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-sentenca)<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>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 | $0.00031 | $0.14158 |
| Opus 5 | $0.00015 | $0.07079 |
| Sonnet 5 | $0.00006 | $0.02832 |
| Haiku 4.5 | $0.00003 | $0.01416 |
Grade A, and why
pipeline-sentenca scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 559 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Orquestrador: Pipeline de Sentença v3.1
v3.1 — Sentença Inteligente (plano em
docs/plans/2026-07-11-sentenca-inteligente-triagem-e-regime-verbatim.md). O que mudou da v3.0: (1) TRIAGEM COGNITIVA (Etapa 2.5, sonnet, SEMPRE obrigatória) — certifica rotina com base em EVIDÊNCIA (buscas de reconhecimento nos MCPs), grava rota estruturada em disco e o orquestrador a lê por script (--rota), nunca lendo o documento; (2) TRILHOS CONDICIONAIS — se a rota exigir, os MESMOS agentes de pesquisa/probática são despachados DIRETO no workspace do processo (sem orquestrador aninhado), validados pelos gates dos respectivos pipelines (verificar_pesquisa.py/verificar_probatica.pycom--etapas); (3) REGIME VERBATIM — triagem e trilho de pesquisa gravam fontes com trecho EXATO dos MCPs,merge_fontes.pyproduz$NUMERO-fontes.json(a ÚNICA origem admitida para citar jurisprudência) everificar_citacoes.pyconfere 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-probaticastandalone — mesma tabela doverificar_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>
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.
- 8d ago First seen · 559 lines · 31 tokens per session scan A 544713508d1f
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.
Other commands, from other repositories
deps-audit
Audit project dependencies for vulnerabilities, outdated packages, license conflicts, and supply chain risks — then provide actionable remediation strategies.
review-epo-claims
Analyze patent claims for EPO Art. 84 EPC compliance - clarity, conciseness, support by description.
voice-compliance
Voice/telephony compliance check — invokes voice-ai-reviewer to produce TM-voice-{slug}.md with TCPA, STIR/SHAKEN, state recording-consent, EU AI Act Art. 50, and synth-voice deepfake-law gaps.
review-policy
Review a policy document for structure, coverage, and language quality.
at-dsgvo
You are helping an enterprise architect generate an Austrian Data Protection Assessment — the Austrian-specific GDPR layer applied by the Datenschutzbehörde (DSB) under the Datenschutzgesetz (DSG 2018, BGBl. I Nr. 165/1999 as amended). Run this after /arckit:eu-rgpd to add Austrian obligations that go beyond the EU…
au-pspf
You are an enterprise architect generating a Protective Security Policy Framework (PSPF) compliance assessment for an Australian Government entity or contractor handling government information.