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 fusengine/agents --skill motion-craftgit 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/motion-craft)<a href="https://agentmods.dev/skills/fusengine/agents/motion-craft"><img src="https://agentmods.dev/badge/skills/fusengine/agents/motion-craft/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/fusengine/agents/motion-craft"><img src="https://agentmods.dev/badge/skills/fusengine/agents/motion-craft.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 | $0.00164 | $0.02585 |
| Opus 5.5 | $0.00066 | $0.01034 |
| Sonnet 5.5 | $0.00033 | $0.00517 |
| Haiku 4.5 | $0.00016 | $0.00259 |
Grade A, and why
motion-craft 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 — 117 lines — stays where its author put it; the contents beside it link to each section on GitHub.
It does not own UI motion tokens: easing curves and the glossary live in fuse-design:design-motion and are pointed to, never copied. UI micro-durations from that skill (100-500 ms) do not apply to film read time. And readable never means frozen: a purposeful gesture is in progress at every moment — no span over 0.75 s without one, the final CTA still ≤ 1.2 s — and nothing "drifts" to fake life; a long read becomes more beats.
Motion Craft
Agent Workflow (MANDATORY)
| Step | Who | What |
|---|---|---|
| Before choosing curves | read fuse-design:design-motion → motion-tokens.md |
Reuse the named easing tokens |
| Naming an effect | animation-glossary.md | Exact term in beats and handoff |
| Building a scene | motion-art-direction templates first: composition-grid, kinetic-type, cut-rhythm |
Grid, entrances and cut times that already enforce these rules |
| Draft review | motion-critic via motion-review |
Scores these rules with frame refs |
| Scripts | fuse-ai-pilot:sniper |
Code validation after scene/render edits |
Overview
| Area | Core rule | Reference |
|---|---|---|
| Focus | One primary gesture at a time, smaller details (rules, underlines, counters) may move with it; frame 0 at full value; behaviours rotate, never opacity-only | focus-hierarchy.md |
| Timing & density | Gesture in progress at every moment: ≤ 0.75 s gesture-free, CTA still ≤ 1.2 s, beats every 0.5-1 s, ≥ 1 onset/s; ≥ 0.25 s per word on screen; long copy → more beats; no drift | timing-holds.md |
| Continuous take | Cut-based edit or one continuous object (morph, cursor, content swap); no opacity blend; one curve; loops with matched velocity | continuous-take.md |
| Easing | No linear motion; springs ζ ≥ 0.85, overshoot ≤ 3 %, one swing at most; springSum; dual-edge squash/stretch | easing-springs.md |
| Color & type | Ink / paper / one accent (OKLCH); area-weighted contrast ≥60 L; a ≥50 % dark/accent plane on 1 beat in 3; no neutral mid-tones; TYPE_SCALE ≥4; never centered | color-type-video.md |
| Anti-slop | Single-source ban list, each absolute ban mapped to a hard-fail ID; no look.md exception |
anti-slop-video.md |
What ships with it
6 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 First seen · 117 lines · 164 tokens per session scan A 0e28d299033a
motion-craft is a skill published in the GitHub repository fusengine/agents (31 stars, last pushed 3d ago), licensed MIT. It adds 164 tokens to every session and 2,585 once invoked, about $0.0007 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
designing-interfaces
Creates a design system for software with a UI. Use when a project has a user interface and architecture is confirmed — whether creating from scratch or extracting patterns from existing code.
evaluate
Run accessibility checks and discover issues mapped to WCAG criteria.
visual
Define visual identity — colors, typography, logo usage, and imagery style.
report
Generate a structured accessibility audit report with remediation guidance.
guidelines
Package all brand elements into a complete brand guidelines document.
ux
Review work through the lens of a UX/UI expert.