Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/georgemarmelstein/superjurista-devnpx agentmods add commands/georgemarmelstein/superjurista-dev/baixar-pjeWrote 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/commands/georgemarmelstein/superjurista-dev/baixar-pje)<a href="https://agentmods.dev/commands/georgemarmelstein/superjurista-dev/baixar-pje"><img src="https://agentmods.dev/badge/commands/georgemarmelstein/superjurista-dev/baixar-pje/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/commands/georgemarmelstein/superjurista-dev/baixar-pje"><img src="https://agentmods.dev/badge/commands/georgemarmelstein/superjurista-dev/baixar-pje.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 | $0.00011 | $0.01146 |
| Opus 5 | $0.00005 | $0.00573 |
| Sonnet 5 | $0.00002 | $0.00229 |
| Haiku 4.5 | $0.00001 | $0.00115 |
Grade A, and why
baixar-pje 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 10d 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 — 165 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/baixar-pje
Baixa processos do PJE. NAO converte para TXT.
Argumentos
$1 = quantidade (padrao: 1)
$2 = modo (padrao: sentenca)
EXECUCAO OBRIGATORIA
Etapa 0: Verificar sessao existente
python -c "
import json
from pathlib import Path
import sys
if not Path('pje_session.json').exists():
print('SESSAO_INEXISTENTE')
sys.exit(1)
d = json.load(open('pje_session.json'))
has_xpje = 'X-pje-cookies' in d.get('headers_api', {})
if has_xpje:
print('SESSAO_COMPLETA')
else:
print('SESSAO_INCOMPLETA')
sys.exit(1)
"
- Se
SESSAO_COMPLETA→ Pular para Etapa 2 (Listar processos) - Se
SESSAO_INEXISTENTEouSESSAO_INCOMPLETA→ Ir para Etapa 1
Etapa 1: Capturar sessao (Chrome MCP + HAR)
Passo 1.1: Verificar se usuario ja esta logado
mcp__claude-in-chrome__tabs_context_mcp
Verificar se existe aba com URL contendo pje1g.trf5.jus.br.
Passo 1.2: Se NAO logado, fazer login via Chrome MCP
-
Pedir credenciais ao usuario (se nao tiver):
- CPF
- Senha
-
Navegar para login:
mcp__claude-in-chrome__navigate -> https://pje1g.trf5.jus.br/pje/login.seam
- Preencher formulario:
mcp__claude-in-chrome__read_page (filter: interactive)
mcp__claude-in-chrome__form_input (campo CPF)
mcp__claude-in-chrome__form_input (campo Senha)
mcp__claude-in-chrome__computer (click no botao Entrar)
- Aguardar login:
mcp__claude-in-chrome__computer (wait 3s)
- Verificar se logou (URL deve conter
QuadroAvisooupainel-usuario)
Passo 1.3: Pedir HAR ao usuario
Exibir mensagem:
Login realizado! Agora preciso capturar os cookies de sessao.
Por favor:
1. Na aba do PJE, pressione F12 (DevTools)
2. Clique na aba "Network" (Rede)
3. Clique em alguma tarefa no painel (para gerar requisicoes)
4. Clique direito na lista de requisicoes → "Save all as HAR with content"
5. Me informe o caminho do arquivo salvo
Exemplo: C:\Users\georg\Downloads\pje1g.trf5.jus.br.har
Passo 1.4: Extrair cookies do HAR
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.
- 10d ago First seen · 165 lines · 0 tokens per session scan A 7bb8b6531dd2
baixar-pje is a command published in the GitHub repository georgemarmelstein/superjurista-dev (22 stars, last pushed 1mo ago), licensed MIT. It adds 11 tokens to every session and 1,146 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.
Other commands, from other repositories
audit-export
Exportar audit trail en JSON/CSV/PDF para auditorías externas. ISO 42001 & NIST AI RMF compliant.
sign
Sign a PDF — stamp a signature block (name + date, or a PNG signature) on a signed copy.
family-tree
A tool that reads a Japanese family-register PDF and creates a self-contained HTML family relationship chart for inheritance matters. A family register is an official record used to establish family relationships and status.
finalize
A final submission workflow that protects a client's edits, creates a signed PDF, and prepares a filing package for the 02hearings location.
/a11y-report
Reporte de conformidad de accesibilidad para stakeholders y legal. Tres formatos: ejecutivo (resumen + score), técnico (detalles completos + código), legal (declaración VPAT/Section 508). Tracking de tendencias. Exportable.
audit
Generate a structured audit report for the current session or a specified time range. The report summarises every governed action, lists any blocked requests, and provides a compliance-ready summary you can download or share.