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 felipenalves/InvOS --skill publicar-temagit clone --depth 1 https://github.com/felipenalves/InvOSWrote 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/felipenalves/invos/publicar-tema)<a href="https://agentmods.dev/skills/felipenalves/invos/publicar-tema"><img src="https://agentmods.dev/badge/skills/felipenalves/invos/publicar-tema/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/felipenalves/invos/publicar-tema"><img src="https://agentmods.dev/badge/skills/felipenalves/invos/publicar-tema.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 | $0.00128 | $0.01765 |
| Opus 5 | $0.00064 | $0.00882 |
| Sonnet 5 | $0.00026 | $0.00353 |
| Haiku 4.5 | $0.00013 | $0.00177 |
Grade A, and why
publicar-tema 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 9d 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 — 155 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/publicar-tema — Pipeline de conteúdo SEO + redes sociais
Skill orquestradora. Pega um tema → entrega artigo no blog + carrossel + 3 legendas (Insta, FB, LinkedIn), tudo conectado.
Dependências
- Estratégia de conteúdo:
marketing/seo/05-estrategia-conteudo.md(lista mestra de temas, criada pelo/seo) - Outras pesquisas SEO:
marketing/seo/01-pesquisa-demanda.md,02-analise-concorrencia.md,08-geo-otimizacao-ia.md - Skill carrossel:
.agents/skills/carrossel/SKILL.md— usar pra fase do carrossel - Site (blog):
site/— destino dos artigos. Estrutura comum: Astro emsite/astro-site/src/content/blog/, ou WordPress, ou outro. Se ainda não tiver site, perguntar antes - Tom de voz:
_memoria/preferencias.md - Contexto:
_memoria/empresa.md,marca/design-guide.md
Workflow
Passo 0 — Escolher o tema
Se o usuário passou um tema explícito → usar.
Se não passou nada → ler marketing/seo/05-estrategia-conteudo.md, listar os artigos satélite + a página pilar, e perguntar:
"Qual tema da estratégia? (lista de opções)"
Marcar mentalmente quais já viraram blog (checar pasta do blog) pra não duplicar.
Passo 1 — Pesquisa rápida
Antes de escrever, ler o que tem nas pesquisas SEO sobre esse tema:
- Keyword principal e variações (
01-pesquisa-demanda.md) - Como concorrentes tratam (
02-analise-concorrencia.md) — pra fugir do óbvio - Ângulo GEO se aplicável (
08-geo-otimizacao-ia.md) — perguntas que IAs respondem
Passo 2 — Escrever o blog post
Destino: depende do stack do site. Padrões comuns:
- Astro:
site/astro-site/src/content/blog/<slug>.md - WordPress: gerar markdown que o usuário cola no editor
- Outro: confirmar com o usuário
Slug: kebab-case curto, sem stopwords. Ex: "Como conservar carne salgada no restaurante" → conservar-carne-salgada.
Frontmatter (se o stack usa markdown com frontmatter):
---
title: "Título atrativo, próximo da keyword"
description: "Meta description 150-160 caracteres, com keyword e benefício pro leitor"
publishedAt: YYYY-MM-DD
author: "<nome configurado em _memoria/empresa.md>"
keywords:
- keyword principal
- variação 1
- variação 2
draft: true
---
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.
- 9d ago First seen · 155 lines · 128 tokens per session scan A fd2b1085c584
publicar-tema is a skill published in the GitHub repository felipenalves/InvOS (5 stars, last pushed 6d ago), licensed MIT. It adds 128 tokens to every session and 1,765 once invoked, about $0.0006 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
hindsight-architect
Expert memory architect. Understands your application, identifies where memory adds value, and produces an implementation plan with bank config, tag schema, and code.
create-agent
Create a new Hindsight-powered subagent with long-term memory. Use when the user wants a specialized agent that learns and remembers across sessions.
hindsight-docs
Complete Hindsight documentation for AI agents. Use this to learn about Hindsight architecture, APIs, configuration, and best practices.
hindsight-local
Store user preferences, learnings from tasks, and procedure outcomes. Use to remember what works and recall context before new tasks. (user).
hindsight-memory
Long-term memory for the agent via Hindsight. Use to recall relevant past context before answering, retain durable facts as you learn them, and reflect over accumulated memory for the "why" behind a decision. Load whenever continuity across sessions matters — the user refers to earlier work, states a lasting…
hindsight-recall
Search long-term memory for relevant context from past coding sessions using Hindsight MCP tools.