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 60fps-Design/plugin --skill motion-specgit clone --depth 1 https://github.com/60fps-Design/pluginWrote 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/60fps-design/plugin/motion-spec)<a href="https://agentmods.dev/skills/60fps-design/plugin/motion-spec"><img src="https://agentmods.dev/badge/skills/60fps-design/plugin/motion-spec/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/60fps-design/plugin/motion-spec"><img src="https://agentmods.dev/badge/skills/60fps-design/plugin/motion-spec.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 | $0.00086 | $0.01587 |
| Opus 5.5 | $0.00034 | $0.00635 |
| Sonnet 5.5 | $0.00017 | $0.00317 |
| Haiku 4.5 | $0.00009 | $0.00159 |
Grade A, and why
motion-spec 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.
How it starts
The opening of the file, as written. The whole thing — 115 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Motion spec
A designer can point at a clip and say "like this". A developer needs numbers, order and edge cases. Your job is to turn one 60fps shot into a spec they can build from without guessing, and to be honest about which numbers are measured and which are judgement.
1. Find the shot
If the user gave a 60fps link or slug, use it. If they described it, call 60fps_search_shots. Go
ahead with the top result when its summary clearly matches what they asked for. Stop and ask only
when it does not, or when the top results are close and differ in a way that matters: then show the
top three with one line each on how they differ.
If the shot holds several interactions (open, pick, confirm, a hint after), ask which one to spec, or spec each as its own numbered part.
Each breakdown and code call counts against the user's daily allowance, so do not fetch details for shots you are only comparing.
2. Read it
Call 60fps_get_motion_breakdown for the trigger, the start, transition and end states, why it
works, the timing words (slow, medium, fast), easing, springiness, stagger, and the keyframe images.
Look at the keyframes: they show the order of events and rough sizes, and they are a check on the
code.
Call 60fps_get_motion_code for the numbers, and check its source:
generated: thegeneratedfield is a compile-checked recreation of this shot. Take every measured number from it. Ignore the response'sanimation,recipesandstagger_delayfields: those are generic starter values, and they disagree with the real timing.recipes: there is no recreation of this shot, so nothing can be measured. The response'sanimationandstagger_delayare the tool's generic reading of the breakdown's timing words. You may use them, but only as suggestions under Recommendations.
Read the timing lines: withAnimation and .animation values, spring parameters, delays and
sleeps, phaseAnimator or keyframeAnimator tracks, haptic calls, and how it handles Reduce Motion
and interruption. A value is real only if a view actually reads it: a keyframe track or a state
variable nothing uses animates nothing, so leave it out of the spec and list it under Code caveats.
Check that each line does what its comment says.
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 · 115 lines · 86 tokens per session scan A bf77354d71e1
motion-spec is a skill published in the GitHub repository 60fps-Design/plugin (1 stars, last pushed 9d ago), licensed MIT. It adds 86 tokens to every session and 1,587 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-10-13.
Other skills, from other repositories
add-component
Add a SwiftUI component from ShipSwift. Use when the user says "add component", "add a view", "add X view", "I need a chart", "add animation", or wants a specific UI element.
figma-a11y-annotations
Rules for generating accessibility annotations on iOS/iPadOS mobile designs in Figma. Enforces a bare-minimum annotation discipline, an iOS vocabulary instead of web ARIA terms, and exact grammar for names, control types, page titles, values, hints, headings, groups, and reading order. Never annotates visible text as…
iOS SwiftUI Accessibility
Enforces WCAG 2.2 accessible coding patterns when writing SwiftUI — labels, traits, Dynamic Type, contrast, touch targets, focus management, orientation, and more. Based on the ios-swiftui-accessibility-techniques project with 41 static analysis rules across 24 WCAG criteria.
liquid-glass
Implement, migrate, review, and diagnose iOS Liquid Glass interfaces in SwiftUI and UIKit. Use for system chrome, custom glass effects, transitions, accessibility, and version-specific issues in native iOS apps.
ttb-skill-native-swiftui-components
Build reusable native SwiftUI UI components using 100% standard SwiftUI primitives with TTBaseUIKit design tokens, localization, chainable modifiers, and project architecture rules. NO TTBaseSUI wrappers. iOS 14+.
apple-design
Complete Apple Human Interface Guidelines (HIG) and Apple Design System standard. Use when designing, building, or auditing UI/UX for iOS, iPadOS, macOS, watchOS, visionOS, or Apple-styled web and mobile applications.