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 calesthio/generative-media-skills --skill seedance-2-0git clone --depth 1 https://github.com/calesthio/generative-media-skillsWrote 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/calesthio/generative-media-skills/seedance-2-0)<a href="https://agentmods.dev/skills/calesthio/generative-media-skills/seedance-2-0"><img src="https://agentmods.dev/badge/skills/calesthio/generative-media-skills/seedance-2-0/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/calesthio/generative-media-skills/seedance-2-0"><img src="https://agentmods.dev/badge/skills/calesthio/generative-media-skills/seedance-2-0.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00090 | $0.07763 |
| Opus 5 | $0.00045 | $0.03882 |
| Sonnet 5 | $0.00018 | $0.01553 |
| Haiku 4.5 | $0.00009 | $0.00776 |
Grade A, and why
seedance-2-0 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 9d 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 — 443 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Direct Seedance 2.0 production
Treat this as a provider- and model-family-specific operating guide, not a generic video-prompt recipe. Establish the exact gateway contract before writing a request. “Seedance 2.0” does not imply one portable model ID or schema.
Evidence labels used here:
- Documented — stated in ByteDance/BytePlus or gateway documentation, verified 2026-07-09.
- Production heuristic — a recommended operating practice inferred from documented behavior and normal video-production constraints; validate on the current deployment.
- Independent evidence — third-party measurement or observation with its limits stated.
Decide whether Seedance 2.0 fits
Prefer this family when the shot benefits from one or more of:
- synchronized picture, dialogue, ambience, music, or effects generated in one pass;
- reference images for subject/product/style/layout, a reference video for motion/camera/editing, or reference audio for timbre/rhythm;
- a short self-contained shot, multi-shot beat, edit, or extension lasting 4–15 seconds;
- a first-frame or strict first-and-last-frame transition;
- a multimodal edit in which an element from one asset modifies a different source video.
Choose another workflow, or plan post-production, when the requirement is:
- a single generated clip longer than 15 seconds;
- frame-exact editorial timing, exact choreography, deterministic simulation, or guaranteed seed reproducibility on direct ModelArk;
- exact long-form typography, legal text, captions, UI, pack copy, or a pixel-exact logo;
- direct upload of ordinary real-person face assets to ModelArk without its authorization/trusted-asset process;
- local weights or offline execution;
- direct BytePlus use from the United States: BytePlus's service-specific terms state that its Model Services are not available there. Check gateway and customer-specific availability rather than assuming a third-party route has the same territorial contract.
Do not call Seedance 2.0 “best” in the abstract. ByteDance's published comparisons include internal evaluation, and public leaderboards change. Select it against the shot's references, audio, control, delivery, cost, latency, and compliance needs.
What ships with it
1 file 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.
- 9d ago First seen · 443 lines · 90 tokens per session scan A 2313f610b800
seedance-2-0 is a skill published in the GitHub repository calesthio/generative-media-skills (171 stars, last pushed 2mo ago), licensed MIT. It adds 90 tokens to every session and 7,763 once invoked, about $0.0005 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 2026-09-03.
Other skills, from other repositories
cliptalk-cover-director
Produces evidence-backed cover candidates and reviewable cover variants for a ClipTalk video. Use when the user asks for a cover, poster frame, thumbnail, or multiple cover directions; do not use for timeline editing or social-video reframing.
cliptalk-smart-reframe
Creates a subject-aware, time-varying crop track and a review-only social-format preview from an accepted ClipTalk cut. Use for automatic vertical, square, or portrait reframing; do not use for a fixed manual crop or before content editing is accepted.
cliptalk-content-extractor
Locates and assembles source passages matching a semantic request. Use for extracting explanations, topics, quotes, demonstrations, or other specifically described content.
cliptalk-interview-editor
Produces a coherent interview edit by combining speaker discovery, topic selection, dialogue context, cleanup, subtitles, and preview. Use for interviews, podcasts, testimonials, or question-and-answer recordings.
cliptalk-shortform-hook-director
Finds and assembles a reviewable short-form cut with a strong opening hook. Use for Shorts, Reels, social clips, talking-head cutdowns, or requests for a punchier opening.
cliptalk-social-reframe-exporter
Creates a review-only 9:16, 4:5, 1:1, or 16:9 version from an existing accepted ClipTalk cut, then checks the rendered preview. Use only when a cut already exists and the user asks to adapt it for Shorts, Reels, Douyin, Xiaohongshu, WeChat Channels, or square feeds; do not use when the user still needs content found…