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 OpaceDigitalAgency/ai-ui-ux-motion-engine --skill ai-ui-ux-motion-enginegit clone --depth 1 https://github.com/OpaceDigitalAgency/ai-ui-ux-motion-engineWrote 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/opacedigitalagency/ai-ui-ux-motion-engine/ai-ui-ux-motion-engine)<a href="https://agentmods.dev/skills/opacedigitalagency/ai-ui-ux-motion-engine/ai-ui-ux-motion-engine"><img src="https://agentmods.dev/badge/skills/opacedigitalagency/ai-ui-ux-motion-engine/ai-ui-ux-motion-engine/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/opacedigitalagency/ai-ui-ux-motion-engine/ai-ui-ux-motion-engine"><img src="https://agentmods.dev/badge/skills/opacedigitalagency/ai-ui-ux-motion-engine/ai-ui-ux-motion-engine.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 | $0.00138 | $0.02887 |
| Opus 5 | $0.00069 | $0.01443 |
| Sonnet 5 | $0.00028 | $0.00577 |
| Haiku 4.5 | $0.00014 | $0.00289 |
Grade A, and why
ai-ui-ux-motion-engine 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 12d 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 — 288 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AI UI/UX Motion Engine
Create a project-specific experience from evidence. Treat references as structural, visual and interaction inputs, never as permission to clone branding, copy, code or protected assets.
Non-negotiable rules
- Read applicable
AGENTS.md, source-of-truth documents, design systems and current working-tree changes before editing. - Define the bounded target, acceptance criteria, dependencies, spend and validation plan.
- Use the fastest route that can meet the accuracy target. For real products,
default to
evidence-accuratewhen authoritative sources exist; never trade accuracy silently for spectacle. State early when CAD, compositing or real footage is required. - Preserve the existing stack unless the user explicitly authorises a change.
- Label observations, facts, proposals, generated visualisations and unknowns.
- Keep content and actions usable without motion, JavaScript or unrestricted data use.
- Never claim cinematic parity, product accuracy, accessibility, performance or release readiness without direct evidence.
- Never configure a paid service, accept provider terms or spend credits without user authority.
- Never downgrade a requested full-screen, homepage or signature cinematic journey to a supporting shot. A camera rotation, dolly, zoom, parallax or static-image reveal is not a flagship.
Mandatory cinematic-intent gate
Activate this gate whenever the request or reference implies any of:
- a cinematic, premium or immersive scroll experience;
- a product opening, assembling, exploding, bursting or transforming;
- a camera orbit, dolly, macro inspection or authored product journey;
- photographic motion controlled by scrolling;
- a reference whose impact comes from changing viewpoint or object state.
The user does not need to use a trigger word or know which tool is required.
Before editing the page:
- Copy the user's requested outcome into
intent.requestSummary; record the signature moment, progression, payoff, required effects and unacceptable substitutes. Do not rewrite the request around the easiest available asset. - Classify truth mode:
illustrative: invented details are acceptable;identity-locked: the same fictional or concept product must stay stable;evidence-accurate: visible counts, geometry, labels and mechanics must match authoritative product evidence.
- Confirm the reference or desired scenes, available source images or CAD, number and placement of flagship/supporting moments, target devices, media provider access and permitted credit/attempt cap. If the reference is a video, inspect keyframes plus any available transcript, prompt pack and description links; do not reconstruct its workflow from a summary or isolated screenshot.
- State the dependency plainly. Photographic camera movement or physical transformation requires suitable source media plus an image/video generation, 3D or compositing route. CSS cannot invent unseen product views.
- If the required provider or source material is unavailable, stop the cinematic asset work. Offer the static layout/fallback honestly; never substitute fades, zooms or stock background video and call it equivalent.
- Create a cinematic brief from
assets/cinematic-brief.example.json, validate it withscripts/validate-cinematic-brief.mjs, and obtain spend/terms authority before generation. Do not upload or spend after a failed validation. - Produce one isolated private proof of the signature moment before redesigning the page or generating the full library.
