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 07-before-aftergit 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/07-before-after)<a href="https://agentmods.dev/skills/rediumvex/ai-video-generator-claude/07-before-after"><img src="https://agentmods.dev/badge/skills/rediumvex/ai-video-generator-claude/07-before-after/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/07-before-after"><img src="https://agentmods.dev/badge/skills/rediumvex/ai-video-generator-claude/07-before-after.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 | $0.00079 | $0.04330 |
| Opus 5 | $0.00039 | $0.02165 |
| Sonnet 5 | $0.00016 | $0.00866 |
| Haiku 4.5 | $0.00008 | $0.00433 |
Grade A, and why
seedance-before-after 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 12d 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 — 292 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Before-After — Transformation Reveal Video Prompts
Transformation content is the highest-engagement format on social media. This skill generates precise Seedance 2.0 prompts that capture the full emotional arc of change: tension, reveal, payoff.
Input Specs
Before generating prompts, establish:
- Subject: What is transforming? (person, room, product, brand, body, space, logo, website)
- From state: Describe the before — tone, condition, mood, colors, energy
- To state: Describe the after — tone, condition, mood, colors, energy
- Duration: 4s, 6s, or 8s clip
- Aspect ratio: 9:16 (Reels/TikTok), 1:1 (feed), 16:9 (YouTube)
- Transition style: hard cut, wipe, morph dissolve, object match, time-lapse compress
- Platform destination: Instagram Reels, TikTok, YouTube Shorts, LinkedIn
Material References
- Use
@material[image1]for the "before" state photo - Use
@material[image2]for the "after" state photo - Use
@material[video1]for existing transformation footage - Use
@material[audio1]for background music or sound effects
Platform Optimization
- TikTok (9:16): Hook by 1.5s. Transition at 2-3s mark. Text overlays in center 80%. Bottom 20% obscured by UI.
- Instagram Reels (9:16): Hook by 2s. Higher polish expected. Cover frame must work as grid image — pick the "after" hero moment.
- YouTube Shorts (9:16): Hook by 2-3s. Can run longer (up to 60s). Description provides context.
- LinkedIn (16:9 or 1:1): Professional tone. Slower transitions acceptable. Text overlays should include metric/result.
2-Second Hook Structures
1. The Flash Compare
Show both states in rapid alternation — before/after/before — within the first 1.5 seconds. The brain registers contrast before the viewer consciously decides to watch.
Prompt element: "rapid flash cut between [before state] and [after state], alternating twice in the first 1.5 seconds, creating a visual stutter effect that forces viewer attention"
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.
- 12d ago First seen · 292 lines · 79 tokens per session scan A 7151cde6a85b
seedance-before-after is a skill published in the GitHub repository rediumvex/ai-video-generator-claude (361 stars, last pushed 1mo ago), licensed MIT. It adds 79 tokens to every session and 4,330 once invoked, about $0.0004 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
linkedin-humanizer
Remove the AI tells human readers and LinkedIn's AI-slop filter react to in a post or comment: 2026 vocabulary by paragraph density, reveal bridges, staccato fragments, stacked triads, performed sincerity. Tiered rewriter (forensic / strict / aesthetic / all) plus --mode audit pass-fail review and --mode profile voice…
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 a specific existing LinkedIn comment from its URL. Use when the user wants to reply to a comment on any post, or follow up after an author replied to them. Parses the commentUrn, resolves the correct parentComment target (LinkedIn flattens threads to 2 levels), and posts via Publora on approval. Not…
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.