planejar-sistema

planejar-sistema is a command for Claude Code from georgemarmelstein/superjurista-dev. It costs 0 tokens per session (6,225 once invoked), scanned A, original, MIT.

Planejador de arquitetura para sistemas agênticos, isto é, sistemas formados por agentes de software que executam tarefas coordenadas. Ele cria um plano com agentes, fluxo de trabalho, contratos e diagrama antes da implementação.

In plain words
What is it for?
Serve para transformar a descrição de um sistema em um blueprint técnico, verificar agentes existentes, dividir o trabalho em etapas e especificar o que cada agente deve fazer.
Why use it?
Ajuda a evitar dependências circulares e decisões de arquitetura tomadas fora de ordem durante a criação do sistema.

Command for Claude Code

Written for Claude Code: ${CLAUDE_PLUGIN_ROOT} variable. Also seen: reads .claude/ paths; names the AskUserQuestion tool.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the superjurista-dev plugin — 11 skills, 22 commands, 7 agents shipped together

Good fit Serve para transformar a descrição de um sistema em um blueprint técnico, verificar agentes existentes, dividir o trabalho em etapas e especificar o que cada agente deve fazer.

Compare 6 commands from other repositories ↓
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add georgemarmelstein/superjurista-dev
Claude Code
/plugin install superjurista-dev

Made for: Claude Code.

Or install superjurista-dev, the plugin that ships this one along with the rest of its 11 skills, 22 commands, 7 agents.

Wrote 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.

agentmods badge for planejar-sistema

README.md
[![agentmods](https://agentmods.dev/badge/commands/georgemarmelstein/superjurista-dev/planejar-sistema/github.svg)](https://agentmods.dev/commands/georgemarmelstein/superjurista-dev/planejar-sistema)
Your own site
<a href="https://agentmods.dev/commands/georgemarmelstein/superjurista-dev/planejar-sistema"><img src="https://agentmods.dev/badge/commands/georgemarmelstein/superjurista-dev/planejar-sistema/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.

agentmods 80×15 button for planejar-sistema

Your own site · 80×15
<a href="https://agentmods.dev/commands/georgemarmelstein/superjurista-dev/planejar-sistema"><img src="https://agentmods.dev/badge/commands/georgemarmelstein/superjurista-dev/planejar-sistema.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 6,225 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00000 $0.06225
Opus 5 $0.00000 $0.03112
Sonnet 5 $0.00000 $0.01245
Haiku 4.5 $0.00000 $0.00622

Measured 10d ago against content hash 594bcdce6c49, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

planejar-sistema 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.

commands/planejar-sistema.md · 676 lines

How it starts

The opening of the file, as written. The whole thing — 676 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Command: planejar-sistema v1.0

Propósito: Planejador de arquitetura para sistemas agênticos - resolve o problema de dependência circular entre criação de agents e orquestradores

Diferencial: Gera blueprint completo ANTES de criar artefatos, permitindo design top-down

Nota: Este é um command de planejamento que executa diretamente (não delega para subagentes). Usa estrutura de fases para organização mas não segue padrão "Orquestrador Cego".


description: Planeja arquitetura de sistemas agênticos - gera blueprint com agents, fluxo e contratos argument-hint: [descrição-do-sistema-a-criar] allowed-tools: Read Write Bash Glob AskUserQuestion TodoWrite

<regras_uso> - SEMPRE validar com usuário antes de prosseguir entre fases - SEMPRE verificar agents existentes via Glob antes de marcar como "a criar" - SEMPRE incluir diagrama ASCII no blueprint - NUNCA criar agents automaticamente - apenas especificar - NUNCA pular a fase de brainstorming </regras_uso>

<se_muitas_etapas> Pipelines ideais têm 3-8 etapas → Sugerir agrupamento ou divisão em sub-pipelines → Validar com usuário antes de prosseguir </se_muitas_etapas>

<se_agent_ambiguo> Capacidade deve ser atômica (uma coisa bem feita) → Sugerir divisão em 2+ agents → Validar com usuário </se_agent_ambiguo>

<se_conflito_specs> Consultar specs originais via Read → ${CLAUDE_PLUGIN_ROOT}/spec/templates/agent.md → ${CLAUDE_PLUGIN_ROOT}/spec/templates/orquestrador.md → Seguir spec, não intuição </se_conflito_specs>

<se_blueprint_rejeitado> Usuário escolheu "Não, ajustar" na validação → Perguntar: "Qual parte precisa ser ajustada?" → Se ajuste em fluxo/etapas → voltar para Fase 1 → Se ajuste em especificação → retrabalhar Fase 2 → Máximo 3 iterações por fase → Se 3x sem aprovação → parar e informar limitação </se_blueprint_rejeitado>

<contratos_dados>

# Fase Entrada Saída Validação
0 Inicialização $ARGUMENTS (descrição) TodoWrite criado Descrição não vazia
1 Descoberta $ARGUMENTS Conceito aprovado Fluxo validado com usuário
2 Design e Geração Conceito Blueprint .md Arquivo salvo com sucesso
</contratos_dados>

Read the full file on GitHub · 676 lines

Changes

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.

  1. 10d ago First seen · 676 lines · 0 tokens per session scan A 594bcdce6c49

Subscribe to this mod's changes

planejar-sistema is a command published in the GitHub repository georgemarmelstein/superjurista-dev (22 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 6,225 tokens. 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.