- Reject drift with automated technical checks and an overview contact sheet. Sample only risky transitions densely; inspect every frame only for a detected defect or evidence-critical mechanics. Use at most the approved attempts; then simplify the action, change technique or report the blocker.
- Create a creative-review JSON from
assets/creative-acceptance.example.jsonand runscripts/validate-creative-acceptance.mjs. Technical media validation does not prove narrative, impact or creative acceptance. - Integrate only an owner-approved asset after the creative validator passes
with
--stage integration. Never put a weak proof into a live hero to see whether surrounding UI rescues it.
What ships with it
30 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- agents/openai.yaml 343 B
- assets/cinematic-brief.example.json 4.8 KB
- assets/cinematic-scroll-controller.js 3.0 KB runs code
- assets/creative-acceptance-placeholder.txt 175 B
- assets/creative-acceptance.example.json 704 B
- assets/regressions/camera-only-homepage-failure.json 3.0 KB
- references/accessibility-performance.md 1.6 KB
- references/cinematic-case-study.md 2.6 KB
- references/cinematic-intake.md 6.1 KB
- references/cinematic-prompts.md 4.4 KB
- references/framework-recipes.md 1.8 KB
- references/generated-product-scrubber.md 12 KB
- references/media-pipeline.md 4.1 KB
- references/motion-patterns.md 4.1 KB
- references/prompts.md 2.5 KB
- references/research-and-extraction.md 2.0 KB
- references/source-coverage.md 4.0 KB
- references/tool-connections.md 4.3 KB
- references/verification.md 4.8 KB
- references/workflow.md 4.1 KB
- scripts/audit-motion-safety.mjs 2.7 KB runs code
- scripts/extract-reference-frames.sh 1.4 KB runs code
- scripts/higgsfield-preflight.mjs 2.3 KB runs code
- scripts/prepare-scroll-media.sh 2.8 KB runs code
- scripts/render-cinematic-prompt.mjs 3.7 KB runs code
- scripts/test-cinematic-regressions.mjs 2.6 KB runs code
- scripts/validate-cinematic-brief.mjs 15 KB runs code
- scripts/validate-creative-acceptance.mjs 3.8 KB runs code
- scripts/validate-package.mjs 14 KB runs code
- scripts/validate-scroll-media.mjs 8.0 KB runs code
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.
- 12d ago First seen · 288 lines · 138 tokens per session scan A e77294ce33de
ai-ui-ux-motion-engine is a skill published in the GitHub repository OpaceDigitalAgency/ai-ui-ux-motion-engine (1 stars, last pushed 7d ago), licensed MIT. It adds 138 tokens to every session and 2,887 once invoked, 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.
Other skills, from other repositories
ai-ui-ux-motion-engine
Design, redesign, build, audit and validate distinctive production websites with cinematic scroll reveals, product films, burst or exploded-view effects, reference-led design systems, purposeful motion and multi-pass refinement. Use for landing pages, product sites, portfolios, interactive storytelling, premium or…
aceternity-ui
100+ animated React components (Aceternity UI) for Next.js with Tailwind. Use for hero sections, parallax, 3D effects, or encountering animation, shadcn CLI integration errors.
animation-motion-design
Animation and motion design patterns using Motion library (formerly Framer Motion) and View Transitions API. Use when implementing component animations, page transitions, micro-interactions, gesture-driven UIs, or ensuring motion accessibility with prefers-reduced-motion.
design-engineering
UI craftsmanship: animation rules, easing, micro-interactions, state polish. Triggers: animation, transition, ease-out, motion, micro-interaction, hover, loading state, UI polish.
apply-mantel-styles
Provides guidelines for applying Mantel's brand styles to diagrams and frontend components. Use when asked to create visuals that need to align with Mantel's branding.
julilaoshi-design
Public-safe julilaoshi-design workflow for official Pencil MCP execution and the free browser-first julilaoshi-design Web 2.0 editor. Use when a task needs Pencil handshake/canvas edits, .pen execution, screenshot review, or lightweight HTML design-to-web tweaking without redistributing official Pencil or leaking…