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-methodgit 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-method)<a href="https://agentmods.dev/skills/fusengine/agents/motion-method"><img src="https://agentmods.dev/badge/skills/fusengine/agents/motion-method/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-method"><img src="https://agentmods.dev/badge/skills/fusengine/agents/motion-method.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 | $0.00115 | $0.02884 |
| Opus 5.5 | $0.00046 | $0.01154 |
| Sonnet 5.5 | $0.00023 | $0.00577 |
| Haiku 4.5 | $0.00012 | $0.00288 |
Grade A, and why
motion-method 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 — 133 lines — stays where its author put it; the contents beside it link to each section on GitHub.
The other skills point here for order and gates: motion-art-direction locks the visual system before any scene code, motion-craft decides how each beat looks and moves, motion-assets supplies the real screenshots, motion-render produces the frames and files, motion-review judges them. This skill decides WHEN each of them runs and WHEN to stop.
Gates G1 (stills → draft) and G2 (draft → master) are owner approvals. They are enforced by the harness motion scope (hooks/hooks.json) and specified in references/stage-gates.md: draft and master renders are denied until the owner types MOTION-APPROVE stills|draft <code>. The agent still stops at each gate on its own. G0 (board + look.md, before scene code) is an owner step, not a harness gate: the agent stops and waits, never self-approves.
Motion Method
Agent Workflow (MANDATORY)
| Step | Who | What |
|---|---|---|
| Before the brief | fuse-ai-pilot:explore-codebase |
Find the product's real tokens, screens, copy, existing .motion/ state |
| Named style unknown | fuse-ai-pilot:research-expert |
Verify what the named reference style actually looks like (no guessing) |
| G0 tone | fuse-ai-pilot:challenger |
Blind-locks one of 3 text tone sketches (motion-art-direction) |
| Draft rendered | motion-critic |
One review pass per round via motion-review; at most 2 fix rounds |
| Scripts written | fuse-ai-pilot:sniper |
Validate scene/render scripts (code only) |
| Before "done" | fuse-ai-pilot:challenger |
Challenge the "master verified" claim |
Overview
| Stage | Output | Stop? |
|---|---|---|
| 1 Brief lock | .motion/brief.md — genre: ad or demo, <inputs> (with defaults), <direction>, <structure>, <build>, <gotchas>, <start> |
Ask ONE question if an input has no default; genre: ad → owner confirms the message |
| 2 Beat map | .motion/beats.md — one row per beat (0.5-1 s), its primary gesture, details, words, 3D reason; DURATION = sum of beats; ≤ 0.75 s gesture-free, CTA still ≤ 1.2 s, ≥ 1 beat change/s; key action on the drop |
— |
| 2b G0 art direction | brief → 3 text sketches (tone candidates) → fuse-ai-pilot:challenger locks the tone blind → reference board → .motion/look.md (dials) + 3 key frames → owner sees the key frames → scene code (motion-art-direction) |
STOP — G0, owner approves; never self-approve |
| 3 Assets | real screenshots + .motion/assets.json (see motion-assets) |
— |
| 4 Scene | Built from the motion-art-direction templates first — cut-rhythm, composition-grid, kinetic-type, objects.md — then motion-render for seek/capture/encode only (window.seek(t) / DURATION / FPS, ?t= and ?capture) |
— |
5 --stage stills (default) |
one still per beat + contact sheet | STOP — G1 |
6 --stage draft (540p) |
draft mp4 → motion-critic (≤2 fix rounds) |
STOP — G2 |
7 --stage master |
master file, verified with ffprobe + frame diff vs approved stills | — |
| 8 Validate | sniper on scripts, challenger on the "done" claim | — |
What ships with it
8 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 · 133 lines · 115 tokens per session scan A 6ea6930e7786
motion-method is a skill published in the GitHub repository fusengine/agents (31 stars, last pushed 3d ago), licensed MIT. It adds 115 tokens to every session and 2,884 once invoked, about $0.0005 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
radin-record
Log bugs, follow-ups, ideas or feedback raised this session as backlog entries that outlive the conversation. Use for /radin-record or any ask to save something for later, even a vague one ("add the findings"): scan the whole session.
radin-doctor
Check that radin's install under /.claude is complete and its companion tools are reachable.
radin-do
Record one ad-hoc prompt as a backlog entry, then execute just that task. Use for /radin-do .
radin-stats
Show the stats/gain output of every companion tool that ships one, side by side.
radin-batch
Work backlog tasks via sub-agents, prioritized, one commit each; asks whether to plan each task first. Use for "work through my backlog", "skip planning", or name an epic or task to run only those.
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.