skill-probatica

skill-probatica is a command for coding agents from georgemarmelstein/superjurista-dev. It costs 30 tokens per session (9,559 once invoked), scanned A, original, MIT.

Um comando que organiza a análise de provas em várias etapas e por tipos de documento. Ele coordena analistas especializados para criar um inventário, avaliar a qualidade das provas e encontrar lacunas.

In plain words
What is it for?
Serve para inventariar documentos, fazer triagem, analisar diferentes tipos de prova, mapear sua qualidade e detectar o que ainda falta no processo.
Why use it?
Casos com muitos documentos podem esconder informações ausentes ou evidências frágeis. O fluxo divide o trabalho e verifica se cada etapa foi concluída corretamente.

Command

Part of the superjurista-dev plugin — 11 skills, 22 commands, 7 agents shipped together

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.

agentmods
npx agentmods add commands/georgemarmelstein/superjurista-dev/skill-probatica
Clone the repo
git clone --depth 1 https://github.com/georgemarmelstein/superjurista-dev

Or install superjurista-dev, the plugin that ships this one along with the rest of its 11 skills, 22 commands, 7 agents.

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 skill-probatica

README.md
[![agentmods](https://agentmods.dev/badge/commands/georgemarmelstein/superjurista-dev/skill-probatica.svg)](https://agentmods.dev/commands/georgemarmelstein/superjurista-dev/skill-probatica)
Your own site
<a href="https://agentmods.dev/commands/georgemarmelstein/superjurista-dev/skill-probatica"><img src="https://agentmods.dev/badge/commands/georgemarmelstein/superjurista-dev/skill-probatica.svg" alt="Measured on agentmods" height="20"></a>
Per session 30 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 9,559 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00030 $0.09559
Opus 5 $0.00015 $0.04779
Sonnet 5 $0.00006 $0.01912
Haiku 4.5 $0.00003 $0.00956

Measured 4d ago against content hash 0f110e3b6c12, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

skill-probatica 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 4d 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.

scaffold/commands/skill-probatica.md · 850 lines

How it starts

The opening of the file, as written. The whole thing — 850 lines — stays where its author put it; the contents beside it link to each section on GitHub.

<tools_subagentes> | Tool | Função | |------|--------| | Read | Ler prompts e entradas | | Write | Salvar resultados | </tools_subagentes>

<regras_uso> - Subagentes LEEM prompts diretamente (não recebem cópia) - Orquestrador NÃO executa tarefas dos subagentes - Orquestrador NÃO lê o prompt: instrui subagente a ler via Read - Cada subagente tem contexto ISOLADO (não vê conversa anterior) - EXCEÇÃO Etapa 2: Orquestrador LÊ o inventário para fazer triagem (não é tarefa de subagente) </regras_uso>

<sinalizador_ausente> AVISO: Sinalizador não encontrado. -> Regenerar com SUFIXO DE CORREÇÃO específico -> Se falhar 2x -> PARAR e informar usuário </sinalizador_ausente>

<processo_nao_encontrado> Se processo.txt não encontrado em data/sentenca/$NUMERO: -> Verificar em data/decisao/$NUMERO -> Se encontrado, usar como $WORKSPACE -> Se não encontrado em nenhum, PARAR e informar usuário </processo_nao_encontrado>

<limite_tentativas> | Escopo | Limite | |--------|--------| | Por etapa | 2 tentativas | | Total no pipeline | 12 tentativas | </limite_tentativas>

<contratos_dados>

# Etapa Entrada Saída Validação
0 Preparação $ARGUMENTS $WORKSPACE, $NUMERO, $PROCESSO Variáveis extraídas
1 Inventário $PROCESSO $NUMERO-inventario.md "# INVENTÁRIO PROBATÓRIO" ... "É o que satisfaz inventariar do acervo probatório."
2 Triagem inventário Lista de analistas a ativar Orquestrador lê inventário e decide
3 Analistas $PROCESSO + inventário $NUMERO-analise-[tipo].md Sinalizadores de cada analista
4 Mapeamento inventário + análises $NUMERO-mapa-qualidade.md "# MAPA DE QUALIDADE PROBATÓRIA" ... "Mapa de qualidade probatória concluído."
5 Lacunas mapa + inventário $NUMERO-lacunas.md "# ANÁLISE DE LACUNAS PROBATÓRIAS" ... "Análise de lacunas probatórias concluída."
6 Finalização - Resumo ao usuário -
</contratos_dados>

Read the full file on GitHub · 850 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. 4d ago First seen · 850 lines · 30 tokens per session scan A 0f110e3b6c12

Subscribe to this mod's changes

skill-probatica is a command published in the GitHub repository georgemarmelstein/superjurista-dev (20 stars, last pushed 1mo ago), licensed MIT. It adds 30 tokens to every session and 9,559 once invoked, about $0.0002 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.