pipeline-sentenca

pipeline-sentenca is a command for Claude Code from georgemarmelstein/superjurista-dev. It costs 31 tokens per session (14,158 once invoked), scanned A, original, MIT.

Pipeline para preparar sentenças judiciais, com triagem do processo, pesquisa, análise de provas e redação baseada em fontes registradas. Sentença judicial é a decisão escrita que encerra ou resolve uma fase de um processo.

In plain words
What is it for?
Serve para analisar processos, pesquisar jurisprudência, avaliar provas, consolidar fontes, verificar citações e produzir uma minuta de sentença.
Why use it?
Ajuda a escolher as etapas necessárias para cada processo e a manter as citações ligadas aos trechos exatos das fontes pesquisadas.

Command for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: reads .claude/ paths; names the TodoWrite tool.

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

Good fit Serve para analisar processos, pesquisar jurisprudência, avaliar provas, consolidar fontes, verificar citações e produzir uma minuta de sentença.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/georgemarmelstein/superjurista-dev/pipeline-sentenca
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.

Clone the repo
git clone --depth 1 https://github.com/georgemarmelstein/superjurista-dev

Made for: Claude Code.

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 pipeline-sentenca

README.md
[![agentmods](https://agentmods.dev/badge/commands/georgemarmelstein/superjurista-dev/pipeline-sentenca.svg)](https://agentmods.dev/commands/georgemarmelstein/superjurista-dev/pipeline-sentenca)
Your own site
<a href="https://agentmods.dev/commands/georgemarmelstein/superjurista-dev/pipeline-sentenca"><img src="https://agentmods.dev/badge/commands/georgemarmelstein/superjurista-dev/pipeline-sentenca.svg" alt="Measured on agentmods" height="20"></a>
Per session 31 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 14,158 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 $0.00031 $0.14158
Opus 5 $0.00015 $0.07079
Sonnet 5 $0.00006 $0.02832
Haiku 4.5 $0.00003 $0.01416

Measured 8d ago against content hash 544713508d1f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

pipeline-sentenca 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 8d 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/pipeline-sentenca.md · 559 lines

How it starts

The opening of the file, as written. The whole thing — 559 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Orquestrador: Pipeline de Sentença v3.1

v3.1 — Sentença Inteligente (plano em docs/plans/2026-07-11-sentenca-inteligente-triagem-e-regime-verbatim.md). O que mudou da v3.0: (1) TRIAGEM COGNITIVA (Etapa 2.5, sonnet, SEMPRE obrigatória) — certifica rotina com base em EVIDÊNCIA (buscas de reconhecimento nos MCPs), grava rota estruturada em disco e o orquestrador a lê por script (--rota), nunca lendo o documento; (2) TRILHOS CONDICIONAIS — se a rota exigir, os MESMOS agentes de pesquisa/probática são despachados DIRETO no workspace do processo (sem orquestrador aninhado), validados pelos gates dos respectivos pipelines (verificar_pesquisa.py/verificar_probatica.py com --etapas); (3) REGIME VERBATIM — triagem e trilho de pesquisa gravam fontes com trecho EXATO dos MCPs, merge_fontes.py produz $NUMERO-fontes.json (a ÚNICA origem admitida para citar jurisprudência) e verificar_citacoes.py confere cada citação nas Etapas 4 e 6; (4) VÁLVULA ESCALAR — a análise pode pedir trilho que a triagem não previu (gate sai com exit 3), com MÁXIMO 1 escalada por processo e detecção PERSISTENTE em disco (sobrevive a /clear). Toda a disciplina v3.0 permanece: retomada por PENDENTES, gate por script, merge por script, resposta de 1 linha.

Trilho 2.7 v2 — tribunal probatório ADVERSARIAL: o trilho probático deste pipeline usa os agentes de .claude/agents/tribunal/ (teses pró-autor/pró-réu em paralelo → réplicas CRUZADAS em paralelo → síntese do juiz-mediador no consolidado). As lentes metodológicas (pearl/haack/fbd + consolidador-probatica) continuam no /pipeline-probatica standalone — mesma tabela do verificar_probatica.py, subconjuntos diferentes.

<scripts_deterministicos> | Script | Função | |--------|--------| | scripts/verificar_sentenca.py | Gate + retomada do tronco: varredura (PENDENTES, inclui triagem), --etapa (exit-coded; analise pode sair 3 = ESCALAR), --rota (imprime ROTA:/TEMA:/FATO:; + JUSTIFICATIVA: em rota direta), --gate (final) | | scripts/merge_sentenca.py | Etapa 5: relatório+fundamentação → sentença, validada; sem LLM, sem contexto | | scripts/verificar_pesquisa.py | Gate do trilho 2.6: --etapas (varredura do trilho), --etapa , fechamento exit-coded com --etapas ,consolidado --gate | | scripts/verificar_probatica.py | Gate do trilho 2.7 (subconjunto ADVERSARIAL): --etapas inventario,tese-pro-autor,tese-pro-reu,replica-pro-autor,replica-pro-reu,consolidado (varredura), --etapa , fechamento exit-coded com --etapas ... --gate | | scripts/merge_fontes.py | Funde os parciais fontes-*.json em $NUMERO-fontes.json (valida whitelist, deduplica, renumera); roda SEMPRE após a triagem e de novo após o trilho de pesquisa | | scripts/verificar_citacoes.py | Gate de citações verbatim: Etapa 4 (documento default -fundamentacao.md) e Etapa 6 (--doc=-sentenca.md) | </scripts_deterministicos>

Read the full file on GitHub · 559 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. 8d ago First seen · 559 lines · 31 tokens per session scan A 544713508d1f

Subscribe to this mod's changes

pipeline-sentenca is a command published in the GitHub repository georgemarmelstein/superjurista-dev (21 stars, last pushed 1mo ago), licensed MIT. It adds 31 tokens to every session and 14,158 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.