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 1370998960-del/https-github.com-Emily2040-seedance-2.0 --skill seedance-filtergit clone --depth 1 https://github.com/1370998960-del/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/1370998960-del/https-github.com-emily2040-seedance-2.0/seedance-filter)<a href="https://agentmods.dev/skills/1370998960-del/https-github.com-emily2040-seedance-2.0/seedance-filter"><img src="https://agentmods.dev/badge/skills/1370998960-del/https-github.com-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/1370998960-del/https-github.com-emily2040-seedance-2.0/seedance-filter"><img src="https://agentmods.dev/badge/skills/1370998960-del/https-github.com-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 39 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 39 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 39 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 | $0.00049 | $0.00874 |
| Opus 5.5 | $0.00020 | $0.00350 |
| Sonnet 5.5 | $0.00010 | $0.00175 |
| Haiku 4.5 | $0.00005 | $0.00087 |
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 1mo 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.
This is a copy
97% identical to seedance-filter — 4 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.
seedance-filter
Intent
A wrongly blocked prompt makes a user feel accused by a machine with no court of appeal. This skill is the advocate: clear the innocent by stating their honest intent plainly, and never coach the guilty. The user's dignity and the platform's boundary are protected in the same gesture.
Boundary — read before anything else
This skill repairs false positives only: benign production content blocked or degraded by over-broad filtering (medical, historical, athletic, fictional-original contexts). It works by clarifying legitimate context in plain language — never by disguising intent. It does not rephrase genuinely prohibited content: anything risky involving minors, real-person likeness without rights, sexual or graphic or illegal material. If the underlying request is prohibited, refuse plainly and offer a legitimate alternative only where one exists.
Use this when a prompt is blocked, degraded, likely to trigger moderation, or needs a safer rewrite without losing creative intent. This skill does not help evade safety systems. It rewrites risky surface wording into professional, non-graphic production language and preserves the safe creative core.
Repair Method
- Identify the creative intent: action, mood, camera, subject, and final beat.
- Identify risky surface wording: graphic harm, protected identity, sexualized framing, real-person likeness, weapons, self-harm, hate, evasion language, or exact IP copying.
- Replace risky terms with professional, non-graphic, production-context language.
- Preserve composition, action, mood, camera logic, and authorized references.
- For likely false positives, clarify benign production context, ownership, and non-graphic intent. Do not help bypass safety systems or provide evasion tactics.
Safer Rewrite Patterns
| Intent | Safer direction |
|---|---|
| Conflict | staged confrontation, choreographed action beat, no graphic injury |
| Aftermath | non-graphic distress, torn fabric, scattered props, dramatic silence |
| Suspense | threat implied by shadow, locked door, heavy breathing, low light |
| Weapon-like prop | prop object handled safely within a staged action scene |
| Horror mood | eerie atmosphere, flickering practical light, off-screen sound cue |
| Protected identity | original character with broad genre archetype traits |
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.
- 1mo ago First seen · 65 lines · 49 tokens per session scan A db8eff58f61d
seedance-filter is a skill published in the GitHub repository 1370998960-del/https-github.com-Emily2040-seedance-2.0 (249 stars, last pushed 3mo ago), licensed MIT. It adds 49 tokens to every session and 874 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 97% identical to seedance-filter, differing in 4 lines, and is treated as a copy.
Other skills, from other repositories
seedance-filter
This skill should be used when a Seedance 2.0 prompt is blocked or rejected, when moderation is a suspected cause of a problem, or when the user asks for a content-boundary review or safer alternative. Assess the actual request before offering a clarification.
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-vocab-en
This skill should be used when an English Seedance 2.0 prompt needs clearer production wording, less generic prose, or precise vocabulary for camera, lighting, motion, VFX, audio, and constraints. Route blocked prompts through seedance-filter for context and boundary review.
seedance-antislop
This skill should be used when a Seedance 2.0 prompt contains generic AI filler, hollow superlatives, vague cinematic language, bloated adjectives, weak verbs, or needs sharper production-specific wording.
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-vocab-zh
This skill should be used when the user asks for Chinese Seedance 2.0 prompt wording, Mandarin cinematic vocabulary, Chinese prompt compression, or translation of camera, lighting, action, VFX, audio, and production terms into Chinese.