Borrowing it
Nothing to install: this file belongs to Lengros/bennu. 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/Lengros/bennu/main/.claude/skills/motion/SKILL.mdgit clone --depth 1 https://github.com/Lengros/bennuWrote 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/lengros/bennu/motion)<a href="https://agentmods.dev/skills/lengros/bennu/motion"><img src="https://agentmods.dev/badge/skills/lengros/bennu/motion/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/lengros/bennu/motion"><img src="https://agentmods.dev/badge/skills/lengros/bennu/motion.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 | $0.00227 | $0.04486 |
| Opus 5.5 | $0.00091 | $0.01794 |
| Sonnet 5.5 | $0.00045 | $0.00897 |
| Haiku 4.5 | $0.00023 | $0.00449 |
Grade A, and why
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 2mo 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 — 387 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/motion — how UI should move
This skill owns the layer none of the other design skills cover: how an element should
move once it's on screen. /design commits a static look, /prototype wires a clickable
flow, /diagram draws structure — none of them tell you whether a dropdown should use
ease-out or a custom curve, how long a drawer should take, or why an entrance from
scale(0) looks broken. That motion-craft gap is what this fills.
Core principle: Good motion is mostly subtraction and exact values, not flourish. The agent's default failure isn't "too little animation" — it's animating the wrong things, with weak built-in easings, wrong durations, and wrong origins. The aggregate of small invisible correctness (right easing, right timing, right origin, interruptible, GPU-only) is what makes an interface feel expensive. The catalog below is that aggregate.
Attribution. Adapted from Emil Kowalski's design-engineering philosophy (animations.dev) — ex-Vercel/Linear, author of Sonner and Vaul. Ported into Bennu 2026-06-20.
Scope in Bennu — which advice applies where:
/prototype(vanilla, no framework): the CSS sections apply directly — custom easing variables,transitionvs@keyframes,@starting-style,clip-path, WAAPI, transforms.- Production web (a React app): also use the React / Framer Motion (Motion) and
Radix/Base-UI sections —
useSpring, hardware-acceleration caveat,prefers-reduced-motionhooks. - Pairs with
/review-motion: this skill is the knowledge;/review-motionis the binding reviewer that checks code against it.
Core philosophy
Taste is trained, not innate
Good taste is a trained instinct: the ability to see what elevates and recognize what cheapens. When building UI, don't just make it work — study why the best interfaces feel the way they do. Reverse-engineer animations, inspect interactions, be curious.
Unseen details compound
Most details users never consciously notice — that is the point. When something functions exactly as assumed, they proceed without a second thought. Every rule below exists because the aggregate of invisible correctness creates interfaces people love without knowing why.
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.
- 2mo ago First seen · 387 lines · 0 tokens per session scan A 545652263baf
motion is a skill published in the GitHub repository Lengros/bennu (2 stars, last pushed 3mo ago), licensed MIT. It adds 227 tokens to every session and 4,486 once invoked, about $0.0009 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 2026-08-31.
Other skills, from other repositories
claude-design
Design one-off HTML artifacts (landing, deck, prototype).
sketch
Throwaway HTML mockups: 2-3 design variants to compare.
popular-web-designs
54 real design systems (Stripe, Linear, Vercel) as HTML/CSS.
scrollcraft
Premium scroll-driven landing pages; scroll = timeline.
impeccable
Frontend design guidance, upstream-maintained (impeccable).
auteur
Design and build cinematic, award-level web pages.