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-probatica)<a href="https://agentmods.dev/commands/georgemarmelstein/superjurista-dev/pipeline-probatica"><img src="https://agentmods.dev/badge/commands/georgemarmelstein/superjurista-dev/pipeline-probatica.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 | $0.00029 | $0.05579 |
| Opus 5 | $0.00015 | $0.02789 |
| Sonnet 5 | $0.00006 | $0.01116 |
| Haiku 4.5 | $0.00003 | $0.00558 |
Grade A, and why
pipeline-probatica 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 — 273 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Orquestrador: Pipeline de Análise Probatória v3.0
v3.0 — retomada + gate por script (molde vivo:
.claude/commands/pipeline-sentenca.md). O que mudou da v2: (1) RETOMADA — análise cujo artefato já existe e passa no gate não roda de novo (as 5 etapas rodam em opus — retrabalho é o desperdício mais caro); (2) validação DETERMINÍSTICA —scripts/verificar_probatica.pyconfere as âncoras (normalizadas de acento/caixa); o orquestrador NÃO lê documentos para validar; (3) subagente responde UMA LINHA de status — o documento vive no arquivo, nunca na conversa; (4) as âncoras foram alinhadas aos sinalizadores REAIS dos agentes (o fechamento do inventário é "É o que satisfaz inventariar do acervo probatório." — a v2 impunha outra frase; o gate aceita as duas para não reprovar artefato antigo bom). Os 5 agentes e seus contratos analíticos são os mesmos.
<scripts_deterministicos> | Script | Função | |--------|--------| | scripts/verificar_probatica.py | Gate + retomada: varredura (PENDENTES), --etapa (exit-coded), --etapas (subconjunto), --gate (final) | </scripts_deterministicos>
<agents_utilizados> | Agent | Capacidade | Arquivo | |-------|------------|---------| | inventariador-probatica | Cataloga provas sem emitir juízo de valor | .claude/agents/analise/inventariador-probatica.md | | probatica-pearl | Análise causal (DAG, Bradford Hill, contrafactual) | .claude/agents/analise/probatica-pearl.md | | probatica-haack | Análise foundherentista (warrant, 7 fases) | .claude/agents/analise/probatica-haack.md | | probatica-fbd | Análise probatória penal (Damasceno, 7 movimentos, ADR) | .claude/agents/analise/probatica-fbd.md | | consolidador-probatica | Consolida Pearl + Haack + FBD em síntese unificada | .claude/agents/analise/consolidador-probatica.md | </agents_utilizados>
<regras_uso>
- RETOMADA: antes de despachar qualquer etapa, o gate diz o que já está válido — o que está OK não roda de novo. Primeira rodada e retomada pós-falha são a MESMA operação: rodar o que a varredura listar em PENDENTES.
- CONDUZIR POR CAMINHO: o orquestrador passa paths prontos; o subagente lê as entradas (Read) e GRAVA o documento no arquivo (Write). O documento NUNCA volta inline na resposta.
- RESPOSTA DE UMA LINHA: cada subagente responde apenas " OK | " — quem confere o conteúdo é o script, não o orquestrador lendo.
- VALIDAÇÃO POR SCRIPT: nunca validar lendo o documento; sempre python scripts/verificar_probatica.py "$WORKSPACE" --etapa <nome>.
- Subagentes LEEM o próprio prompt via Read (.claude/agents/analise/...); o orquestrador não copia a capacidade deles — injeta só os caminhos e o lembrete metodológico.
- As análises 2a/2b/2c (pearl, haack, fbd) são INDEPENDENTES entre si: despachar as pendentes em PARALELO (até 3 Tasks opus no MESMO turno). Dependem TODAS do inventário (Etapa 1); a consolidação (Etapa 3) só roda depois delas.
- Subagentes nunca usam TodoWrite.
</regras_uso>
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 · 273 lines · 29 tokens per session scan A d5baefdaabbb
pipeline-probatica is a command published in the GitHub repository georgemarmelstein/superjurista-dev (21 stars, last pushed 1mo ago), licensed MIT. It adds 29 tokens to every session and 5,579 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
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.