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/jangles-byte/atelier/motionnpx skills add jangles-byte/atelier --skill motiongit clone --depth 1 https://github.com/jangles-byte/atelierWhat 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 | $0.00179 | $0.01104 |
| Opus 5 | $0.00089 | $0.00552 |
| Sonnet 5 | $0.00036 | $0.00221 |
| Haiku 4.5 | $0.00018 | $0.00110 |
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 2d 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 — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Motion
Motion is communication. Every animation answers one of three questions — what just happened? (feedback), where did it go? (orientation), or is this alive? (character). Animation that answers none of them is decoration on a delay; delete it rather than tune it.
The rule that makes this skill different from reading about animation: you cannot judge motion from source code, and you cannot judge it from a still. Run it, capture it, watch it. There is a script here that does exactly that.
Workflow
- Name the question. Feedback, orientation, or character — and what the motion
temperament is (snappy or viscous, calm or nervous). One line is enough. If the project
has a design philosophy from
design-direction, take the temperament from there. - Start from a recipe, not from scratch. Find the pattern in the recipe files below; they carry tuned values, per-stack code, reduced-motion variants, and the failure mode for each. Adapt the values to your temperament rather than inventing timings.
- Implement with curves and springs from references/easing-and-springs.md.
- Watch it. Capture the running animation and look at the result:
It records real composited frames over the DevTools protocol, so it works for CSS, Web Animations, GSAP/Framer, canvas, and WebGL alike. For native or engine work, use the platform's own capture (simulator recording, engine profiler playback)../scripts/capture-motion.py index.html --out motion.gif \ --trigger "document.querySelector('#open').click()" --duration 1200 - Diagnose if it underwhelms — work references/dead-motion-diagnostic.md in order before touching values, then re-capture. The first render of a fix is a hypothesis.
- Check the frame cost with the
performance-craftskill, and confirm the reduced-motion path is complete and calm — not merely disabled.
What ships with it
7 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.
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.
- 2d ago First seen · 67 lines · 0 tokens per session scan A ea0c371d9ba7
motion is a skill published in the GitHub repository jangles-byte/atelier (2 stars, last pushed 1mo ago), licensed MIT. It adds 179 tokens to every session and 1,104 once invoked, about $0.0009 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
sheleg-design
Use when deciding how something LOOKS or MOVES — cinematic landing pages and hero sections, particle/WebGL backgrounds, scroll-linked or scrubbed motion, layers that drift, dashboards, admin or internal tools, mobile screens, chat or agent interfaces, tokens, themes, palettes, typography and the Figma border. Triggers…
apply-color-theory-principles
Use when making deliberate color decisions in painting, design, or illustration to create harmony, contrast, mood, and visual hierarchy.
design-color-palette
Use when creating a cohesive, purposeful color palette for a brand, illustration, UI, or fine-art project.
animation-at-work
Apply web animation principles from Animation at Work by Rachel Nabors. Covers human perception of motion, 12 principles of animation, animation patterns (transitions, supplements, feedback, demonstrations, decorations), CSS transitions, CSS animations, Web Animations API, SVG/Canvas/WebGL, communicating animation…
modern-frontend-design
How to design and build modern, premium-quality frontend interfaces that look like high-end SaaS products, modern AI tools, and award-winning design websites — not generic templates. Use this skill whenever the user asks to build a frontend, create a landing page, design a dashboard, scaffold a web app UI, build a…
html-ppt-zhangzara-biennale-yellow
A curatorial deck for a contemporary art biennale — the thesis, the rooms, the works, and the visitor journey. Built as a decision-grade design craft deck for museum board, curators.