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.
git 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/commands/fusengine/agents/motion)<a href="https://agentmods.dev/commands/fusengine/agents/motion"><img src="https://agentmods.dev/badge/commands/fusengine/agents/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/commands/fusengine/agents/motion"><img src="https://agentmods.dev/badge/commands/fusengine/agents/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 | $0.00077 | $0.00897 |
| Opus 5.5 | $0.00031 | $0.00359 |
| Sonnet 5.5 | $0.00015 | $0.00179 |
| Haiku 4.5 | $0.00008 | $0.00090 |
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 — 40 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/motion — Product Film Pipeline
Spawn the motion-expert agent with the brief below. It routes every step to its owning skill and STOPS at the owner's art-direction step (G0), stills gate (G1) and draft gate (G2).
Complete documentation: skills/motion-method/SKILL.md
Usage
/motion 20 s launch clip for the new statusline, Linear-launch style, 16:9 mp4 + README GIF
/motion 9:16 social cut showing the review queue, one accent, under 8 MB
/motion terminal demo of the install command, GIF for the README
/motion 15 s Reels ad for the review queue, genre ad, one CTA
Missing brief fields (genre ad|demo, audience, one-sentence message, named reference style, surfaces + byte budgets, duration, aspect, accent, sensitive-data list) → the agent asks ONE question first.
Workflow
skills/motion-method/SKILL.md— lock.motion/brief.md(genre: ad→references/ad-genre.md, you confirm the message), write the beat map (DURATION = sum of beats; a gesture on every beat of the grid — no span over 0.75 s without one, the final CTA still ≤ 1.2 s).skills/motion-art-direction/SKILL.md— G0: 3 text sketches (tone candidates) → challenger locks the tone blind → reference board →.motion/look.md(dials) + 3 key frames → you see the key frames → STOP (G0). No.motion/scene/*file is written before you approve.skills/motion-assets/SKILL.md— real screenshots, masked, "Example data" label,.motion/assets.json.- Scene:
motion-art-directiontemplates first (cut-rhythm→composition-grid→kinetic-type→objects.md), built againstlook.md;skills/motion-render/SKILL.mdsupplies only thewindow.seek(t)/ capture / encode mechanics. bun .motion/render.js --stage stills→ one still per beat on a contact sheet → STOP (G1), owner approves.--stage draft→motion-criticviaskills/motion-review/SKILL.md(≤2 fix rounds) → STOP (G2), owner approves.--stage master→ ffprobe, frame count, size vs budget, frames diffed vs approved stills; sniper on scripts, challenger on "done".
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 · 40 lines · 77 tokens per session scan A dab82f648736
motion is a command published in the GitHub repository fusengine/agents (31 stars, last pushed 3d ago), licensed MIT. It adds 77 tokens to every session and 897 once invoked, about $0.0003 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 commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.
speckit.bug.fix
Apply the remediation from a bug assessment and record what was changed.