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 aprovar-postgit 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/aprovar-post)<a href="https://agentmods.dev/skills/felipenalves/invos/aprovar-post"><img src="https://agentmods.dev/badge/skills/felipenalves/invos/aprovar-post.svg" alt="Measured on agentmods" 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 | $0.00117 | $0.01475 |
| Opus 5 | $0.00059 | $0.00737 |
| Sonnet 5 | $0.00023 | $0.00295 |
| Haiku 4.5 | $0.00012 | $0.00147 |
Grade A, and why
aprovar-post scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 7d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -sf -o /dev/null -w "%{http_code}" "$SITE_URL/blog/$slug/" How it starts
The opening of the file, as written. The whole thing — 152 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/aprovar-post — Pipeline de aprovação e publicação automática
Faz a ponte entre o conteúdo aprovado (blog + carrossel + legendas, criado por /publicar-tema)
e a publicação real no feed (site + Instagram + Facebook).
Quando NÃO usar
- Conteúdo ainda não foi criado → use
/publicar-temaprimeiro - Usuário ainda está revisando → não rodar até ele dizer "aprovado" / "pode postar"
- Site não está deployado / Meta API não configurada → seguir setup abaixo
Pré-requisitos (uma vez só)
.envna raiz com:META_PAGE_ACCESS_TOKEN— token de longa duração da Página FBMETA_PAGE_ID— ID da Página FBMETA_IG_USER_ID— ID da conta Insta BusinessSITE_URL— ex:https://exemplo.com.br
- Site com deploy automático a partir do
maindo GitHub (Netlify, Vercel, etc.) - Conta Insta Business conectada à Página FB
- Página FB com permissões corretas no Meta App
- Scripts
scripts/postar-instagram.jsescripts/postar-facebook.jsconfigurados
Se algo disso faltar: parar e apontar pro guia de setup (criar marketing/automacao-meta-setup.md se ainda não existir).
Argumento
/aprovar-post <slug> — onde <slug> é o nome do arquivo do blog sem .md.
Exemplo: /aprovar-post como-conservar-produto
Se o usuário não passou slug, listar os blogs em draft (arquivos com draft: true) e perguntar qual.
Workflow
Passo 1 — Localizar arquivos
- Blog:
site/.../blog/<slug>.md(caminho depende do stack — Astro, Hugo, etc.) - Carrossel: procurar
marketing/conteudo/<slug>-*(a pasta tem sufixo de data) - Validar que existem PNGs em
<pasta-carrossel>/instagram/slide-XX.png(2 a 10) - Validar que existem
legenda.mdelegenda-linkedin.md
Se faltar qualquer um, parar e relatar.
Passo 2 — Mostrar resumo + pedir confirmação final
Mostrar pro usuário:
- Título do blog
- Quantos slides do carrossel
- Primeiras 200 chars da legenda
- URL final que vai ser publicada
Perguntar: "Confirma publicação? (sim/não)". Só seguir se ele disser sim.
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.
- 7d ago First seen · 152 lines · 117 tokens per session scan A 78507eae0578
aprovar-post is a skill published in the GitHub repository felipenalves/InvOS (5 stars, last pushed 4d ago), licensed MIT. It adds 117 tokens to every session and 1,475 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). 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.