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 anuncio-googlegit 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/anuncio-google)<a href="https://agentmods.dev/skills/felipenalves/invos/anuncio-google"><img src="https://agentmods.dev/badge/skills/felipenalves/invos/anuncio-google/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/anuncio-google"><img src="https://agentmods.dev/badge/skills/felipenalves/invos/anuncio-google.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 | $0.00114 | $0.01801 |
| Opus 5 | $0.00057 | $0.00901 |
| Sonnet 5 | $0.00023 | $0.00360 |
| Haiku 4.5 | $0.00011 | $0.00180 |
Grade A, and why
anuncio-google scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 175 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/anuncio-google — Estrutura de campanha Google Ads
Skill que monta a campanha inteira em CSV pronto pra importar no Google Ads Editor. Sai do briefing direto pro CSV — sem montar grupo por grupo na mão na interface do Google.
Dependências
- Contexto do negócio:
_memoria/empresa.md(produto/serviço, público, região, diferenciais) - Tom de voz:
_memoria/preferencias.md - Pesquisa SEO (se existir):
marketing/seo/01-pesquisa-demanda.md,06-google-ads.md— usar como insumo - Outputs vão em:
marketing/campanhas/google-ads-<YYYY-MM-DD>/
Workflow
Passo 1 — Briefing
Se o usuário não passou briefing, perguntar:
- Produto/serviço a anunciar? (1-3 linhas)
- Quem é o público? (perfil, dor que resolve)
- Região: raio em km a partir de qual cidade?
- Orçamento diário? (R$/dia)
- Objetivo: ligações / WhatsApp / formulário / visita?
- Site/landing page existe? URL?
Se já existe marketing/seo/06-google-ads.md (criado pelo /seo), usar como base — pular as perguntas que já foram respondidas lá.
Passo 2 — Pesquisa de palavras-chave
Se já existe marketing/seo/01-pesquisa-demanda.md, usar o top 10-20 de termos prioritários (intenção transacional + comercial).
Se não existe, gerar:
- 30-50 termos-semente baseados no briefing
- WebSearch pra cada grupo: ver concorrência, sazonalidade
- Filtrar pelos de intenção comercial/transacional (descartar informacionais)
- Agrupar em clusters (ex: "feijoada-buffet", "feijoada-restaurante", "feijoada-evento")
Passo 3 — Estrutura de campanha
Padrão recomendado pra B2B local:
Campanha 1: <Negócio> — Search Geral
├── Grupo: <Cluster 1>
│ ├── 10-15 keywords (mix de exata, frase, ampla modificada)
│ ├── 3 RSAs (15 headlines + 4 descriptions cada)
│ └── 10-15 keywords negativas no grupo
├── Grupo: <Cluster 2>
│ └── ...
└── ... (1 grupo por cluster do Passo 2)
Campanha 2: <Negócio> — Local (opcional)
├── Anúncios pra Google Maps
└── Segmentação por proximidade
Lista de negativas globais: termos genéricos descartados, marcas concorrentes
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 First seen · 175 lines · 114 tokens per session scan A da67abeae807
anuncio-google is a skill published in the GitHub repository felipenalves/InvOS (5 stars, last pushed 5d ago), licensed MIT. It adds 114 tokens to every session and 1,801 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-local
Store user preferences, learnings from tasks, and procedure outcomes. Use to remember what works and recall context before new tasks. (user).
hindsight-docs
Complete Hindsight documentation for AI agents. Use this to learn about Hindsight architecture, APIs, configuration, and best practices.
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.