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 tatagoncalvesof/imperatriz-toolkit --skill maestro-de-conteudogit clone --depth 1 https://github.com/tatagoncalvesof/imperatriz-toolkitWrote 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/tatagoncalvesof/imperatriz-toolkit/maestro-de-conteudo)<a href="https://agentmods.dev/skills/tatagoncalvesof/imperatriz-toolkit/maestro-de-conteudo"><img src="https://agentmods.dev/badge/skills/tatagoncalvesof/imperatriz-toolkit/maestro-de-conteudo/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/tatagoncalvesof/imperatriz-toolkit/maestro-de-conteudo"><img src="https://agentmods.dev/badge/skills/tatagoncalvesof/imperatriz-toolkit/maestro-de-conteudo.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 | $0.00413 | $0.03131 |
| Opus 5 | $0.00206 | $0.01566 |
| Sonnet 5 | $0.00083 | $0.00626 |
| Haiku 4.5 | $0.00041 | $0.00313 |
Grade A, and why
maestro-de-conteudo 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 12d 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 — 216 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Maestro de Conteúdo — Orquestrador Único da Travessia
Uma skill. Cinco fases. Do zero ao calendário de 30 dias publicável.
A mentorada roda APENAS essa skill. Não precisa decorar 6 nomes, não precisa entender qual roda antes de qual, não precisa saber o que é "Pilar Editorial" ou "Porta da Travessia". O Maestro guia.
Skill orquestradora de fundações editoriais — desenhada pra resolver UM problema específico: a mentorada que abre o Claude Code pela primeira vez precisa de UM caminho, não de uma planilha de skills.
O que ela faz: chama 5 skills filhas em sequência fixa, com pausa de validação entre cada fase, passando o contexto acumulado. No fim, a mentorada tem o pacote completo pra começar a publicar.
O que ela NÃO faz: produz peças de conteúdo. Produção é trabalho das skills filhas (carrossel, stories, LinkedIn, e-mail) que a mentorada roda DEPOIS, com a régua editorial e o calendário em mãos.
Filosofia central
Quatro princípios não negociáveis:
- Mentorada NÃO escolhe ordem. A ordem é fixa porque cada fase alimenta a próxima. Posicionamento alimenta voz alimenta porta alimenta linha alimenta calendário. Pular ou inverter quebra o resultado.
- Mentorada SEMPRE começa do zero. Não tenta ler arquivos antigos, não pergunta "você já tem X capturado?". Trata cada execução como primeira vez. Mais previsível, menos ponto de falha.
- Pausa entre fases é regra. Mentorada cansa. A skill PERGUNTA se quer continuar agora ou voltar depois. Sessão de 2h30min é dura — em 5 sessões de 30-45min ela executa melhor.
- Maestro não escreve copy. Despacha pras skills filhas, recebe output, valida que veio completo, passa pro próximo. Nunca duplica o trabalho de uma filha.
As 5 fases (sequência fixa)
FASE 1 — Posicionamento (~30min)
↓ despacha pra /posicionamento-estrategico
↓ output: 01-posicionamento.json
↓ pausa de validação
FASE 2 — Voz de Marca (~45min)
↓ despacha pra /voz-de-marca-builder --entrevista
↓ output: 03-voz-de-marca.json
↓ pausa de validação
FASE 3 — Porta da Travessia (~10min)
↓ despacha pra /dossie-mentorada (apenas pra capturar Porta + nível)
↓ output: 02-porta-atual.json
↓ pausa de validação
FASE 4 — Linha Editorial (~45min)
↓ despacha pra /linha-editorial-imperatriz --gerar
↓ pré-requisitos JÁ atendidos pelas fases 1-3
↓ output: 04-linha-editorial.json + manifesto.md + dashboard.html
↓ pausa de validação
FASE 5 — Calendário 30 Dias (~30min)
↓ despacha pra /calendario-imperatriz --gerar
↓ pré-requisito JÁ atendido pela fase 4
↓ output: calendário-30-dias.md + dashboard interativo
↓ ENTREGA FINAL
What ships with it
11 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- .gitignore 155 B
- LICENSE 1.1 KB
- README.md 1.8 KB
- references/01-FASE-POSICIONAMENTO.md 3.0 KB
- references/02-FASE-VOZ-DE-MARCA.md 2.7 KB
- references/03-FASE-PORTA-DA-TRAVESSIA.md 3.8 KB
- references/04-FASE-LINHA-EDITORIAL.md 3.3 KB
- references/05-FASE-CALENDARIO.md 2.5 KB
- references/06-PAUSAS-E-VALIDACOES.md 3.9 KB
- references/07-OUTPUT-FINAL.md 5.2 KB
- references/08-ANTI-PADROES.md 4.4 KB
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.
- 12d ago First seen · 216 lines · 413 tokens per session scan A 3f01792aa1ad
maestro-de-conteudo is a skill published in the GitHub repository tatagoncalvesof/imperatriz-toolkit (2 stars, last pushed 3mo ago), licensed MIT. It adds 413 tokens to every session and 3,131 once invoked, about $0.0021 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
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.
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…
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.
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.
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).
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.