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.
git clone --depth 1 https://github.com/georgemarmelstein/superjurista-devWrote 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/pipeline-revisao-minuta)<a href="https://agentmods.dev/commands/georgemarmelstein/superjurista-dev/pipeline-revisao-minuta"><img src="https://agentmods.dev/badge/commands/georgemarmelstein/superjurista-dev/pipeline-revisao-minuta/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/pipeline-revisao-minuta"><img src="https://agentmods.dev/badge/commands/georgemarmelstein/superjurista-dev/pipeline-revisao-minuta.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 | $0.00033 | $0.07540 |
| Opus 5 | $0.00016 | $0.03770 |
| Sonnet 5 | $0.00007 | $0.01508 |
| Haiku 4.5 | $0.00003 | $0.00754 |
Grade A, and why
pipeline-revisao-minuta 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 11d 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 — 334 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Orquestrador: Pipeline de Revisão de Minuta v3.0
v3.0 — retomada + gate por script + citações em duas passadas (molde vivo:
.claude/commands/pipeline-sentenca.md). O que mudou da v2: (1) FRONTMATTER consertado — o YAML agora é a PRIMEIRA linha do arquivo (na v2 vinha DEPOIS de um H1, defeito conhecido); (2) RETOMADA — revisão cujo relatório já existe e passa no gate não roda de novo (5 revisores opus — retrabalho é o desperdício mais caro); (3) validação DETERMINÍSTICA —scripts/verificar_revisao.pyconfere as âncoras (normalizadas de acento/caixa); o orquestrador NÃO lê relatórios para validar; (4) CITAÇÕES EM DUAS PASSADAS —scripts/verificar_citacoes.pyroda ANTES dos revisores (1ª passada, informativa: os [ERRO] alimentam o verificador-fontes) e DE NOVO sobre a robustecida (2ª passada, FATAL, com--ignorar-apos "log de alterações", porque o Log de Alterações AUTO-CITA trechos da minuta — 26 falsos positivos num documento real, calibração de 11/07/2026); (5) a âncora de fim da remessa foi alinhada ao sinalizador REAL do agente ("Verificação de remessa necessária concluída." — a tabela v2 impunha frase mais curta; o gate aceita as duas); (6) subagente responde UMA LINHA de status — o relatório vive no arquivo, nunca na conversa.
<scripts_deterministicos> | Script | Função | |--------|--------| | scripts/verificar_revisao.py | Gate + retomada: varredura (PENDENTES), --etapa (exit-coded), --etapas (subconjunto), --gate (final) | | scripts/verificar_citacoes.py | Gate de citações verbatim: 1ª passada sobre $MINUTA (informativa) e 2ª passada sobre a robustecida (fatal, com --ignorar-apos "log de alterações") | </scripts_deterministicos>
<agents_utilizados> | Agent | Capacidade | Arquivo | |-------|------------|---------| | analista-embargabilidade | Vícios embargáveis (omissão, contradição, obscuridade, erro material) | .claude/agents/revisao/analista-embargabilidade.md | | verificador-calculos | Critérios de cálculo (correção, juros, marcos, EC 113/2021) | .claude/agents/revisao/verificador-calculos.md | | verificador-fontes | Pertinência/vigência de citações (autenticidade é do script) | .claude/agents/revisao/verificador-fontes.md | | verificador-honorarios | Honorários advocatícios (CPC/2015, leis especiais, temas) | .claude/agents/revisao/verificador-honorarios.md | | verificador-remessa | Remessa necessária (cabimento, dispensa, regimes especiais) | .claude/agents/revisao/verificador-remessa.md | | redator-minuta-robustecida | Consolida revisões em minuta robustecida com log | .claude/agents/redacao/redator-minuta-robustecida.md | </agents_utilizados>
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.
- 11d ago First seen · 334 lines · 33 tokens per session scan A 6106b88d58d2
pipeline-revisao-minuta is a command published in the GitHub repository georgemarmelstein/superjurista-dev (22 stars, last pushed 1mo ago), licensed MIT. It adds 33 tokens to every session and 7,540 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.
Other commands, from other repositories
brand-generate
Generate an on-brand document from a saved Brand Profile.
prose-review-docs
Reviews markdown documentation files or directories against the active prose style rules — the plugin's vendor-neutral baseline plus your organization's overlay when one is configured. Accepts a file path or directory (recursive). Runs prose-style-checker and optionally Vale. Supports --fix to auto-apply safe…
cti-report
Render case deliverables — relationship graph (PNG/SVG/Mermaid) and a polished PDF/DOCX assessment. Usage: /cti-report [--graph|--pdf].
ppt-image2-editable-rebuild
Rebuild image2 or imagegen reference slides as editable PowerPoint decks.
render-figures
Compile all .tex and .typ figure files in a directory.
harness-onboarding
Generate a human-readable onboarding document from HARNESS.md, AGENTS.md, and REFLECTIONLOG.md — a friendly guide for new team members.