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 skills add frankxai/awesome-motion-design-agent-skills --skill site-motion-excellence-directorgit clone --depth 1 https://github.com/frankxai/awesome-motion-design-agent-skillsWrote 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/skills/frankxai/awesome-motion-design-agent-skills/site-motion-excellence-director)<a href="https://agentmods.dev/skills/frankxai/awesome-motion-design-agent-skills/site-motion-excellence-director"><img src="https://agentmods.dev/badge/skills/frankxai/awesome-motion-design-agent-skills/site-motion-excellence-director/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/skills/frankxai/awesome-motion-design-agent-skills/site-motion-excellence-director"><img src="https://agentmods.dev/badge/skills/frankxai/awesome-motion-design-agent-skills/site-motion-excellence-director.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 | $0.00079 | $0.00548 |
| Opus 5 | $0.00039 | $0.00274 |
| Sonnet 5 | $0.00016 | $0.00110 |
| Haiku 4.5 | $0.00008 | $0.00055 |
Grade A, and why
site-motion-excellence-director 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 11d 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 — 54 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Site Motion Excellence Director
Use this skill before adding substantial motion to a website or app.
Workflow
- Identify the brand, route, audience, and first user task.
- Define the first read before animation.
- Name the motion job: orient, reveal, explain, confirm, compare, express brand, or convert.
- Pass the still-frame gate.
- Write a beat sequence: setup, trigger, primary move, secondary support, hold, final state.
- Choose the lightest runtime that preserves the intent.
- Specify reduced motion in the same pass.
- Implement only after the spec is clear.
- Verify with browser screenshots, mobile, reduced motion, and video/frame proof.
- Score with the excellence gate.
Runtime Rules
- Use CSS for simple state changes, hover/focus, skeletons, and low-risk reveals.
- Use Motion for React for component choreography, layout transitions, presence, and React scroll work.
- Use GSAP ScrollTrigger for pinned, scrubbed, snapped, SVG/canvas, or complex authored timelines.
- Use Rive for interactive vector state machines.
- Use Lottie/dotLottie for portable non-interactive vector loops.
- Use Three.js only when 3D is central and visually verified.
- Use Remotion for rendered video, social variants, product explainers, and exact text/layout in media.
- Use Grok/imagegen/Veo/Sora/Luma/Runway/Higgsfield only as source generation, then finish and QA in context.
Taste Rules
- Motion is hierarchy over time.
- Do not animate a weak still frame.
- Make one object the hero.
- Use stillness as contrast.
- Keep repeated task motion short and quiet.
- Do not bake exact product text into generated images or videos.
- Treat mobile as separate choreography.
- Never ship meaningful motion without reduced-motion behavior.
Required Spec
Use templates/site-motion/SITE_MOTION_SPEC.md for substantial site motion.
Use rubrics/site-motion-excellence-gate.md before handoff.
Output Shape
Return: motion thesis, first-read diagnosis, still-frame verdict, motion map, runtime choice, reduced-motion plan, implementation tasks, QA proof required, and excellence score.
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.
- 11d ago First seen · 54 lines · 79 tokens per session scan A cdc09b9227b8
site-motion-excellence-director is a skill published in the GitHub repository frankxai/awesome-motion-design-agent-skills (1 stars, last pushed 4d ago), licensed CC0-1.0. It adds 79 tokens to every session and 548 once invoked, about $0.0004 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 2026-09-01.
Other skills, from other repositories
frontend-ui-ux-system
A company-level guide for designing web interfaces and user experiences. It covers visual styles, design tokens (named values for colors, spacing, and typography), layout, interaction, accessibility, motion, and review checks.
frontend-design
Design and build production-ready frontend interfaces with design systems, responsive layouts, accessible components, and dark mode support. Use when the user requests frontend design or provides relevant inputs for this workflow.
ss-feedback
Add appropriate user feedback states (loading, success, error, empty) to a component or page.
frontend-glassmorphism
Builds premium glassmorphism (3D-like, soft blur) frontend UI components and landing pages using React/Next.js + Tailwind conventions. Use when designing modern SaaS pages, hero sections, pricing, navbars, feature grids, and animations with accessible contrast and performance constraints.
frontend-aesthetic-direction
A skill for choosing a complete visual direction for a new frontend project with no existing brand or design system. It defines rules for typography, colors, spacing, shapes, components, imagery, icons, and motion.
make-tweakable
A hidden floating settings panel for a single-file HTML design or prototype. It lets someone adjust selected colors, fonts, spacing, text, layout options, or feature switches while comparing variations in the same file.