criar-team

criar-team is a command for Claude Code from georgemarmelstein/superjurista-dev. It costs 29 tokens per session (2,129 once invoked), scanned B, original, MIT.

A command for creating an Agent Team, meaning several coding agents working on one task. It offers parallel subagents or an experimental mode where teammates exchange messages and debate.

In plain words
What is it for?
Use it to choose and create a parallel subagent setup or an interactive Agent Team, including enabling the experimental feature when needed.
Why use it?
It makes the trade-off between isolated parallel work and interactive agent discussion explicit. It also checks whether the experimental team feature is enabled.

Command for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: reads .claude/ paths; mentions subagents; 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 Use it to choose and create a parallel subagent setup or an interactive Agent Team, including enabling the experimental feature when needed.

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-team

README.md
[![agentmods](https://agentmods.dev/badge/commands/georgemarmelstein/superjurista-dev/criar-team.svg)](https://agentmods.dev/commands/georgemarmelstein/superjurista-dev/criar-team)
Your own site
<a href="https://agentmods.dev/commands/georgemarmelstein/superjurista-dev/criar-team"><img src="https://agentmods.dev/badge/commands/georgemarmelstein/superjurista-dev/criar-team.svg" alt="Measured on agentmods" height="20"></a>
Per session 29 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,129 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. 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 $0.00029 $0.02129
Opus 5 $0.00015 $0.01064
Sonnet 5 $0.00006 $0.00426
Haiku 4.5 $0.00003 $0.00213

Measured 8d ago against content hash 6b9e341d5b6f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade B, and why

criar-team scanned grade B with 1 finding 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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

grep -q "CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS" ~/.claude/settings.json && echo "HABILITADO" || echo "DESABILITADO"
commands/criar-team.md · 258 lines

How it starts

The opening of the file, as written. The whole thing — 258 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Comando: Criar Agent Team

```bash
grep -q "CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS" ~/.claude/settings.json && echo "HABILITADO" || echo "DESABILITADO"
```

Registrar resultado para informar opções disponíveis.
**Pergunta:** "Qual abordagem de Agent Team você quer usar?"

**Opções:**

Se feature HABILITADA:
1. **v2.10 Agent Teams (Debate Real)** - Teammates debatem via mensagens, desafiam uns aos outros
2. **v2.8 Subagents (Paralelo)** - Executam isolados, consolidador sintetiza depois

Se feature DESABILITADA:
1. **v2.8 Subagents (Paralelo)** - Única opção disponível
2. **Habilitar v2.10** - Configurar feature e reiniciar

Explicar diferenças:
```
┌─────────────────────────────────────────────────────────────┐
│ v2.8 SUBAGENTS          │ v2.10 AGENT TEAMS                 │
├─────────────────────────┼───────────────────────────────────┤
│ Paralelo isolado        │ Debate via mensagens              │
│ Comunicação: arquivos   │ Comunicação: mensagens diretas    │
│ Sem debate              │ Teammates desafiam uns aos outros │
│ Funciona hoje           │ Requer feature experimental       │
│ Menos tokens            │ Mais tokens                       │
└─────────────────────────┴───────────────────────────────────┘
```
1. Ler SPEC:
   ```
   Read: ${CLAUDE_PLUGIN_ROOT}/spec/referencias/team-pattern.md
   ```

2. Fazer perguntas de descoberta:
   - Objetivo do team
   - Quantos teammates (2-4)
   - Agents existentes para reutilizar
   - Agent downstream
   - Orquestrador de integração

3. Propor arquitetura

4. Gerar código:
   - Teammates (agents que escrevem em arquivos separados)
   - Consolidador (lê arquivos, sintetiza)
   - Orquestrador (dispara Tasks em paralelo)
1. Ler SPEC:
   ```
   Read: ${CLAUDE_PLUGIN_ROOT}/spec/referencias/agent-teams-v210.md
   ```

2. Fazer perguntas de descoberta:
   - Objetivo do team (o que querem resolver/criar)
   - Quantos teammates (2-5)
   - Perspectivas distintas de cada um
   - Tipo de debate (científico, criativo, revisão)
   - Documento de convergência

3. Gerar PROMPT para o Lead:

   O output não é código, é um PROMPT otimizado para o usuário
   usar em uma nova sessão do Claude Code:

   ```markdown
   # Prompt para Agent Team: [nome]

   ## Pré-requisitos
   - Feature habilitada: ✅
   - Reiniciar Claude Code antes de usar

   ## Prompt para o Lead

   ```
   Crie um agent team com [N] teammates para [objetivo].

   CONTEXTO:
   [contexto relevante]

   TEAMMATES:
   1. [NOME-1]: [papel]
      - Avalia pelo critério: "[critério]"
      - Foco em [área]

   2. [NOME-2]: [papel]
      - Avalia pelo critério: "[critério]"
      - Foco em [área]

   [...]

   PROCESSO:
   1. Cada teammate produz sua análise/proposta
   2. Cada um LÊ os outputs dos outros e CRITICA
   3. Debate: desafiem as propostas, apontem falhas
   4. Convergência: o que sobrevive ao escrutínio?
   5. Lead sintetiza a recomendação final

   O objetivo é que o DEBATE entre perspectivas diferentes
   produza um resultado mais robusto do que cada um sozinho.
   ```

   ## Como Usar
   1. Abra nova sessão do Claude Code
   2. Cole o prompt acima
   3. Observe o debate acontecer
   4. Interaja com teammates se necessário (Shift+Up/Down)
   ```

Read the full file on GitHub · 258 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. 8d ago First seen · 258 lines · 29 tokens per session scan B 6b9e341d5b6f

Subscribe to this mod's changes

criar-team 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 2,129 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.