forge-studio-lite: Command for Claude Code

.claude/commands/carrusel.md

carrusel is a command for Claude Code from Carlos-Dominguez-faber/forge-studio-lite. It costs 26 tokens per session (2,207 once invoked), scanned A, original, MIT.

A command that creates a Spanish-language Instagram carousel as a set of 1080×1080 PNG slides. An Instagram carousel is one post containing several swipeable images.

In plain words
What is it for?
Use it to choose a narrative structure, prepare a slide storyboard, render the slides from HTML and CSS, and review the finished images.
Why use it?
It gives the slides a planned story, such as an opening hook, explanation, evidence, and call to action, before rendering them.

Command for Claude Code

Written for Claude Code: argument-hint in frontmatter. Also seen: names the AskUserQuestion tool; positional $N argument.

This is Carlos-Dominguez-faber/forge-studio-lite's own configuration. It tells Claude Code how to work on forge-studio-lite itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything forge-studio-lite configures →

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is 3. Slug kebab-case → ./carousels/<slug>/.

Reuse

Borrowing it

Nothing to install: this file belongs to Carlos-Dominguez-faber/forge-studio-lite. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/Carlos-Dominguez-faber/forge-studio-lite/main/.claude/commands/carrusel.md
Clone the repo
git clone --depth 1 https://github.com/Carlos-Dominguez-faber/forge-studio-lite

Made for: Claude Code.

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 carrusel

README.md
[![agentmods](https://agentmods.dev/badge/commands/carlos-dominguez-faber/forge-studio-lite/carrusel/github.svg)](https://agentmods.dev/commands/carlos-dominguez-faber/forge-studio-lite/carrusel)
Your own site
<a href="https://agentmods.dev/commands/carlos-dominguez-faber/forge-studio-lite/carrusel"><img src="https://agentmods.dev/badge/commands/carlos-dominguez-faber/forge-studio-lite/carrusel/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 carrusel

Your own site · 80×15
<a href="https://agentmods.dev/commands/carlos-dominguez-faber/forge-studio-lite/carrusel"><img src="https://agentmods.dev/badge/commands/carlos-dominguez-faber/forge-studio-lite/carrusel.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 26 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,207 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 $0.00026 $0.02207
Opus 5 $0.00013 $0.01104
Sonnet 5 $0.00005 $0.00441
Haiku 4.5 $0.00003 $0.00221

Measured 12d ago against content hash 534b63cb11e2, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

carrusel 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 12d 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.

.claude/commands/carrusel.md · 156 lines

How it starts

The opening of the file, as written. The whole thing — 156 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/carrusel

Carrusel de Instagram en PNG 1080×1080 a partir de slides HTML consistentes con la marca. Cero generación AI — puro HTML + CSS + Playwright screenshot ⇒ determinístico, gratis y rápido (~5–15s para 5 slides).

El valor del carrusel está en la historia, no en el diseño. Por eso antes de escribir slides eliges una estructura narrativa (hook → desarrollo → CTA). Lee docs/estructuras-narrativas.md y escoge la que calce con el objetivo del usuario.

Flujo guiado (OBLIGATORIO)

$0 de generación, pero igual sigue el gate de docs/flujo-guiado.md — aquí el gate es de dirección de contenido, no de gasto.

  1. Intake: confirma tema, objetivo (lead magnet / educativo / prueba social / …),

    de slides y estructura narrativa (docs/estructuras-narrativas.md). Pregunta solo lo que falte.

  2. Outline: escribe STORYBOARD.md (1 sección por slide, rol: hook/punto/prueba/cta).
  3. Aprobar outline: muestra el outline (rol + copy de cada slide) y pide OK antes de escribir los HTML. AskUserQuestion: [Aprobar y renderizar] / [Ajustar] / [Cancelar].
  4. Renderizar: escribe los slide-NN.html y npm run carrusel -- ./carousels/<slug>.
  5. Revisar: entrega los PNG; ofrece editar slides puntuales (edita el HTML, re-corre).

Pipeline

Agente (tú):
  1. Lee brand/{brand.json,voice.json,brand.css}
  2. Lee docs/estructuras-narrativas.md → elige estructura según objetivo
  3. Slug kebab-case → ./carousels/<slug>/
  4. STORYBOARD.md (1 sección por slide, rol: hook | punto | prueba | cta)
  5. slides/source/slide-NN.html (self-contained, CSS inline desde brand.css)

TS pipeline:
  npm run carrusel -- ./carousels/<slug>   (= carousel.ts, Playwright screenshot)

Reglas

  • Sin generación AI. Solo HTML + CSS + screenshot. Cada slide es un archivo self-contained: copia los tokens de brand/brand.css al <style>, sin links externos a brand.css (los paths relativos rompen según dónde viva el proyecto).
  • Siempre 1080×1080. html, body, .slide con dimensiones fijas.
  • Consistente con la voz. Cada línea respeta brand/voice.json: usa hooks, nunca avoid. Tono según voice.tone.
  • Keyword-highlighting. Resalta 1–3 palabras clave por slide con el color primario: <span style="color: var(--primary);">palabra</span>. Es lo que da el "punch" visual.
  • El hook va en slide-01; el CTA en la última. Si tienes un logo (brand/photos/logo.png), úsalo solo en la slide de CTA.

Read the full file on GitHub · 156 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. 12d ago First seen · 156 lines · 26 tokens per session scan A 534b63cb11e2

Subscribe to this mod's changes

carrusel is a command published in the GitHub repository Carlos-Dominguez-faber/forge-studio-lite (14 stars, last pushed 2mo ago), licensed MIT. It adds 26 tokens to every session and 2,207 once invoked, about $0.0001 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 2026-08-30.