Borrowing it
Nothing to install: this file belongs to wassermanproductions/motion-previs-studio. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/wassermanproductions/motion-previs-studio/main/AGENTS.mdgit clone --depth 1 https://github.com/wassermanproductions/motion-previs-studioWrote 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.
[](https://agentmods.dev/instructions/wassermanproductions/motion-previs-studio/agents-md)<a href="https://agentmods.dev/instructions/wassermanproductions/motion-previs-studio/agents-md"><img src="https://agentmods.dev/badge/instructions/wassermanproductions/motion-previs-studio/agents-md.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.01568 | $0.01568 |
| Opus 5 | $0.00784 | $0.00784 |
| Sonnet 5 | $0.00314 | $0.00314 |
| Haiku 4.5 | $0.00157 | $0.00157 |
Grade A, and why
motion-previs-studio 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 8d 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 — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — running & modifying Motion Previs Studio with an AI agent
This file is the single source of truth for AI coding agents (Claude Code, Codex, Hermes, …) working on this repo. Read it before making changes.
What this app is
Electron + TypeScript + React desktop app. Filmmakers import a reference video shot, extract pose (MediaPipe), depth, a subject-masked optical-flow camera solve, edges/lineart/masks/normals control layers, and OpenPose BODY_25 skeleton video + keypoints, then export a production pack (control videos + prompts + Blender scripts + ZIP) for AI-video generators (Seedance, ComfyUI, Runway, Kling) and Blender. All ML runs locally in the renderer.
Commands
npm install # once; runs scripts/prepare-mediapipe-assets.cjs (postinstall)
npm run dev # Vite + Electron with hot reload (127.0.0.1 only)
npm run build # tsc + vite build into dist/
npm start # run the production build
npm run verify # smoke checks (tests/smoke.cjs)
npm run verify:quality # unified quality-score sync check
npm run verify:engines # engine/runtime checks
npm run verify:e2e # headless Electron export; asserts openpose_pose.mp4 + openpose_keypoints.json land in the bundle
npm run verify:all # verify + build + verify:e2e
npm run dist # electron-builder → arm64 DMG + ZIP in release/
Definition of done for any change: npm run build && npm run verify:quality && npm run verify:engines && npm run verify:e2e green. Run npm run verify:all before shipping.
Repo map
src/ React UI. App.tsx owns the whole studio surface.
src/lib/ Pure-ish analysis modules, all locally runnable:
pose.ts (MediaPipe), cameraMotion.ts (LK + RANSAC camera solve),
aiDepth.ts (Depth Anything), openpose.ts (BODY_25 render + JSON),
poseVideo.ts, frameEncoder.ts (deterministic ffmpeg frame encode),
quality.ts (single source of the unified quality score).
src/components/ ThreePreview (three.js stick figure), PoseCanvas.
src/control/ Agent-control renderer layer: registry.ts (the window.__mps surface
contract), handler.ts (whitelisted action dispatcher, wired from main.tsx).
electron/ main.cjs (window, IPC, ffmpeg, save/restore, Send to Blockout, control server wiring),
control.cjs (localhost HTTP agent-control server + discovery file),
preload.cjs (window.motionPrevis bridge), security.cjs (path + IPC allowlist).
mcp/ motion-previs-mcp.mjs (zero-dep stdio MCP bridge) + README.md (agent-integration guide).
shared/ quality.cjs — the CJS mirror of src/lib/quality.ts (verify:quality checks they agree).
tests/ e2e-electron.cjs (real export + control-server smoke), smoke, quality-sync, engines.
public/ generated MediaPipe/model/bin assets (gitignored).
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.
- 8d ago First seen · 70 lines · 1,568 tokens per session scan A 7c22b0d471fa
motion-previs-studio AGENTS.md is an instructions file published in the GitHub repository wassermanproductions/motion-previs-studio (343 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 1,568 tokens to every session, about $0.0078 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.
Other instructions, from other repositories
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.