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-rendergit 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-render)<a href="https://agentmods.dev/skills/fusengine/agents/motion-render"><img src="https://agentmods.dev/badge/skills/fusengine/agents/motion-render/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-render"><img src="https://agentmods.dev/badge/skills/fusengine/agents/motion-render.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 | $0.00107 | $0.02628 |
| Opus 5.5 | $0.00043 | $0.01051 |
| Sonnet 5.5 | $0.00021 | $0.00526 |
| Haiku 4.5 | $0.00011 | $0.00263 |
Grade A, and why
motion-render 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 — 155 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Terminal subjects use VHS tapes; sound, when the brief asks for it, follows the audio
reference. Templates are generalized from the proven docs/demo/statusline-mod/ and
docs/demo/hook-sniper.tape pipelines and were run end to end before shipping.
Motion Render
Agent Workflow (MANDATORY)
- Read the locked inputs:
.motion/brief.md(surfaces, byte budgets, aspect, duration) and.motion/beats.md— if either is missing, go back tomotion-method. - Check tools:
ffmpeg -version,ffprobe -version,bun --version, a Chrome binary (orCHROME_BIN);vhs --version+ttydfor terminal films. Missing tool → say so, never fake a render. - Scaffold the scene:
motion-art-directiontemplates FIRST — composition-grid (layout), kinetic-type (word behaviours), cut-rhythm (beat map) — only afterlook.mdand the key frames exist. This skill then adds the mechanics: the shell, theseekclock, capture and encode (never hand-roll a capture). - Render
stills→ STOP at G1.draft→motion-critic→ STOP at G2.master→ verify the FILE. The harnessmotionscope denies draft/master until the owner typesMOTION-APPROVE— stop at each gate anyway, never lean on the deny. - Hand off: lead runs
fuse-ai-pilot:sniperon the scripts and the challenger on the "done" claim.
What ships with it
15 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.
- references/audio.md 9.6 KB
- references/delivery-github.md 3.1 KB
- references/determinism.md 6.5 KB
- references/encoding.md 5.8 KB
- references/seek-contract.md 6.5 KB
- references/stages-budgets.md 6.0 KB
- references/templates/capture-cdp.md 9.4 KB
- references/templates/index-skeleton.md 9.1 KB
- references/templates/interaction-kit.md 8.7 KB
- references/templates/render-cli.md 17 KB
- references/templates/timeline-seek.md 27 KB
- references/templates/vhs-tape.md 4.0 KB
- references/templates/webgl-scene.md 7.9 KB
- references/verification.md 4.4 KB
- references/vhs-terminal.md 3.4 KB
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 · 155 lines · 107 tokens per session scan A 1934f0ca4954
motion-render is a skill published in the GitHub repository fusengine/agents (31 stars, last pushed 3d ago), licensed MIT. It adds 107 tokens to every session and 2,628 once invoked, about $0.0004 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.