criar-agente

criar-agente is a command for Claude Code from georgemarmelstein/superjurista-dev. It costs 35 tokens per session (6,301 once invoked), scanned A, original, MIT.

A guided command for creating modular coding agents from an initial idea. It refines the idea through brainstorming, shows a preview, writes the agent specification to a file, and validates the result.

In plain words
What is it for?
Use it to design modular agents, clarify their capabilities, generate their specification files, preview changes, and rework designs that fail validation.
Why use it?
It turns a rough concept into a checked agent definition while preserving required design and output rules. This reduces omissions and makes the agent easier to reuse.

Command for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: reads .claude/ paths; names the TodoWrite 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 Use it to design modular agents, clarify their capabilities, generate their specification files, preview changes, and rework designs that fail validation.

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 criar-agente

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

Your own site · 80×15
<a href="https://agentmods.dev/commands/georgemarmelstein/superjurista-dev/criar-agente"><img src="https://agentmods.dev/badge/commands/georgemarmelstein/superjurista-dev/criar-agente.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 35 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 6,301 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 $0.00035 $0.06301
Opus 5 $0.00017 $0.03150
Sonnet 5 $0.00007 $0.01260
Haiku 4.5 $0.00003 $0.00630

Measured 10d ago against content hash 7740473f9b42, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

criar-agente 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/criar-agente.md · 689 lines

How it starts

The opening of the file, as written. The whole thing — 689 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Orquestrador: criar-agente v2.1

Propósito: Meta-orquestrador que cria agentes modulares.

Diferencial: Refina a ideia por brainstorming e garante o contrato de saída v3.0 — o agente GRAVA o próprio documento (Write) e responde 1 linha; os <sinalizadores> são âncoras que o gate do pipeline confere NO ARQUIVO, não texto ecoado inline. A capacidade atômica e a modularidade (o contrato por tipo) permanecem intactas.

<regras_uso> - Skill brainstorming é OBRIGATÓRIO na Fase 1 - AskUserQuestion para decisões que impactam o design - Nunca pular a validação final - Mostrar preview antes de salvar </regras_uso>

<se_score_baixo> Mostrar itens faltantes e corrigir automaticamente → Regenerar e revalidar → Se falhar 2x → pedir ajuda ao usuário </se_score_baixo>

<se_conflito_specs> Consultar SPECs originais via Read → Seguir spec, não intuição </se_conflito_specs>

<contratos_dados>

# Fase Entrada Saída Validação
0 Inicialização $ARGUMENTS (ideia bruta) TodoWrite criado Variáveis definidas
1 Brainstorming $ARGUMENTS Conceito refinado Capacidade atômica clara
2 Especificação Conceito refinado Estrutura completa Todos campos preenchidos
3 Geração Estrutura completa Agent .md Score >= 102/128 (80%)
</contratos_dados>

<rastreamento_progresso> <formato_todowrite> javascript TodoWrite([ {content: "Fase 1 - Brainstorming", status: "pending", activeForm: "Refinando ideias"}, {content: "Fase 2 - Especificação", status: "pending", activeForm: "Definindo estrutura"}, {content: "Fase 3 - Geração e Validação", status: "pending", activeForm: "Criando agent"}, ]) </formato_todowrite> </rastreamento_progresso>

<sinalizadores_formato>

Fase Sinalização de Conclusão
0 TodoWrite criado com todas as fases
1 Conceito aprovado pelo usuário
2 Estrutura completa validada
3 Agent salvo com score >= 102
</sinalizadores_formato>

<sufixos_correcao>

Read the full file on GitHub · 689 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 · 689 lines · 35 tokens per session scan A 7740473f9b42

Subscribe to this mod's changes

criar-agente is a command published in the GitHub repository georgemarmelstein/superjurista-dev (22 stars, last pushed 1mo ago), licensed MIT. It adds 35 tokens to every session and 6,301 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.