imperio-infra

imperio-infra is a skill for Claude Code from tatagoncalvesof/imperatriz-toolkit. It costs 106 tokens per session (9,339 once invoked), scanned A, original, MIT.

A skill for preparing AI agents to run reliably in production. It covers commands and hooks, MCP connections, repeat-safe operations, schedules and failure windows, token costs, and monitoring.

In plain words
What is it for?
Generating production configurations for agent safeguards, service connections, repeat-safe execution, time controls, cost tracking and observability.
Why use it?
An agent that works once may fail when repeated, run at the wrong time, spend too much, or provide too little visibility into what happened.

Skill for Claude Code

Written for Claude Code: PreToolUse hook event. Also seen: model in frontmatter; positional $N argument.

Good fit Generating production configurations for agent safeguards, service connections, repeat-safe execution, time controls, cost tracking and observability.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/tatagoncalvesof/imperatriz-toolkit/imperio-infra
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 tatagoncalvesof/imperatriz-toolkit --skill imperio-infra
Clone the repo
git clone --depth 1 https://github.com/tatagoncalvesof/imperatriz-toolkit

Made for: Claude Code.

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 imperio-infra

README.md
[![agentmods](https://agentmods.dev/badge/skills/tatagoncalvesof/imperatriz-toolkit/imperio-infra/github.svg)](https://agentmods.dev/skills/tatagoncalvesof/imperatriz-toolkit/imperio-infra)
Your own site
<a href="https://agentmods.dev/skills/tatagoncalvesof/imperatriz-toolkit/imperio-infra"><img src="https://agentmods.dev/badge/skills/tatagoncalvesof/imperatriz-toolkit/imperio-infra/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 imperio-infra

Your own site · 80×15
<a href="https://agentmods.dev/skills/tatagoncalvesof/imperatriz-toolkit/imperio-infra"><img src="https://agentmods.dev/badge/skills/tatagoncalvesof/imperatriz-toolkit/imperio-infra.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 106 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 9,339 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 $0.00106 $0.09339
Opus 5 $0.00053 $0.04670
Sonnet 5 $0.00021 $0.01868
Haiku 4.5 $0.00011 $0.00934

Measured 11d ago against content hash 3d3ff6cf159e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

imperio-infra 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 11d 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.

skills/imperio-infra/SKILL.md · 874 lines

How it starts

The opening of the file, as written. The whole thing — 874 lines — stays where its author put it; the contents beside it link to each section on GitHub.

IMPERIO INFRA — Infraestrutura Operacional para Agentes IA em Producao

"Qualquer amador faz um agente que funciona 1 vez. Profissional faz agente que roda 1000 vezes sem quebrar, sem cobrar dobrado, sem mandar mensagem meia-noite pro cliente." — Tata Goncalves

IDENTIDADE

Voce e o Engenheiro de Infraestrutura do Imperio IA — o especialista que transforma agentes "de brinquedo" em sistemas de producao robustos. Voce aplica os 6 frameworks operacionais da Apostila Imperio IA Agentes (por Tata Goncalves) para blindar cada agente antes de soltar no mundo real.

Voce fala portugues brasileiro, com o tom da Tata: direto, confiante, acolhedor e empoderador. Usa expressoes como "bora blindar isso", "agora sim, profissional", "confia no processo", "vamo deixar isso a prova de bala".

Voce NAO da config generica. Voce ADAPTA tudo ao contexto real do usuario: os agentes que ele tem, os servicos que usa, o volume de clientes, o orcamento disponivel. Se o cara tem 3 agentes pequenos, voce nao monta infra pra 50. Se tem operacao high-ticket com cliente exigente, voce eh mais rigoroso nos hooks e janelas de horario.

REGRA DE OURO

Agente sem infraestrutura = bomba-relogio. Todo agente que interage com o mundo real (manda mensagem, cria registro, cobra) PRECISA dos 6 frameworks. Sem isso, voce vai:

  • Mandar mensagem duplicada pro cliente (sem UNICO)
  • Mandar WhatsApp 3h da manha (sem RELOGIO)
  • Gastar R$500 num dia sem perceber (sem MOEDA)
  • Nao saber por que o lead sumiu (sem OLHAR)
  • Quebrar tudo quando o Stripe cai (sem GUARDIAO)
  • Ficar preso no manual quando podia estar automatizado (sem PONTE)

OS 6 FRAMEWORKS

Framework 1: GUARDIAO — Commands + Hooks

O que eh: Sistema de velocidade (commands) + seguranca (hooks) para operacoes diarias.

COMMANDS = Atalhos que disparam acoes complexas com um unico comando. Em vez de 5 cliques e 3 copiar-colar, voce digita /novo-lead e tudo acontece.

HOOKS = Validadores automaticos que rodam ANTES e DEPOIS de cada acao. Pre-tool hooks validam antes de executar. Post-tool hooks logam decisoes e alertam erros.

Read the full file on GitHub · 874 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. 11d ago First seen · 874 lines · 106 tokens per session scan A 3d3ff6cf159e

Subscribe to this mod's changes

imperio-infra is a skill published in the GitHub repository tatagoncalvesof/imperatriz-toolkit (2 stars, last pushed 3mo ago), licensed MIT. It adds 106 tokens to every session and 9,339 once invoked, about $0.0005 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

codex-setup

Initialize sd0x-dev-flow infrastructure for Codex CLI and other non-Claude agents. Generates AGENTS.md, installs the commit-msg hook, copies runner scripts. The pre-push gate is opt-in via --with-push-gate. Use when setting up a new project or after updating skills.

sd0xdev/sd0x-harness · 65 tokens

smart-rebase

Smart partial rebase for squash-merge repositories. Auto-detect which commits to keep/drop when base branch was squash-merged into target. Use when: user says 'rebase', 'partial rebase', 'base already merged', 'smart rebase', or /smart-rebase. Not for: simple git rebase (the developer runs it — Claude never executes…

sd0xdev/sd0x-harness · 131 tokens

test-review

Test coverage review via Codex exec. Use when: reviewing test sufficiency, identifying coverage gaps, test quality audit. Not for: generating tests (use codex-test-gen), code review (use codex-code-review). Output: coverage analysis + gap report.

sd0xdev/sd0x-harness · 56 tokens

debug

Interactive debugging workflow with hypothesis-driven probe loop. Use when: unknown bugs, script errors, silent failures, troubleshooting. Not for: known bugs (use bug-fix), GitHub issue analysis (use issue-analyze), code understanding (use code-explore). Output: debug report with probe journal + root cause + fix.

sd0xdev/sd0x-harness · 67 tokens

runbook

Generate and update feature release runbooks from existing docs and codebase. Use when: creating operational runbook, release handbook, deployment checklist, pre-release preparation. Not for: incident response (v2), code review (use codex-code-review), architecture design (use architecture).

sd0xdev/sd0x-harness · 59 tokens

feature-dev

Feature development workflow. Use when: implementing features, writing code, running dev loop. Not for: understanding code (use code-explore), reviewing code (use codex-code-review). Output: implemented feature + tests + review gate.

sd0xdev/sd0x-harness · 50 tokens