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-layered-windsurfing-fashion-mvgit 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-layered-windsurfing-fashion-mv)<a href="https://agentmods.dev/skills/linkprint/local-ai-movie-workspace/h3-layered-windsurfing-fashion-mv"><img src="https://agentmods.dev/badge/skills/linkprint/local-ai-movie-workspace/h3-layered-windsurfing-fashion-mv/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-layered-windsurfing-fashion-mv"><img src="https://agentmods.dev/badge/skills/linkprint/local-ai-movie-workspace/h3-layered-windsurfing-fashion-mv.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 | $0.00085 | $0.00743 |
| Opus 5 | $0.00043 | $0.00371 |
| Sonnet 5 | $0.00017 | $0.00149 |
| Haiku 4.5 | $0.00009 | $0.00074 |
Grade A, and why
h3-layered-windsurfing-fashion-mv 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 — 45 lines — stays where its author put it; the contents beside it link to each section on GitHub.
H3 Layered Windsurfing Fashion MV
Give every reference one authority and build each 15-second segment around a musical energy curve.
Route the Request
- For prompt writing or refinement, return text only.
- Read references/style-blueprint.md and use
$h3-prompt-writing. - Invoke
$h3-video-generationonly when the user explicitly asks to render a named segment. Never submit all three segments implicitly. - The full design is three separate 15-second jobs. Use native Ref2VA for identity/equipment references in each job, preserve the same ordered references and prompt labels across all three, then assemble the approved outputs; the Broker still does not expose a single multishot job.
Assign Reference Authority
- Picture 1 is the key visual and opening-state authority: adult identity, face, hair, costume, palette, and first frame.
- Picture 2 is the turnaround and equipment authority: body proportions, board, sail, mast, boom, rigging, fasteners, and color relationships. It is not a storyboard or camera guide.
- Picture 3 is the segment-specific cinematography guide: framing, lens, movement, subject scale, and composition only. It cannot change identity, costume, equipment, or environment logic.
- For the climax segment, omit Picture 3 and direct the giant wave, takeoff, airborne hero hold, landing, and fashion finish entirely in text.
Shape Each Segment
00:00-00:03: build anticipation.00:03: musical drop and decisive action onset.00:03-00:10: sustained high energy.00:06-00:07: optional compact turnaround that proves equipment integrity.00:09-00:10: absolute visual peak with a stable hero camera moment.00:10-00:12: release.00:12-00:15: fashion ending or bridge to the next phrase.
Keep water physics, rig tension, hand placement, wind direction, and board contact coherent. Use a trained adult athlete, controlled fictional conditions, and no injury.
Render Rules
- Default orientation for the full fashion campaign is 9:16, one 15-second segment at a time. The modal demo is a 10-second 16:9 T2VA style preview.
- Default to
864x480; allow960x544when requested. Explicit 768p means1344x768and may never be downgraded. For vertical delivery, use the Broker-supported vertical equivalent only if available and explicitly requested. - Exclude adult content, nudity, sexualized framing, minors, celebrity likeness, named characters, real brands, logos, unsafe weather, injury, broken rigging, changing board geometry, extra limbs, unreadable text, subtitles, 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 · 45 lines · 85 tokens per session scan A dba7b4e9e31f
h3-layered-windsurfing-fashion-mv is a skill published in the GitHub repository linkprint/local-ai-movie-workspace (1 stars, last pushed 14d ago), licensed MIT. It adds 85 tokens to every session and 743 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.