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 linkprint/local-ai-movie-workspace --skill h3-asymmetric-speed-duo-choreographygit clone --depth 1 https://github.com/linkprint/local-ai-movie-workspaceWrote 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/linkprint/local-ai-movie-workspace/h3-asymmetric-speed-duo-choreography)<a href="https://agentmods.dev/skills/linkprint/local-ai-movie-workspace/h3-asymmetric-speed-duo-choreography"><img src="https://agentmods.dev/badge/skills/linkprint/local-ai-movie-workspace/h3-asymmetric-speed-duo-choreography/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/linkprint/local-ai-movie-workspace/h3-asymmetric-speed-duo-choreography"><img src="https://agentmods.dev/badge/skills/linkprint/local-ai-movie-workspace/h3-asymmetric-speed-duo-choreography.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 | $0.00080 | $0.00598 |
| Opus 5 | $0.00040 | $0.00299 |
| Sonnet 5 | $0.00016 | $0.00120 |
| Haiku 4.5 | $0.00008 | $0.00060 |
Grade A, and why
h3-asymmetric-speed-duo-choreography 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 — 36 lines — stays where its author put it; the contents beside it link to each section on GitHub.
H3 Asymmetric Speed Duo Choreography
Turn “one fast, one slow” into a countable movement law that remains visible throughout one continuous shot.
Route the Request
- For prompt writing or refinement, return text only.
- Read references/style-blueprint.md and use
$h3-prompt-writingfor H3 field order, timing, audio, and negatives. - Invoke
$h3-video-generationonly when the user explicitly asks to generate or render. - Use T2VA for original subjects. Use I2VA only when one supplied image defines the exact opening composition. Use native Ref2VA for identity-only or separately layered image/video references.
Lock the Ratio
- Assign performer A as the fast leader and performer B as the slow follower. Give them distinct adult identities, wardrobe, screen positions, and silhouettes.
- Define one action as a complete readable movement, not a frame or micro-twitch.
- State the invariant twice: whenever A completes three full actions, B completes exactly one full action.
- Make B watch A and imitate an earlier action after a deliberate delay. B never catches up, synchronizes, anticipates, or suddenly accelerates.
- Write a beat ledger such as
A1/A2/A3 -> B1, then repeat with new actions. Preserve the 3:1 count even when camera motion or music intensifies. - Use one continuous close orbit or restrained tracking shot, usually knees-to-head or waist-to-head, so both action counters remain visible.
- End with the ratio still unresolved; do not reward B with a synchronized finale.
Render Rules
- Keep one render to 4–15 seconds. Ten seconds should contain two or three complete 3:1 cycles, not dense uncountable motion.
- Default to
864x480; allow960x544when requested. Explicit 768p means1344x768and may never be downgraded. - Use only original adults and original instrumental music. Exclude named characters, celebrity likeness, existing songs, adult content, nudity, sexualized choreography, minors, duplicate bodies, identity swaps, sudden time remapping, cuts, subtitles, logos, and watermarks.
What ships with it
2 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.
- 12d ago First seen · 36 lines · 80 tokens per session scan A 9c61a96b2bc2
h3-asymmetric-speed-duo-choreography is a skill published in the GitHub repository linkprint/local-ai-movie-workspace (1 stars, last pushed 14d ago), licensed MIT. It adds 80 tokens to every session and 598 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 2026-08-31.
Other skills, from other repositories
higgsfield-seedance
Rewrites scene descriptions using professional cinematography language, structures prompts with a six-slot formula (camera + subject + action + setting + style + lighting), and diagnoses content filter rejections via a preflight linter. Use whenever the user asks for a Seedance 2.0 / Seedance Pro prompt, describes a…
higgsfield-acting
Writes the character-performance layer of a video prompt as behavior under pressure, not displayed emotion — objective, obstacle, tactics, beats, subtext, listening, body/status/proxemics, and mandatory eye life. Produces a reusable 150–220-word acting master profile per character plus a per-scene rewrite of it, and a…
higgsfield-prompt
Use when building, writing, refining, or structuring a Higgsfield AI prompt. Covers the MCSLA formula, prompt structure, narrative vs. timestamped formats, and how to write for both text-to-video and image-to-video workflows.
higgsfield-seedance-2-5
Seedance 2.5 prompt director — the omni-reference dialect. Routes the four generation modes (t2v / omnireference / videoedit / videoextension), writes explicit @Image/@Video/@Audio reference roles with exclusions, stages 30-second videos into end-state beats, and covers video editing, forward/backward extension…
higgsfield
Use this skill whenever the user asks anything about Higgsfield AI — writing or refining video/image prompts, choosing a model (Kling, Sora 2, Veo, Wan, Seedance, Minimax Hailuo, DoP, Soul, Nano Banana, Seedream, Flux, GPT Image, etc.), camera controls, named motion presets, Soul ID character consistency, Cinema…
higgsfield-assist
Use when the user asks about Higgsfield Assist (the built-in GPT-5 copilot), how to use the platform's native AI assistant, credit optimization strategies, plan selection, how to get more from fewer credits, or platform efficiency tips.