Borrowing it
Nothing to install: this file belongs to taotao135791-bit/gsap-transform. 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/taotao135791-bit/gsap-transform/main/.github/instructions/video-grammar.instructions.mdgit clone --depth 1 https://github.com/taotao135791-bit/gsap-transformWrote 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/taotao135791-bit/gsap-transform/video-grammar)<a href="https://agentmods.dev/instructions/taotao135791-bit/gsap-transform/video-grammar"><img src="https://agentmods.dev/badge/instructions/taotao135791-bit/gsap-transform/video-grammar/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.
<a href="https://agentmods.dev/instructions/taotao135791-bit/gsap-transform/video-grammar"><img src="https://agentmods.dev/badge/instructions/taotao135791-bit/gsap-transform/video-grammar.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00417 | $0.00417 |
| Opus 5 | $0.00209 | $0.00209 |
| Sonnet 5 | $0.00083 | $0.00083 |
| Haiku 4.5 | $0.00042 | $0.00042 |
Grade A, and why
gsap-transform video-grammar.instructions.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 9d 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.
What it actually says
video-grammar — effect-video aesthetic instructions
Load this in addition to motion-design-taste when the artifact is a rendered video (mp4/webm/mov) from /studio — promos, spots, title sequences, reels. motion-design-taste still owns the page (dials, modes, type, color); video-grammar owns shots, camera, transitions, pacing, aspect.
When building a /studio scene that renders as video, follow skills/video-grammar/SKILL.md:
- Put all shot content inside ONE
.camerawrapper; the master timeline animates the camera (scale/xPercent/yPercent), and content animates inside. Keep those two animation surfaces separate. - Shot type = camera scale (WS 1.0 → CU 2.2 → ECU 3.0+). Open on a WS hold ≥ 1 beat before the first move.
- ONE camera move per shot (V1). Cut (hard or one signature transition) between moves.
- At most ONE hero transition (whip pan / morph / match cut / glitch) per video; the rest are hard cuts (V2).
- Snap every shot boundary + hero reveal to
beat = 60/bpm(V3). Bands: Restrained 60–80, Expressive 90–110, Cinematic 120–140. - The same scene must render acceptably at 16:9, 9:16, and 1:1 via
.cameraoffset — titles inside the aspect safe area (V4). rotationY/rotationX(orbit) only on opaque backgrounds — breaks under--transparent(V5).- Camera ease family:
power2.inOut/power3.inOut;nonefor hard cuts; neverback.*/elastic.*on a camera.
Run motion-anti-slop Group V before declaring a video scene done.
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.
- 9d ago First seen · 21 lines · 417 tokens per session scan A 1a55454de6e7
gsap-transform video-grammar.instructions.md is an instructions file published in the GitHub repository taotao135791-bit/gsap-transform (2 stars, last pushed 2mo ago), licensed MIT. It adds 417 tokens to every session, about $0.0021 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
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.
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).
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).
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.
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.