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/analisar-lista)<a href="https://agentmods.dev/commands/georgemarmelstein/superjurista-dev/analisar-lista"><img src="https://agentmods.dev/badge/commands/georgemarmelstein/superjurista-dev/analisar-lista/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/analisar-lista"><img src="https://agentmods.dev/badge/commands/georgemarmelstein/superjurista-dev/analisar-lista.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 | $0.00015 | $0.08783 |
| Opus 5.5 | $0.00006 | $0.03513 |
| Sonnet 5.5 | $0.00003 | $0.01757 |
| Haiku 4.5 | $0.00002 | $0.00878 |
Grade A, and why
analisar-lista 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 1mo 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 — 839 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Orquestrador: Analisar Lista de Julgamento v2.0
Filosofia: Pipeline modular com injeção de contexto para análise completa de listas de julgamento.
Modelo obrigatório: Opus para todas as etapas (análise jurídica complexa)
<tools_subagentes> | Etapa | Tools Necessárias | |-------|-------------------| | 01-extracao | Read Write | | 02-consistencia-interna | Read Write | | 03-precedentes-vinculantes | Read Write mcp__bnp-api__buscar_precedentes | | 04-jurisprudencia-trf5 | Read Write mcp__julia-trf5__buscar_julia mcp__cjf-jurisprudencia__buscar_jurisprudencia_cjf | | 05-jurisprudencia-turma | Read Write mcp__julia-trf5__buscar_julia | | 06-sensibilidade | Read Write | | 07-consolidacao-processo | Read Write | | 08-consistencia-cruzada | Read Write | | 09-relatorio-final | Read Write | </tools_subagentes>
<tools_proibidas_subagentes> | Tool | Razão da Proibição | |------|-------------------| | TodoWrite | Exclusivo do orquestrador - causa race conditions | | Task | Subagentes não disparam outros subagentes | | AskUserQuestion | Apenas orquestrador interage com usuário | </tools_proibidas_subagentes>
<regras_uso> - Subagentes LEEM prompts diretamente via Read tool - Orquestrador NÃO executa tarefas dos subagentes - Cada subagente tem contexto ISOLADO - Etapas 02-06 podem rodar em PARALELO para cada processo - Etapa 08 só roda após TODOS os processos consolidados </regras_uso>
<json_invalido> ERRO: JSON de saída inválido. → Regenerar com sufixo de correção JSON → Se falhar 2x → PARAR e informar usuário </json_invalido>
<extracao_vazia> ERRO: Nenhum processo extraído. → Verificar se arquivo .docx foi lido corretamente → Perguntar ao usuário se formato está correto </extracao_vazia>
<turma_nao_identificada> AVISO: Turma não identificada na extração. → Perguntar ao usuário qual é a turma → Continuar com valor informado </turma_nao_identificada>
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.
- 1mo ago First seen · 839 lines · 15 tokens per session scan A 5dcf72a7a9a5
analisar-lista is a command published in the GitHub repository georgemarmelstein/superjurista-dev (25 stars, last pushed 3mo ago), licensed MIT. It adds 15 tokens to every session and 8,783 once invoked, about $0.0001 per session on Opus 5.5. 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.
review-policy
Review a policy document for structure, coverage, and language quality.
compliance-audit
Full regulatory compliance audit for GDPR, HIPAA, SOC2, PCI-DSS, ISO 27001, and other frameworks with gap analysis, remediation planning, and evidence collection.
app-store-audit
Run an enterprise pre submission compliance audit on an iOS or Android app against Apple App Store and Google Play rejection rules. Pass a project path or run from the project root.
rgpd
Questões de RGPD e violação de dados — referência, playbook e checklist. GDPR and data-breach matters — reference, playbook and checklist.