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 Sagargupta16/claude-skills --skill motiongit clone --depth 1 https://github.com/Sagargupta16/claude-skillsWrote 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/sagargupta16/claude-skills/motion)<a href="https://agentmods.dev/skills/sagargupta16/claude-skills/motion"><img src="https://agentmods.dev/badge/skills/sagargupta16/claude-skills/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/sagargupta16/claude-skills/motion"><img src="https://agentmods.dev/badge/skills/sagargupta16/claude-skills/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 | $0.00081 | $0.00643 |
| Opus 5 | $0.00041 | $0.00321 |
| Sonnet 5 | $0.00016 | $0.00129 |
| Haiku 4.5 | $0.00008 | $0.00064 |
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 3d 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 — 37 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Motion
One skill, three modes. Pick by intent; load only the matching reference file.
| Mode | When | Reference |
|---|---|---|
audit |
Review existing animation code for quality -- outputs file:line findings against the 12 principles |
references/audit-12-principles.md |
add |
Enhance a feature with new animations, micro-interactions, motion design | references/add-motion.md |
fix |
Animations stutter, transitions jank, perf review of CSS/JS motion | references/fix-performance.md |
Invocation: /motion audit <files>, /motion add [target], /motion fix [file]. Bare /motion fix applies the performance constraints to all UI animation work in this conversation. If no mode is given, infer from the ask (review/check -> audit; add/enhance -> add; jank/slow/stutter -> fix).
Mode boundaries (the numbers differ by design)
Each mode's numeric rules apply only within that mode -- they intentionally disagree:
- Stagger: audit enforces <=50ms per item on existing code; add recommends 100-150ms delays for page-load choreography. When adding motion that must later pass an audit, prefer the audit cap.
- Feedback duration: audit fails user-initiated animations over 300ms; add allows 300-500ms for layout changes. Audit numbers win for interaction feedback.
- Springs vs easing: audit prescribes springs for overshoot-and-settle; add bans bounce/elastic easing curves. Both are right: springs yes, bounce/elastic cubic-beziers no.
Hard rules (all modes)
- transform + opacity only for motion; never animate layout properties (width, height, top, left)
will-changesparingly and temporarily, never permanent- Never migrate or rewrite animation libraries unless explicitly requested
- Respect the project's stated motion policy: if the user or project rules say animations should stay bold and visible, do not add
prefers-reduced-motionguards or tone motion down; if they require accessibility-first motion, do the opposite. Ask if no policy is stated and the change is significant.
What ships with it
3 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.
- 3d ago Changed · -1 lines 23671b66d692
- 10d ago First seen · 38 lines · 81 tokens per session scan A 6287b387c15f
motion is a skill published in the GitHub repository Sagargupta16/claude-skills (5 stars, last pushed 4d ago), licensed MIT. It adds 81 tokens to every session and 643 once invoked, about $0.0004 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
use
Reach Anthropic's first-party playground capability in one step: verify the upstream playground plugin is installed, invoke its skill for interactive single-file HTML explorers (controls beside a live preview, output is a prompt you paste back), or emit the exact install commands when it is absent. Use when: 'make me…
ux-interaction-patterns
UX laws as code — micro-interactions, animation choreography, skeleton UIs, optimistic UI, and performance UX patterns for world-class user experience.
modern-css-patterns
Production-ready modern CSS features — container queries, :has(), subgrid, scroll-driven animations, View Transitions, anchor positioning, and cascade layers.
create-design-system
You are an expert design systems architect.
css-coding-standards
CSS coding standards for systemprompt.io — one --sp- token system in OKLCH with color-mix derivation, BEM naming, one component per file, CSS-first behaviour, forbidden constructs, comment rules, and file limits. Canonical source of truth for all CSS. Load before writing or reviewing any stylesheet.
frontend-coding-standards
Front-end entry point for systemprompt.io — HTML standards, progressive enhancement doctrine, asset registration, and performance requirements. Routes to javascript-coding-standards and css-coding-standards, which are canonical for their languages.