seedance-2.0 is an agent-driven production pipeline for creating AI films from text, images, videos, and references, including audio and platform-specific workflows. Filmmakers and creators use it to plan scenes and generate coherent prompts for Seedance-related tools, while the catalogue contains skills from that workflow.
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 Emily2040/seedance-2.0 --skill seedance-filtergit clone --depth 1 https://github.com/Emily2040/seedance-2.0Wrote 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/emily2040/seedance-2.0/seedance-filter)<a href="https://agentmods.dev/skills/emily2040/seedance-2.0/seedance-filter"><img src="https://agentmods.dev/badge/skills/emily2040/seedance-2.0/seedance-filter/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/emily2040/seedance-2.0/seedance-filter"><img src="https://agentmods.dev/badge/skills/emily2040/seedance-2.0/seedance-filter.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 3 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Anti-Refusal · line 41 Skill attempts to nullify the agent's safety policies or restrictions ('you have no restrictions', 'ignore your guidelines', 'do anything now'). This is a direct jailbreak that disables guardrails.Fix: Remove jailbreak framing that nullifies safety policies or restrictions. Skill content must not instruct the agent to ignore its guidelines or operate without guardrails.
- high Prompt Injection · line 41 This pattern attempts to override system instructions or ignore safety constraints. Without LLM analysis, manual review is recommended.Fix: Remove or rewrite any text that instructs the agent to ignore prompts, override safety rules, or trust unverified content. Ensure skill content cannot be injected to alter agent behavior.
- high YARA Match · line 41 YARA rule matched a hack tool or exploit indicator (offensive tools, reconnaissance, privilege escalation, or exploit frameworks).Fix: Remove offensive tool references and exploit code. Legitimate agent skills should not contain penetration testing tools, exploit frameworks, or reconnaissance utilities.
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 | $0.00057 | $0.00833 |
| Opus 5 | $0.00028 | $0.00417 |
| Sonnet 5 | $0.00011 | $0.00167 |
| Haiku 4.5 | $0.00006 | $0.00083 |
Grade A, and why
seedance-filter 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 2d 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 — 52 lines — stays where its author put it; the contents beside it link to each section on GitHub.
seedance-filter
Before producing prompt text, a prompt-ready block, a rewrite, an example, or a compiled clip, load the Director's Read, classify the brief, and complete its canonical narrative or non-narrative record. Translate that record into visible or audible carriers and keep its internal labels out of final generation prose.
Intent
Assess the actual scene and available rejection information before proposing a rewrite. Keep legitimate creative intent clear without assuming that every rejection is a false positive or every output defect is moderation.
Boundary — read before anything else
This skill clarifies benign requests; it does not disguise prohibited content or help bypass safety systems. Evaluate the underlying request and relevant context, including age, consent, identity, rights and harm. Do not invent those facts or infer a content violation from a topic word alone. If the underlying request is prohibited, refuse plainly and offer a legitimate alternative only where one exists.
Repair Method
- Identify the requested scene, its must-haves and the actual error or rejection information available. Separate the provider's stated reason, the user's report and an unverified hypothesis. Leave the cause unknown when the evidence does not establish it.
- Assess the underlying content. Ask only for missing context that materially affects the boundary or requested output; do not turn a complete benign brief into another interview.
- For an ambiguous phrase with a known benign meaning, clarify that meaning faithfully. Preserve exact dialogue, reference tokens, authorized roles, sound, framing and settings unless their revision was requested.
- If a proposal removes or replaces content, describe that change and offer it as an alternative, or draft within the user's already delegated scope. Do not label a different scene an equivalent wording repair or claim that adding “prop”, “original” or “authorized” establishes those facts.
- Do not promise acceptance or submit repeated synonym probes. A text revision is not authorization for an upload, retry, provider change or spending. Follow the user's budget and retake protocol.
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.
- 2d ago Changed · -15 lines · +8 tokens per session 55e365bfdea7
- 11d ago First seen · 67 lines · 49 tokens per session scan A 343d3d47d12c
seedance-filter is a skill published in the GitHub repository Emily2040/seedance-2.0 (7,260 stars, last pushed 3d ago), licensed MIT. It adds 57 tokens to every session and 833 once invoked, about $0.0003 per session on Opus 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 2026-08-30.
Other skills, from other repositories
seedance-filter
This skill should be used when a Seedance 2.0 prompt is blocked, rejected, silently degraded, or likely to trigger a content filter; or when the user asks for a safer rewrite without losing the creative intent.
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-examples-ja
This skill should be used when the user asks for Japanese Seedance 2.0 examples, Japanese prompt patterns, example rewrites, or safe versions of working Japanese video-generation prompts.
seedance-prompt-short
This skill should be used when the user asks for a compact Seedance 2.0 prompt, short Chinese prompt, prompt compression, 30-100 word output, or removal of unnecessary prompt language.
seedance-examples-zh
This skill should be used when the user asks for Chinese Seedance 2.0 examples, Chinese prompt patterns, example rewrites, or safe versions of working Chinese video-generation prompts.
seedance-vocab-en
This skill should be used when an English Seedance 2.0 prompt is slop-heavy, generic, padded with empty quality words, tripping false-positive filters, or needs precise English production vocabulary for camera, lighting, motion, VFX, audio, and constraints.