carrossel

carrossel is a skill for Claude Code from inhabitants/sapiens-mcp. It costs 59 tokens per session (1,276 once invoked), scanned A, original, MIT.

A workflow for creating Instagram carousels, which are posts made of several swipeable slides, from a brief or an article. It produces the slide content and layout data for review and download in the user's editor.

In plain words
What is it for?
Use it to create a carousel, rewrite slide text, set slide images and update an existing carousel while preserving edits made elsewhere.
Why use it?
It gives the agent a defined way to prepare a carousel without directly exporting the final files. The user can review the result and download it from the editor.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the sapiens-sinteticos plugin — 18 skills, 1 MCP server shipped together

Good fit Use it to create a carousel, rewrite slide text, set slide images and update an existing carousel while preserving edits made elsewhere.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/inhabitants/sapiens-mcp/carrossel
Install

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.

Any agent
npx skills add inhabitants/sapiens-mcp --skill carrossel
Clone the repo
git clone --depth 1 https://github.com/inhabitants/sapiens-mcp

Made for: Claude Code.

Or install sapiens-sinteticos, the plugin that ships this one along with the rest of its 18 skills, 1 MCP server.

Wrote 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.

agentmods badge for carrossel

README.md
[![agentmods](https://agentmods.dev/badge/skills/inhabitants/sapiens-mcp/carrossel/github.svg)](https://agentmods.dev/skills/inhabitants/sapiens-mcp/carrossel)
Your own site
<a href="https://agentmods.dev/skills/inhabitants/sapiens-mcp/carrossel"><img src="https://agentmods.dev/badge/skills/inhabitants/sapiens-mcp/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.

agentmods 80×15 button for carrossel

Your own site · 80×15
<a href="https://agentmods.dev/skills/inhabitants/sapiens-mcp/carrossel"><img src="https://agentmods.dev/badge/skills/inhabitants/sapiens-mcp/carrossel.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 59 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,276 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00059 $0.01276
Opus 5.5 $0.00024 $0.00510
Sonnet 5.5 $0.00012 $0.00255
Haiku 4.5 $0.00006 $0.00128

Measured 4d ago against content hash d94319b1b698, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

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 4d 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.

plugins/sapiens-sinteticos/skills/carrossel/SKILL.md · 49 lines

How it starts

The opening of the file, as written. The whole thing — 49 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Carrossel: gerar, escrever, pôr foto e entregar

O que é

Um carrossel é uma RECEITA: tema (paleta, folha e assinatura) mais slides, cada um com um layout (templateId) e os textos dele (slots). O desenho sai dessa receita no editor da pessoa, que é também onde ela baixa os arquivos. Você escreve a receita; ela abre, confere e baixa.

O fluxo

  1. sapiens_carrossel action=generate com brief (o tema e o ângulo, um parágrafo) OU articleId (artigo publicado) OU userArticleId (artigo dela). Custa 350 Sinapses, já com a escolha de fotos, e estorna se falhar. Devolve o id e a url do editor.
  2. action=get traz o payload inteiro e o catálogo: os layouts com os slots de cada um, as paletas, as folhas e a assinatura. Leia antes de mexer.
  3. action=update grava o payload INTEIRO de volta. Reescreva os textos com a voz da pessoa (puxe a skill voz-da-casa). Mande o theme inteiro e o image de todo slide que você não mexeu: o que faltar volta pro padrão e a foto do slide some. Mande também baseUpdatedAt com o updatedAt do get: se o carrossel mudou depois (uma foto gerada, uma edição dela no editor), o update recusa em vez de apagar isso, e aí você faz get de novo. Foto nova não entra por URL no update, só pelo passo 4.
  4. Foto: action=auto_images (60) deixa a IA escolher do banco; action=set_image põe uma peça DA PESSOA pelo ID citável (img_…, de sapiens_reference ou sapiens_gallery), de graça; action=generate_image gera uma nova pra um slide, ~450 cada.
  5. Mande a url do editor. É lá que ela confere, ajusta e baixa.

A forma e o tamanho

model é a FORMA: feed (o padrão, 9 slides que abrem numa dor, mostram o mecanismo e fecham em ação), reflexao (tema de comportamento sustentado por uma analogia), case (tendência a partir de link ou manchete, fecha numa keyword) e editorial (a IA escolhe os layouts, 7 a 9 slides).

aspect é o TAMANHO: 4:5 (o padrão, a folha que o feed do Instagram mostra inteira) ou 9:16 (tela cheia). Os dois trocam depois no editor sem perder texto.

Read the full file on GitHub · 49 lines

Changes

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.

  1. 4d ago First seen · 49 lines · 59 tokens per session scan A d94319b1b698

Subscribe to this mod's changes

carrossel is a skill published in the GitHub repository inhabitants/sapiens-mcp (1 stars, last pushed 4d ago), licensed MIT. It adds 59 tokens to every session and 1,276 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-10-20.

Related

Other skills, from other repositories

21st-ui

Find, install, and generate UI with 21st.dev. Use when the user asks for a UI component (pricing table, hero, navbar, dashboard, form, etc.), wants design inspiration, needs a brand logo as an SVG component, or wants to generate new UI from a prompt.

21st-dev/magic-mcp · 63 tokens

form-list-layout

Configure what a form and a list look like — sysuiform, sysuisection and sysuielement for forms; sysuilist, sysuilistelement and sysuirelatedlist for lists; sysfilter for saved filters. Views, why a field must exist in the dictionary first, and what snowcreatemenu really writes.

serac-labs/serac · 70 tokens

kernelcad-mcp

Load when kernelcad mcp is available and you need to inspect or edit a live model without re-running the full CLI on every change. The MCP server exposes dynamic introspection tools that operate on evaluated in-memory state.

w1ne/kernelCAD-web · 51 tokens

kernelcad-kinematic

Use when verifying whether a moving assembly is buildable — sampled-pose collision sweeps across joint ranges, IK reachability for end-effector targets, mounting-hole fastener consistency, and static-load capacity on cantilever-shaped parts. Loads alongside kernelcad-authoring to gate design-time mechanism feasibility.

w1ne/kernelCAD-web · 65 tokens

kernelcad-trace-from-image

Convert pixel-space features from a reference photo into normalized [0,1] waypoints, then into mm coordinates feedable to path().spline / path().nurbsSegment. Uses the tracefromimage MCP tool. Load when your blockout is in place and the next step is an organic-curve outline (upper contour, ergonomic handle, sneaker…

w1ne/kernelCAD-web · 94 tokens

reticle-aesthetic

Build landing page sections, hero blocks, and marketing surfaces in the Reticle/Sigil engineering-instrument-grid aesthetic. Use when creating new landing sections, hero components, marketing pages, or when the user says "reticle", "hero", "landing page", "new section", "instrument panel", "grid cell", or wants to…

Kevin-Liu-01/Agent-Machines · 80 tokens