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 agentmods add skills/fusengine/agents/design-motionnpx skills add fusengine/agents --skill design-motiongit clone --depth 1 https://github.com/fusengine/agentsWrote 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/fusengine/agents/design-motion)<a href="https://agentmods.dev/skills/fusengine/agents/design-motion"><img src="https://agentmods.dev/badge/skills/fusengine/agents/design-motion.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 | $0.00029 | $0.02798 |
| Opus 5 | $0.00015 | $0.01399 |
| Sonnet 5 | $0.00006 | $0.00560 |
| Haiku 4.5 | $0.00003 | $0.00280 |
Grade A, and why
design-motion 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.
How it starts
The opening of the file, as written. The whole thing — 170 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Also enforces the ban on the AI motion signature (opacity:0 + translateY(20px) + ease-in-out applied uniformly to every entrance).
Runs only after the static body/component exists (design-web, design-webapp, design-ios, design-android) — never used to hide or compensate for an unfinished layout.
Design Motion — Timing, Easing, Materials, Restraint
When
After the static body/component exists. Motion is applied on top of a settled layout —
never used to compensate for or distract from an unfinished one. Hands off to
design-review next (Part 1 checks the reduced-motion fallback + transform/opacity
discipline; Part 2's motion-verdict.md issues the Block/Approve).
Input
design-system.mdmotion personality /MOTION_INTENSITYdial (1-10).- The static markup/components to animate.
The animation gate — before writing any motion code
Run every candidate through references/animation-decision-framework.md's 4 questions,
in order: (1) should this animate at all — frequency decides, never animate
keyboard-initiated or 100+/day actions; (2) what's the one-sentence purpose (spatial
consistency / state indication / explanation / feedback / preventing jarring change); (3)
what easing; (4) what duration. Most "let's animate this" ideas should die at question 1
— that is the point, not a formality to skip.
Materials — transform/opacity first, other properties gated
Default to transform and opacity — they skip layout and paint and run on the GPU.
Animating width/height/top/left/margin/padding triggers layout+paint+composite
and drops frames; see references/motion-performance.md for the Framer Motion shorthand
caveat (x/y/scale shorthands are NOT hardware-accelerated, use the full transform
string), the CSS-var recalc trap (never drive child transforms via a custom property on
the parent), CSS transitions vs. keyframes for interruptible UI, and velocity-based drag
dismissal (~0.11 threshold, not distance alone). Other atmospheric materials — blur,
backdrop-filter, clip-path, shadow bloom, masks — are allowed when they demonstrably read
as premium and stay smooth on the target viewports, verified in-browser, never a default
reach; keep expensive effects bounded to small/isolated areas. references/motion-physics.md
covers physical-correctness rules for whichever material is used: never scale(0),
origin-aware popovers, asymmetric enter/exit timing (exit ~75% of enter duration),
staggered lists (cap total stagger time), blur masking, @starting-style.
What ships with it
19 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.
- references/animation-decision-framework.md 3.8 KB
- references/animation-glossary.md 4.0 KB
- references/entrance-patterns.md 3.0 KB
- references/glassmorphism-advanced-ref.md 2.7 KB
- references/gsap-scroll-skeletons.md 4.1 KB
- references/interactive-states-ref.md 2.8 KB
- references/layered-backgrounds-ref.md 3.0 KB
- references/micro-interactions.md 3.0 KB
- references/motion-patterns.md 2.4 KB
- references/motion-performance.md 3.4 KB
- references/motion-physics.md 4.0 KB
- references/motion-principles.md 3.3 KB
- references/motion-tokens.md 2.3 KB
- references/page-transitions.md 3.1 KB
- references/patterns-buttons.md 2.2 KB
- references/patterns-cards.md 4.9 KB
- references/patterns-microinteractions.md 2.2 KB
- references/patterns-navigation.md 3.1 KB
- references/reduced-motion.md 2.8 KB
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.
- yesterday First seen · 170 lines · 29 tokens per session scan A 84b85eedc8bf
design-motion is a skill published in the GitHub repository fusengine/agents (25 stars, last pushed 1mo ago), licensed MIT. It adds 29 tokens to every session and 2,798 once invoked, about $0.0001 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 2026-09-03.
Other skills, from other repositories
frontend
Two-mode frontend skill: (1) authoring — accessibility, responsive layout, loading/error states, performance, DESIGN.md authoring, visual direction; (2) critique — READ-only scored review of built UI against anchored rubric, AI-slop detection, two isolated assessments. Router invokes mode via context.
stitch-design-system
Extracts a Stitch design and generates production code artifacts — CSS custom properties with dark mode tokens, a Tailwind v4 @theme block, and a semantic design system document. Run this before framework conversion skills.
stitch-a11y
Audits Stitch-generated components for WCAG 2.1 AA accessibility issues and applies fixes — semantic HTML, ARIA attributes, keyboard navigation, focus management, and screen reader support.
stitch-animate
Adds a purposeful animation layer to Stitch-generated components — CSS transitions, Framer Motion (React/Next.js), or Svelte transitions. Always respects prefers-reduced-motion.
design-with-claude
Use when design work needs a product designer's eye: auditing a codebase for design-system gaps, fixing WCAG contrast and unlabeled inputs, choosing type scales or spacing steps, reviewing UI that looks generic or AI-generated, or designing forms, tables, dashboards, navigation, checkout, onboarding, dark mode, and…
mui-styling
Material-UI (MUI) styling standards: sx-prop priority, theme tokens, spacing scale, responsive design, and accessibility. TRIGGER when: styling MUI components, defining theme tokens, or building responsive layouts. SKIP: component logic and hooks (use react-patterns); cross-stack UX/design decisions (use…