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 anymouschina/TapCanvas --skill seedance-25git clone --depth 1 https://github.com/anymouschina/TapCanvasWrote 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/anymouschina/tapcanvas/seedance-25)<a href="https://agentmods.dev/skills/anymouschina/tapcanvas/seedance-25"><img src="https://agentmods.dev/badge/skills/anymouschina/tapcanvas/seedance-25/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/anymouschina/tapcanvas/seedance-25"><img src="https://agentmods.dev/badge/skills/anymouschina/tapcanvas/seedance-25.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 | $0.00186 | $0.02995 |
| Opus 5.5 | $0.00074 | $0.01198 |
| Sonnet 5.5 | $0.00037 | $0.00599 |
| Haiku 4.5 | $0.00019 | $0.00299 |
Grade A, and why
seedance-25 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 — 154 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Seedance 2.5 Director
Compile ideas, scripts, and multimodal assets into production-ready Seedance 2.5 prompts. Choose the task mode and reference roles first, then design visible events, continuity, camera, light, performance, and sound. Do not substitute adjective stacks for directorial decisions.
Truth Boundary
- Treat only capabilities and values stated in official sources as officially supported. Read capabilities-and-limits.md before stating reference counts, durations, resolutions, or locked parameters.
- Treat Dreamina Web, Jimeng, CapCut, APIs, and third-party providers as separate surfaces. Recheck current official documentation before stating entry points, model IDs, prices, regions, quotas, API fields, or operation availability.
- Never carry Seedance 2.0 numeric limits into 2.5. Reuse directing, reference-role, continuity, and repair methods only after replacing every platform fact with a verified 2.5 fact.
- Never claim to have viewed, heard, measured, or verified an attachment that the active client cannot inspect. Label user descriptions as user-reported and direct observations as observed.
- The copied official guides omit embedded images and finished-video comparisons. Do not describe those example results as visually verified.
Workflow
1. Build the Minimum Production Brief
Extract the following fields from information already supplied. Ask one short question only when a missing answer would materially change the result; otherwise use a conservative default and disclose the assumption.
- Goal: what the viewer should see, understand, or feel.
- Surface and task mode: text-only, multimodal reference, first-frame, first/last-frame, edit, extend, multi-clip production, one-click video, transition, storyboard, or blockout rendering.
- Duration, aspect ratio, and resolution: return configurable values as generation settings instead of prompt prose.
- Assets: what each image, video, and audio clip can actually contribute.
- Must preserve versus may change: identity, wardrobe, product structure, prop ownership, geography, camera, motion, and audio.
- Audio: dialogue language or accent, speaker, delivery, ambience, sound effects, music, or silence.
- Rights: whether likenesses, voices, brands, music, and source assets are owned, licensed, or otherwise authorized.
What ships with it
6 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.
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 Changed · +14 lines · +25 tokens per session db456fff1d2b
- 1mo ago First seen · 140 lines · 161 tokens per session scan A 30b4dd838e8b
seedance-25 is a skill published in the GitHub repository anymouschina/TapCanvas (712 stars, last pushed 4d ago), licensed MIT. It adds 186 tokens to every session and 2,995 once invoked, about $0.0007 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 2026-09-21.
seedance-25 compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| seedance-25anymouschina/TapCanvas | Skill | 712 | 4d ago | MIT | A | 186 | Codex |
| dramakexixihhhh/ai-short-drama-skill | Skill | 88 | 2mo ago | MIT | A | 279 | Claude Code, Codex |
| last30Dayschaitanyagiri/munder-difflin | Skill | 9.3k | 6d ago | MIT | A | 83 | Claude Code |
| thisWeekchaitanyagiri/munder-difflin | Skill | 9.3k | 6d ago | MIT | A | 77 | Claude Code |
| short-drama-storyboardzenstory-ai/drama-skills | Skill | 3.9k | today | MIT | A | 102 | Codex |
| md-fetch-summarizechaitanyagiri/munder-difflin | Skill | 9.3k | 6d ago | MIT | A | 93 | Claude Code |
| social-postHao0321/claude-skill-social-post | Skill | 750 | 22d ago | MIT | A | 119 | Codex |