipificacao provisoria.
  3. Preambulo com a autoridade policial, base legal de atuacao e medidas requeridas.
  4. Sumario dos fatos, em ordem cronologica, com prejuizo e modus operandi quando relevantes.
  5. Investigados e diligencias executadas, destacando a ligacao entre prova e alvo.
  6. Fundamentacao juridica por medida requerida, em subtitulos separados.
  7. Pedidos, em lista clara, na mesma ordem da fundamentacao.
  8. Fechamento com local, data e assinatura.

Read the full file on GitHub · 103 lines

Changes

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.

  1. 12d ago First seen · 103 lines · 126 tokens per session scan A 527b9e48fc63

Subscribe to this mod's changes

representacoes-cautelares is a skill published in the GitHub repository ThomasMoreAI/legal-skills-open (72 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 126 tokens to every session and 1,279 once invoked, about $0.0006 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.