relatar-processo

relatar-processo is a command for coding agents from georgemarmelstein/superjurista-dev. It costs 14 tokens per session (5,376 once invoked), scanned A, original, MIT.

A command workflow for producing a report about a court case. It first creates a timeline from a case file, then uses that timeline and the original file to write the report.

In plain words
What is it for?
Reading a process file, creating a case timeline, and saving a numbered report in Markdown format.
Why use it?
It separates date ordering from report writing, making the process easier to check. It also defines required files, validation markers, and retry limits.

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/relatar-processo
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 relatar-processo

README.md
[![agentmods](https://agentmods.dev/badge/commands/georgemarmelstein/superjurista-dev/relatar-processo.svg)](https://agentmods.dev/commands/georgemarmelstein/superjurista-dev/relatar-processo)
Your own site
<a href="https://agentmods.dev/commands/georgemarmelstein/superjurista-dev/relatar-processo"><img src="https://agentmods.dev/badge/commands/georgemarmelstein/superjurista-dev/relatar-processo.svg" alt="Measured on agentmods" height="20"></a>
Per session 14 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 5,376 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 5.1 $0.00014 $0.05376
Opus 5 $0.00007 $0.02688
Sonnet 5 $0.00003 $0.01075
Haiku 4.5 $0.00001 $0.00538

Measured 5d ago against content hash 3e5ec050ae70, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

relatar-processo 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 5d 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/relatar-processo.md · 501 lines

How it starts

The opening of the file, as written. The whole thing — 501 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Orquestrador: Relatar Processo v2.0

<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) </regras_uso>

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

<limite_tentativas> | Escopo | Limite | |--------|--------| | Por etapa | 2 tentativas | | Total no pipeline | 4 tentativas | </limite_tentativas>

<contratos_dados>

# Etapa Entrada Saída Validação
0 Preparação $ARGUMENTS $WORKSPACE, $NUMERO Variáveis extraídas, processo.txt existe
1 Linha do Tempo $WORKSPACE/processo.txt $WORKSPACE/$NUMERO-linha-tempo.md Sinalizadores início/fim
2 Relatório $WORKSPACE/processo.txt + linha-tempo $WORKSPACE/$NUMERO-relatorio.md Sinalizadores início/fim
3 Finalização Arquivos gerados Resumo ao usuário Todos os arquivos existem
</contratos_dados>

<rastreamento_progresso>

<regra_ouro> | Quem | Pode usar TodoWrite? | |------|---------------------| | Orquestrador (contexto principal) | SIM - gerencia todo o progresso | | Subagentes (Task tool) | NÃO - apenas retornam resultado | </regra_ouro>

<quando_atualizar> | Momento | Ação | |---------|------| | Início do pipeline | Criar TodoWrite com TODAS as etapas (status: pending) | | Antes de disparar etapa | Marcar etapa como in_progress | | Após validar output | Marcar etapa como completed | | Se falhar 2x | Manter in_progress e PARAR | </quando_atualizar>

<formato_todowrite> javascript TodoWrite([ {content: "Etapa 0 - Preparação", status: "completed", activeForm: "Preparando"}, {content: "Etapa 1 - Linha do Tempo", status: "in_progress", activeForm: "Extraindo cronologia"}, {content: "Etapa 2 - Relatório", status: "pending", activeForm: "Gerando relatório"}, {content: "Etapa 3 - Finalização", status: "pending", activeForm: "Finalizando"}, ]) </formato_todowrite> </rastreamento_progresso>

Read the full file on GitHub · 501 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. 5d ago First seen · 501 lines · 14 tokens per session scan A 3e5ec050ae70

Subscribe to this mod's changes

relatar-processo is a command published in the GitHub repository georgemarmelstein/superjurista-dev (20 stars, last pushed 1mo ago), licensed MIT. It adds 14 tokens to every session and 5,376 once invoked, about $0.0001 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.