agent-first

A project rule for video work that says the agent carries out commands, compositions, and renders on the user’s behalf.

In plain words
What is it for?
Use it to guide video projects: read the project instructions, run checks and renders, store MP4 files in renders, compositions in compositions, briefs in briefs, and record third-party credits.
Why use it?
It makes the expected workflow and file locations clear when producing videos.

Cursor rule for Cursor

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.

agentmods
npx agentmods add rules/maiscafe/video_motion/agent-first
Clone the repo
git clone --depth 1 https://github.com/maiscafe/video_motion

Made for: Cursor.

Per session 150 This file is loaded in full into every session.
When invoked 150 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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 $0.00150 $0.00150
Opus 5 $0.00075 $0.00075
Sonnet 5 $0.00030 $0.00030
Haiku 4.5 $0.00015 $0.00015

Measured yesterday against content hash b43f4bd054ea, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

agent-first 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 yesterday.

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.

.cursor/rules/agent-first.mdc · 15 lines

What it actually says

video_motion — agent-first

  • Leia AGENTS.md na raiz antes de criar ou editar vídeos.
  • O usuário não roda terminal. Você executa npm run check, npm run render:*, instalação de skills, etc.
  • Todo MP4 vai em renders/. Toda composição em compositions/. Brief em briefs/.
  • Use skills HyperFrames + Revenue-Centric Design quando existirem em .agents/skills/.
  • Créditos de terceiros: docs/CREDITOS.md.
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. yesterday First seen · 15 lines · 150 tokens per session scan A b43f4bd054ea

Subscribe to this mod's changes

agent-first is a cursor rule published in the GitHub repository maiscafe/video_motion (2 stars, last pushed 1mo ago), licensed MIT. It adds 150 tokens to every session, about $0.0007 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.