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 sideshowroberto/vfx-agent-toolkit --skill seedance-promptgit clone --depth 1 https://github.com/sideshowroberto/vfx-agent-toolkitWrote 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/sideshowroberto/vfx-agent-toolkit/seedance-prompt)<a href="https://agentmods.dev/skills/sideshowroberto/vfx-agent-toolkit/seedance-prompt"><img src="https://agentmods.dev/badge/skills/sideshowroberto/vfx-agent-toolkit/seedance-prompt/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/sideshowroberto/vfx-agent-toolkit/seedance-prompt"><img src="https://agentmods.dev/badge/skills/sideshowroberto/vfx-agent-toolkit/seedance-prompt.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 | $0.00068 | $0.01576 |
| Opus 5.5 | $0.00027 | $0.00630 |
| Sonnet 5.5 | $0.00014 | $0.00315 |
| Haiku 4.5 | $0.00007 | $0.00158 |
Grade A, and why
seedance-prompt 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 today.
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 — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.
seedance-prompt
Reference resolution: [ref:<name>] resolves to ../seedance-20/references/<name>.md (the seedance-20 skill's vendored reference corpus); [skill:<name>] is the sibling skill of that name.
Build production-ready Seedance prompts from clear concepts or supplied reference assets. Treat the prompt as a short shooting brief: it must say what changes on screen, what the camera does, what the light and sound contribute, and what must stay stable. Keep final prompts under the platform prompt budget and remove filler before delivery.
Load [ref:quick-ref] for the checklist, [ref:reference-workflow] for multimodal references, [ref:i2v-guide] for image-to-video, [ref:first-last-frame-guide] for first/last-frame work, [ref:examples-by-mode] when examples are useful, [ref:shot-list-continuity] for multi-shot professional plans, and [ref:multilingual-community-examples] for Chinese/Russian/Japanese/Korean/Spanish or mixed-language prompts.
Director Formula
Use Subject + Action + Scene + Camera + Lighting/Style + Audio + Constraints. Put the subject and primary action first because early clauses set the shot hierarchy. Do not force every slot if a reference asset already shows the information; for I2V, describe only the motion, camera, timing, transformation, audio, and preservation constraints that the still image cannot show.
| Slot | Use for | Prompt-ready pattern |
|---|---|---|
| Subject | The anchor the model must track. | Original ceramic perfume bottle on black acrylic, label preserved exactly |
| Action | The visible change. | condensation beads form and slide down the glass over five seconds |
| Scene | Only what is not already in references. | quiet rain-lit kitchen counter, shallow depth of field |
| Camera | One primary move with endpoint. | slow dolly-in from medium product shot to macro label detail |
| Light and style | Physical light plus safe visual language. | warm practical key from frame left, cool blue rim, clean commercial realism |
| Audio | Ambient bed, SFX, dialogue, or silence. | Sound: low room tone, soft glass chime on final frame |
| Constraints | Preservation and exclusions. | do not alter logo, shape, label, or cap geometry |
| Timing | Shot sequencing or time structure. | 0-2s steady; 2-4s door opens, flame bends; 4-5s smoke curls toward hallway |
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.
- today First seen · 83 lines · 68 tokens per session scan A 9086a0e58442
seedance-prompt is a skill published in the GitHub repository sideshowroberto/vfx-agent-toolkit (16 stars, last pushed 22d ago), licensed MIT. It adds 68 tokens to every session and 1,576 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 2026-11-02.
Other skills, from other repositories
seedance-prompt
This skill should be used when the user asks to write, improve, translate, compress, or debug a Seedance 2.0 video prompt; mentions T2V, I2V, V2V, R2V, camera direction, prompt quality, or provides reference assets for a production-ready prompt.
seedance-prompt
This skill should be used when the user asks to write, improve, translate, compress, or debug a Seedance 2.0 video prompt; mentions T2V, I2V, V2V, R2V, camera direction, prompt quality, or provides reference assets for a production-ready prompt.
seedance-prompt
This skill should be used when the user asks to write, improve, translate, compress, or debug a Seedance 2.x video prompt; mentions T2V, I2V, V2V, R2V, camera direction, prompt quality, or provides reference assets for a production-ready prompt. Model profile, duration, request fields, and reference tokens must come…
dcc-diagnostics
Infrastructure skill — DCC-agnostic observability primitives: capture screenshots, query audit logs, inspect tool performance metrics, and monitor process health. Works in any DCC environment (Maya, Blender, Houdini, Unreal, etc.) or standalone Python. Use for debugging any skill failure or verifying DCC state. Not…
de-vibe
Audit and fix the tells that software was vibe-coded / AI-generated, then give it a small distinctive identity, so it ships looking handcrafted and professional. Use whenever the user says "de-vibe", "does this look AI-generated / vibe coded?", "make this look shippable / handcrafted / professional", "remove the AI…
qt-ui-inspector
Infrastructure skill — DCC-agnostic Qt UI introspection: list top-level windows, find widgets by name/class, describe widget properties, walk the widget tree, and poll for availability. Works in any DCC with a Qt binding (Maya, Blender, Houdini, Unreal, etc.). All tools are read-only and lazy-loaded.