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 rediumvex/ai-video-generator-claude --skill 01-viral-hookgit clone --depth 1 https://github.com/rediumvex/ai-video-generator-claudeWrote 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/rediumvex/ai-video-generator-claude/01-viral-hook)<a href="https://agentmods.dev/skills/rediumvex/ai-video-generator-claude/01-viral-hook"><img src="https://agentmods.dev/badge/skills/rediumvex/ai-video-generator-claude/01-viral-hook/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/rediumvex/ai-video-generator-claude/01-viral-hook"><img src="https://agentmods.dev/badge/skills/rediumvex/ai-video-generator-claude/01-viral-hook.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 | $0.00102 | $0.04446 |
| Opus 5.5 | $0.00041 | $0.01778 |
| Sonnet 5.5 | $0.00020 | $0.00889 |
| Haiku 4.5 | $0.00010 | $0.00445 |
Grade A, and why
seedance-viral-hook 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.
How it starts
The opening of the file, as written. The whole thing — 338 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Viral Hook — Scroll-Stopping Short-Form Video Prompts
Seedance 2.0 on Higgsfield — Input Specs
- Images: Up to 9 reference images (mood boards, product shots, brand assets)
- Videos: Up to 3 video clips (existing footage, motion references)
- Audio: Up to 3 audio files (trending sounds, voiceover, SFX)
- Text: Full prompt with timing, camera, lighting, sound
- Max Assets: 12 total combined
- Output: 4-15 seconds, 720p video with synchronized audio
- Reference Syntax:
@material[name]to reference uploaded assets
The Attention Economy: Why 2 Seconds
- 0-2s: The gate. If 50%+ bounce here, the video dies. If 90% stay, the algorithm promotes.
- 2-5s: Hook confirmation. Brain decides: worth my time or not.
- 5-15s: Engagement peak. Emotional beats, reveals, payoffs land here.
- 15s+: Retention cliff. Most viral videos are under 15 seconds.
Videos with 80%+ completion get 2-3x algorithmic reach. Your hook determines everything.
The Hook Arsenal: 12 Battle-Tested Patterns
1. Pattern Interrupt — Break Reality
| Technique | Mechanism | Prompt Template |
|---|---|---|
| Physics Break | Objects defy gravity, water flows up, time reverses | "Open with [object] defying physics — floating upward, sliding in reverse, freezing mid-air. Camera steady, treating impossible action as mundane. First 0.8s shows normal expectation, 0.8-2s breaks it. No music, only ambient sound emphasizing the wrongness." |
| Scale Warp | Familiar object at impossible size | "Extreme wide shot: [tiny object — coin, key, pen] scaled to building size in landscape. Human figure provides scale reference at base. Drone-style camera slowly pushing forward. Overcast lighting, photorealistic. Viewer spends 2s processing scale." |
| Color Bomb | Grayscale world gets sudden saturation | "Scene begins fully desaturated — gray, lifeless, muted. At 1.2s, single element ignites with saturated color [neon pink/electric blue/gold]. Color bleeds outward across frame over 0.8s. Hard bass hit synced to color moment." |
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 · 338 lines · 102 tokens per session scan A 23a21dae0317
seedance-viral-hook is a skill published in the GitHub repository rediumvex/ai-video-generator-claude (438 stars, last pushed 2mo ago), licensed MIT. It adds 102 tokens to every session and 4,446 once invoked, about $0.0004 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 2026-08-30.
Other skills, from other repositories
linkedin-humanizer
Remove AI tells from LinkedIn posts/comments: 2026 vocabulary density, reveal bridges, staccato fragments, stacked triads, performed sincerity. Tiered rewriter plus --mode audit LinkedIn post auditor and --mode profile voice builder. Not for drafting from scratch (use linkedin-post-writer) or beating AI detectors.…
linkedin-marketing
Plan, draft, audit, and publish LinkedIn posts and comments. Use when the user wants to write a viral LinkedIn post, draft a comment or reply on any LinkedIn post URL, audit a draft against 2026 algorithm heuristics, remove AI tells, extract hook formulas from viral posts, or plan a week of content. Powered by the…
linkedin-reply-handler
Draft a reply to one LinkedIn comment from its URL, or sweep a whole thread from just the post URL and draft a reply to every comment worth answering, in one batch. Use for replying to a comment, following an author reply, or clearing all comments on a post. Resolves the correct parentComment (LinkedIn flattens…
linkedin-post-writer
Draft a new LinkedIn post from scratch using one of 20 2026 hook formulas (anaphora, R.I.P., time-anchor, curiosity-gap, contrarian, controlled A/B, false-binary, and more) plus a founders-edition angle library, picked by engagement goal (comments, reposts, likes, saves). Runs the humanizer pass and schedules via…
linkedin-comment-drafter
Draft a LinkedIn comment on someone else's post from its URL, or reshare (repost) it to your feed with optional commentary. Use when the user pastes a post URL and asks to comment, engage, be first commenter, or repost with their thoughts. Produces 1-3 variants in the user's voice, picks a reaction, and publishes via…
linkedin-content-planner
Generate a 7-day LinkedIn content plan from a theme, audience, and pillars. Produces per-day post pillar, format, hook type, CTA, posting time, daily comment targets, and a weekly inbound-readiness check. Use when the user wants to plan a week or month of content, not draft a single post (use linkedin-post-writer).