video-animado

video-animado is a skill for Claude Code from DGatoM/DG-Claw. It costs 134 tokens per session (1,489 once invoked), scanned B, original, MIT.

A DG Claw removal procedure that stops its service, scheduled tasks, and panel, while preserving items in the default mode. An optional purge moves identity, memory, planning, and related files into a dated backup.

In plain words
What is it for?
Use it to take a DG Claw assistant offline, choose what to preserve, and create a backup when purging its workspace.
Why use it?
It makes removal reversible and clarifies what will remain or be moved before anything is changed. This reduces the risk of deleting data that may be needed later.

Skill for Claude Code

Written for Claude Code: user-invocable in frontmatter. Also seen: reads .claude/ paths.

Good fit Use it to take a DG Claw assistant offline, choose what to preserve, and create a backup when purging its workspace.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/dgatom/dg-claw/video-animado
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 DGatoM/DG-Claw --skill video-animado
Clone the repo
git clone --depth 1 https://github.com/DGatoM/DG-Claw

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 video-animado

README.md
[![agentmods](https://agentmods.dev/badge/skills/dgatom/dg-claw/video-animado/github.svg)](https://agentmods.dev/skills/dgatom/dg-claw/video-animado)
Your own site
<a href="https://agentmods.dev/skills/dgatom/dg-claw/video-animado"><img src="https://agentmods.dev/badge/skills/dgatom/dg-claw/video-animado/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 video-animado

Your own site · 80×15
<a href="https://agentmods.dev/skills/dgatom/dg-claw/video-animado"><img src="https://agentmods.dev/badge/skills/dgatom/dg-claw/video-animado.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 134 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,489 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. 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 $0.00134 $0.01489
Opus 5.5 $0.00054 $0.00596
Sonnet 5.5 $0.00027 $0.00298
Haiku 4.5 $0.00013 $0.00149

Measured 19d ago against content hash 895925a0561b, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade B, and why

video-animado scanned grade B 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 19d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/renderizar.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

Asks for rootmediumPrivilege escalation

A mod that escalates privileges can change anything on the machine, not only the project.

| "o Chromium do Playwright não está nesta caixa" | `sudo -E /opt/venv/bin/python -m playwright install --with-deps chromium` |
skills/video-animado/SKILL.md · 76 lines

How it starts

The opening of the file, as written. The whole thing — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Vídeo animado (MP4 curto, renderizado na caixa)

Você escreve UMA página HTML cuja animação depende só do tempo t. O script scripts/renderizar.py abre a página no Chromium, chama __render(t) quadro a quadro, e o ffmpeg monta o MP4 (H.264, 30 fps). Um vídeo de 5 s leva cerca de 20 segundos para renderizar.

Passo a passo

  1. Planeje antes de codar. Escreva no chat, em poucas linhas: formato, duração, cenas com tempos e o texto de cada uma. Exemplo para 5 s: cena 1 (0 a 1,8 s) gancho, cena 2 (1,8 a 3,6 s) ideia, cena 3 (3,6 a 5 s) fecho. Formato padrão: vertical 1080x1920. Horizontal: 1920x1080. Quadrado: 1080x1080.
  2. Copie o template e adapte: cp ~/.claude/skills/video-animado/templates/composicao-base.html ./video.html Troque textos, cores e a função __render(t). Não mexa no motor (easings, tween, pose). Se mudar o formato, ajuste juntos o CSS de html, body, #palco e window.__tamanho.
  3. Renderize: /opt/venv/bin/python ~/.claude/skills/video-animado/scripts/renderizar.py video.html video.mp4 (opções: --fps 30, --largura N --altura N). Mostra o progresso a cada 30 quadros e, no fim, caminho, duração e tamanho, conferindo a duração com o ffprobe.
  4. Confira com os olhos. Extraia 3 quadros e olhe cada um com a ferramenta de leitura de imagem:
    for s in 0.5 2.5 4.5; do ffmpeg -y -loglevel error -ss $s -i video.mp4 -frames:v 1 q$s.png; done
    
    Procure texto cortado, fora da margem segura, sobreposto ou pequeno demais. Se achar, corrija e renderize de novo.
  5. Entregue o MP4 ao aluno (anexo ou caminho do arquivo, como o canal permitir) e diga em uma linha o que tem em cada cena.

O contrato da página

  • window.__duracao = 5; (segundos) e window.__tamanho = [1080, 1920];
  • window.__render = function (t) { ... } desenha o estado EXATO do instante t, sempre do zero, sem depender do quadro anterior.
  • Proibido: requestAnimationFrame, setTimeout, setInterval, CSS animation rodando sozinha, vídeo ou GIF embutido, imagens da internet. Tudo é calculado de t.
  • Helpers do template: tween(t, inicio, fim, de, para, 'saida') devolve o valor interpolado; pose(id, {x, y, escala, rot, op, w, h, raio}) aplica o estado do elemento. Easings: suave, saida, entrada, volta, elastico, linear.
  • Alternativa avançada: WAAPI com animation.pause() e animation.currentTime = t * 1000.
  • Fontes: use só as da caixa (DejaVu Sans, Liberation Sans, Arial). Fonte da internet não carrega.

Read the full file on GitHub · 76 lines

Files

What ships with it

2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 19d ago First seen · 76 lines · 134 tokens per session scan B 895925a0561b

Subscribe to this mod's changes

video-animado is a skill published in the GitHub repository DGatoM/DG-Claw (20 stars, last pushed 2d ago), licensed MIT. It adds 134 tokens to every session and 1,489 once invoked, about $0.0005 per session on Opus 5.5. A static security scan graded it B with 1 finding (asks for root). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-18.

Related

video-animado compared with skills from other repositories

video-animado next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
video-animadoDGatoM/DG-ClawSkill202d agoMITB134Claude Code
imagegenopenai/codexSkill133kyesterdayApache-2.0A113Codex
playwright-climicrosoft/playwrightSkill99kyesterdayApache-2.0A19Claude Code
local-ai-agentsmicrosoft/ai-agents-for-beginnersSkill79k4d agoMITA200Claude Code, Codex
systematic-debuggingobra/superpowersSkill313k3d agoMITA21Claude Code
next-cache-components-adoptionvercel/next.jsSkill143kyesterdayMITA95Claude Code
next-partial-prefetching-adoptionvercel/next.jsSkill143kyesterdayMITA103Claude Code