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 carrosselgit 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/carrossel)<a href="https://agentmods.dev/skills/felipenalves/invos/carrossel"><img src="https://agentmods.dev/badge/skills/felipenalves/invos/carrossel/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/carrossel"><img src="https://agentmods.dev/badge/skills/felipenalves/invos/carrossel.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 | $0.00118 | $0.03436 |
| Opus 5 | $0.00059 | $0.01718 |
| Sonnet 5 | $0.00024 | $0.00687 |
| Haiku 4.5 | $0.00012 | $0.00344 |
Grade A, and why
carrossel 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 — 273 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/carrossel — Carrossel e posts visuais
Skill central de criação de conteúdo visual. Pega um tema → entrega HTMLs estilizados + PNGs prontos pra postar + legenda no padrão da marca.
Dependências
- Identidade visual:
marca/design-guide.md— LER ANTES de criar qualquer visual - Contexto do negócio:
_memoria/empresa.md - Tom de voz:
_memoria/preferencias.md - Playwright: pra renderizar HTML em PNG (
npx playwright screenshotou viarender.js) - OpenAI API (opcional): pra gerar fotos realistas — só se o cliente tiver chave configurada
- Outputs vão em:
marketing/conteudo/<tipo>-<tema>-<YYYY-MM-DD>/
Tipos de conteúdo
Ao receber um pedido, identificar qual tipo se encaixa:
1. CARROSSEL TEXTO PURO
- Quando usar: posts educacionais, dicas, listas, explicações
- Formato: 1080x1350 (4:5) — sempre
- Estilo: tipografia clean, cores da marca alternadas, sem fotos
2. CARROSSEL COM FOTO
- Quando usar: apresentação visual, conteúdo aspiracional, capa com personagem
- Formato: 1080x1350 (4:5)
- Estilo: foto como capa com gradient overlay + slides internos no padrão alternado
- Foto: pode ser IA (gerada por OpenAI) ou real (passada pelo usuário)
3. POST ÚNICO
- Quando usar: frase de impacto, dado/estatística, depoimento, bastidores
- Formato: 1080x1350
- Estilo: varia conforme o conteúdo (citação, número grande, foto com overlay)
Se o tipo não estiver claro, perguntar:
"Que tipo de conteúdo? (1) carrossel texto, (2) carrossel com foto, (3) post único"
Estilo visual base
O INVOS tem um estilo próprio — editorial, calmo, premium. Sem clip-art, sem emoji decorativo, sem gradiente arco-íris, sem template genérico de IA. marca/design-guide.md sobrescreve esses padrões; quando o design-guide for vago ou estiver em branco, usar o que tá aqui (não parar pra pedir /instalar — o /carrossel funciona com defaults bons).
Tipografia padrão
- Fonte: Inter (Google Fonts), pesos 400/500/600/700/800/900
- Título de capa: 90-100px, weight 900, line-height 0.98, letter-spacing -0.04em
- H2 (slides internos): 60-72px, weight 800, line-height 1.04, letter-spacing -0.035em
- Corpo: 20-24px, weight 500, line-height 1.5
- Eyebrow/kicker: 13-16px, weight 700-800, UPPERCASE, letter-spacing 0.22-0.32em, cor de destaque
- Page counter (canto sup. dir.): 14-16px, weight 500-600, letter-spacing 0.18em, cor muted
- Meta/handle (@): 15-18px, weight 600
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 · 273 lines · 118 tokens per session scan A e1fc6244f42e
carrossel is a skill published in the GitHub repository felipenalves/InvOS (5 stars, last pushed 7d ago), licensed MIT. It adds 118 tokens to every session and 3,436 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
wowerpoint
Turn one document into a kawaii NotebookLM slide-deck PDF. Use for "wowerpoint this", "make a deck about ", "turn this report into slides", or any request to render a single document as shareable narrative slides.
hindsight-local
Store user preferences, learnings from tasks, and procedure outcomes. Use to remember what works and recall context before new tasks. (user).
gpt-image-2-style-library
Choose GPT-Image2 / gpt-image-2 visual styles and industrial prompt templates from the awesome-gpt-image-2 style library. Use when an agent needs to create, rewrite, classify, or improve image-generation prompts with repository-backed templates, categories, style tags, scene tags, pitfalls, and example cases.
feature-demo-recording
Record a demo video of a web feature from a real browser. Two modes -- a NARRATED film where measured voiceover drives the timeline (designed slides, subtitles, punch-in camera, rendered from an HTML timeline), and a SILENT evidence clip for a PR or a QA pass. Use when the user asks to record a video, demo, or screen…
ffmpeg
Process audio and video with the ffmpeg / ffprobe CLIs — convert, trim, extract audio, resize, change format, make GIFs, inspect media. Use for any audio/video transformation.
meta-ads-creative
Create evidence-based Meta ad creative briefs, copy angles, and testable asset concepts for Facebook and Instagram. Use when asked for Meta ad creative, Facebook ads copy, Instagram ad assets, UGC concepts, creative briefs, new ad concepts, or creative refreshes.