zihin-criar-agente

zihin-criar-agente is a skill for Claude Code from zihin-ai/zihin-mcp. It costs 55 tokens per session (1,082 once invoked), scanned A, original, MIT.

A Portuguese-language playbook for creating and publishing an AI agent on Zihin, an agent platform. It covers the agent, its persona, its tools, validation, publishing, and distribution channels.

In plain words
What is it for?
Creating an agent, defining its persona, selecting models, validating the setup, publishing it, and connecting it to channels.
Why use it?
It provides an ordered process and lists required settings and expected errors, reducing uncertainty when configuring a Zihin agent.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the zihin plugin — 6 skills, 1 MCP server shipped together

Good fit Creating an agent, defining its persona, selecting models, validating the setup, publishing it, and connecting it to channels.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/zihin-ai/zihin-mcp/zihin-criar-agente
Install

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.

Any agent
npx skills add zihin-ai/zihin-mcp --skill zihin-criar-agente
Clone the repo
git clone --depth 1 https://github.com/zihin-ai/zihin-mcp

Made for: Claude Code.

Or install zihin, the plugin that ships this one along with the rest of its 6 skills, 1 MCP server.

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 zihin-criar-agente

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/zihin-ai/zihin-mcp/zihin-criar-agente"><img src="https://agentmods.dev/badge/skills/zihin-ai/zihin-mcp/zihin-criar-agente.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 55 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,082 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 $0.00055 $0.01082
Opus 5 $0.00028 $0.00541
Sonnet 5 $0.00011 $0.00216
Haiku 4.5 $0.00006 $0.00108

Measured 8d ago against content hash ae570663911b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

zihin-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 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.

plugin/skills/zihin-criar-agente/SKILL.md · 74 lines

How it starts

The opening of the file, as written. The whole thing — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Criar e publicar um agente Zihin

Sequência canônica — não pule a validação nem inverta a ordem:

Passo 1 — Criar o agente

create_agent com name (interno), commercial_name (exibido ao usuário final), bio, type (assistant | chatbot | workflow | classifier | orchestrator — orchestrator invoca outros agentes) e llm_config:

  • model: "provider.modelo" explícito (ex.: openai.gpt-4.1-nano) ou "auto" (roteamento inteligente). Consulte modelos válidos no resource zihin://models — NUNCA invente IDs de modelo. O prefixo de provider é obrigatório: "gpt-4o" é rejeitado, "openai.gpt-4o" é aceito.
  • fallback_chain: até 5 modelos ordenados, sem repetição.
  • max_iterations: teto de iterações do loop por turno (máx. 30 — o runtime clampa aí).
  • Contrato completo em zihin://schemas/llm_config. Ele é campo da tool, não schema_datavalidate_schema_data não aceita esse tipo.
  • Guarde o agent_id retornado.

Tier do plano — onde o erro aparece. Modelo acima do tier não bloqueia create_agent nem update_agent: a chamada passa e volta com warnings explicando. O bloqueio é no publish_agent, com MODEL_TIER_RESTRICTED. Se vier um warnings sobre tier, trate ali — trocar o modelo ou usar "auto" — em vez de seguir e descobrir na publicação. whoami informa o plano do tenant.

Outro erro esperável: PLAN_LIMIT_REACHED (limite de agentes do plano).

Passo 2 — Persona (obrigatória antes de publicar)

create_schema com schema_type: "persona_config". Formato canônico ÚNICO aceito:

{
  "editor_schema": {
    "persona": {
      "role": "Assistente de atendimento",        // obrigatório, min 3 chars
      "objective": "Responder dúvidas de clientes de forma objetiva.", // obrigatório, min 10 chars
      "tone": "profissional",
      "language": "pt-BR",
      "expertise": ["área 1"],
      "constraints": ["NUNCA fazer X", "SEMPRE fazer Y"],
      "personality_traits": ["Objetivo"]
    }
  }
}

O formato legado com instructions na raiz NÃO funciona. Contrato formal: zihin://schemas/persona_config. Pergunte ao usuário sobre objetivo/comportamento antes de criar — não invente persona.

Read the full file on GitHub · 74 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 Changed · +4 lines ae570663911b
  2. 12d ago First seen · 70 lines · 55 tokens per session scan A 7fc1908b7ccc

Subscribe to this mod's changes

zihin-criar-agente is a skill published in the GitHub repository zihin-ai/zihin-mcp (0 stars, last pushed 10d ago), licensed MIT. It adds 55 tokens to every session and 1,082 once invoked, about $0.0003 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 2026-08-31.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens