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 agentmods add instructions/maiscafe/video_motion/agents-mdgit clone --depth 1 https://github.com/maiscafe/video_motionWhat 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 | $0.01296 | $0.01296 |
| Opus 5 | $0.00648 | $0.00648 |
| Sonnet 5 | $0.00259 | $0.00259 |
| Haiku 4.5 | $0.00130 | $0.00130 |
Grade A, and why
video_motion AGENTS.md 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 2d 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 — 140 lines — stays where its author put it; the contents beside it link to each section on GitHub.
video_motion — instruções para o agente de IA
Público deste arquivo: Cursor, Claude Code, Copilot ou qualquer agente com acesso ao terminal.
O usuário não roda comandos. Ele descreve o vídeo; você executa tudo nesta pasta.
Missão
Transformar pedidos em linguagem natural em MP4 9:16 em renders/, usando HyperFrames + GSAP + (opcional) skills de conversão.
O usuário abre a pasta video_motion no agente e pede, por exemplo:
"Cria um anúncio 19s para Instagram: hook sobre dor X, CTA teste grátis em meusite.com"
Você: brief → composição HTML → script npm → check → render → informar caminho do MP4.
Antes de codar — skills obrigatórias
- Se
.agents/skills/não existir, instale (com aprovação do usuário se necessário):
npx skills add heygen-com/hyperframes
npx skills add heliocosta-dev/revenue-centric-design
-
Leia a skill HyperFrames (
/hyperframesou.agents/skills/hyperframes/SKILL.md) antes de editar HTML. -
Para copy/CTA/conversão, aplique Revenue-Centric Design (Richard @richardrx + Hélio @heliotsx). Créditos:
docs/CREDITOS.md. -
Inspiração workflow agent-first: Nett0.
Fluxo padrão (sempre seguir)
1. Entender pedido → salvar brief em briefs/{slug}.md
2. Criar/editar compositions/{slug}.html (GSAP + window.__timelines)
3. Adicionar script render:{slug} no package.json → renders/{slug}.mp4
4. npm run check (ou lint da composição)
5. npm run render:{slug}
6. Confirmar renders/{slug}.mp4 existe e reportar ao usuário
Nunca peça ao usuário para rodar npm, instalar FFmpeg ou editar HTML — você faz.
Estrutura do repo
| Pasta / arquivo | Uso |
|---|---|
index.html |
Obrigatório — entrada HyperFrames (não apagar) |
compositions/ |
HTML dos vídeos |
renders/ |
Saída — todo MP4 vai aqui |
briefs/ |
Brief do pedido (ICP, hook, CTA, duração) |
docs/ |
Créditos, áudio, orgânico — consulte quando relevante |
exemplos/ |
Referências e pedidos exemplo |
package.json |
Você adiciona render:* conforme cria vídeos |
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.
- 2d ago First seen · 140 lines · 1,296 tokens per session scan A 46819e05ad37
video_motion AGENTS.md is an instructions file published in the GitHub repository maiscafe/video_motion (2 stars, last pushed 1mo ago), licensed MIT. It adds 1,296 tokens to every session, about $0.0065 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 instructions, from other repositories
diffusers AGENTS.md
AGENTS.md instructions for huggingface/diffusers, a project described as: 🤗 Diffusers: State-of-the-art diffusion models for image, video, and audio generation in PyTorch.
comfy-prompt-studio AGENTS.md
Instructions for yxhpy/comfy-prompt-studio, covering agents.md - ai 代理配置文档, ai 提供商, 1. ollama (默认), 2. gemini and 提示词生成服务.
davinci-resolve-mcp AGENTS.md
Instructions for apvlv/davinci-resolve-mcp, covering project knowledge base, structure, where to look, code map and conventions.
lianhuanhua-skills AGENTS.md
Instructions for littlewindy123/lianhuanhua-skills, covering agents.md, project goal, architecture rules, commands and before committing.
docvideoer CLAUDE.md
Instructions for coding-ax/docvideoer, covering claude.md — docvideoer, 触发方式, 外部 skill 依赖, 工作目录 and 核心流水线(6 步).
framer-motion-skills copilot-instructions.md
Copilot instructions for C-Jeril/framer-motion-skills, covering framer motion ai skills, available skills, usage, recommendations and code examples.