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.
npx skills add zihin-ai/zihin-mcp --skill zihin-governanca-e-operacaogit clone --depth 1 https://github.com/zihin-ai/zihin-mcpWrote 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/skills/zihin-ai/zihin-mcp/zihin-governanca-e-operacao)<a href="https://agentmods.dev/skills/zihin-ai/zihin-mcp/zihin-governanca-e-operacao"><img src="https://agentmods.dev/badge/skills/zihin-ai/zihin-mcp/zihin-governanca-e-operacao/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/skills/zihin-ai/zihin-mcp/zihin-governanca-e-operacao"><img src="https://agentmods.dev/badge/skills/zihin-ai/zihin-mcp/zihin-governanca-e-operacao.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 | $0.00080 | $0.01460 |
| Opus 5 | $0.00040 | $0.00730 |
| Sonnet 5 | $0.00016 | $0.00292 |
| Haiku 4.5 | $0.00008 | $0.00146 |
Grade A, and why
zihin-governanca-e-operacao 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.
How it starts
The opening of the file, as written. The whole thing — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Governança e operação
Teto de gasto por agente (budget)
Budget ≠ quota: budget é teto de custo em USD por agente e conta TODAS as chamadas LLM, BYOK incluído; quota é a franquia de tokens do plano (BYOK não consome).
get_agent_budget— saldo do ciclo + teto efetivo (unlimited: true= sem teto). O teto pode ser excedido em até 1 chamada em voo (hard-stop age antes do turno seguinte).list_agent_budgets— visão consolidada de todos os agentes (1 chamada, sem N+1).set_agent_budget— define/eleva/remove (limit_usd: null= ilimitado). É o laço de recuperação: agente parado por budget volta a rodar no próximo turno após elevar o teto.- Budget é POR AGENTE, não consolida subagentes: orchestrator com teto + subagentes sem teto = fan-out escapa. Para conter custo de árvore, aplique teto em cada agente.
CSPs — políticas de segurança contextual
create_csp / update_csp / toggle_csp / get_effective_csps (merge efetivo por agente). Contrato: zihin://schemas/csp_config (entidade — envie só name/policy_type/scope/rules/...).
- Escopos hierárquicos:
tenant>team>agent>user(herança de cima pra baixo;scope_target_idobrigatório fora de tenant). - ⚠️ Campo fora do contrato é aceito em silêncio e fica inerte — o schema permite propriedades extras, então errar o nome não dá erro, dá uma política que não faz nada. Confira em
zihin://schemas/csp_config, em$defs.{tipo}Rules. - ⚠️
update_cspsubstituirulesinteiro, não mescla: reenvie os campos que quer manter. - Tipos e rules, com os nomes reais:
schedule—allowed_hours: {start, end},allowed_days,blocked_dates,timezone. Aplicado: fora da janela o turno é recusado na admissão, antes de chamar o modelo. Avaliado no timezone declarado (sem ele, UTC).behavior—must_not_tools,max_iterations,max_tool_calls,max_tokens_per_request,require_approval_for,approval_policy_id,tone,language,must_do,must_not.data—sensitive_fields,never_expose,restricted_entities,restriction_message.custom— shape livre, vira bloco de política no prompt sem interpretação do runtime.origin— NÃO é aplicado em runtime (nenhum entrypoint propaga IP/origem do cliente; countries/vpn/tor exigem provedor de geo que não integramos). É aceito e armazenado, mas não bloqueia: não use como controle de segurança.
- Superfície de tools:
must_not_toolsé o único jeito de tirar uma tool do agente sem desligar o recurso no tenant. Vale nos dois runtimes, inclusive no resume de HITL. Verzihin://skills/tools-de-agente. - Multi-agente (behavior):
max_agent_depth(0-5, default 2),allowed_invoke_agents(whitelist de UUIDs; vazio = todos),child_timeout_ms(5000-300000).
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.
- 8d ago Changed · +8 lines 77eb40c18fc2
- 12d ago First seen · 51 lines · 80 tokens per session scan A 4bcfc09ae830
zihin-governanca-e-operacao is a skill published in the GitHub repository zihin-ai/zihin-mcp (0 stars, last pushed 10d ago), licensed MIT. It adds 80 tokens to every session and 1,460 once invoked, about $0.0004 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.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…
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…
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.
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…
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…