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-japanese-craft-commercialgit 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-japanese-craft-commercial)<a href="https://agentmods.dev/skills/linkprint/local-ai-movie-workspace/h3-japanese-craft-commercial"><img src="https://agentmods.dev/badge/skills/linkprint/local-ai-movie-workspace/h3-japanese-craft-commercial/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-japanese-craft-commercial"><img src="https://agentmods.dev/badge/skills/linkprint/local-ai-movie-workspace/h3-japanese-craft-commercial.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 | $0.00075 | $0.00561 |
| Opus 5 | $0.00037 | $0.00280 |
| Sonnet 5 | $0.00015 | $0.00112 |
| Haiku 4.5 | $0.00007 | $0.00056 |
Grade A, and why
h3-japanese-craft-commercial 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 — 38 lines — stays where its author put it; the contents beside it link to each section on GitHub.
H3 Japanese Craft Commercial
Show the dignity of making through material detail and precise action. Do not copy a brand, logo, existing campaign, or named director.
Route the Request
- For prompt writing or refinement, return text only.
- Only when the user explicitly asks to generate or render, compose the prompt and invoke
$h3-video-generation. - Use
$h3-prompt-writingfor field order and timed cuts. - Read references/style-blueprint.md before drafting.
Build the Commercial
- Lock the product geometry, material, finish, edge, handle, glaze, grain, or construction details.
- Use no more than three visual beats in 10 seconds: process macro, functional proof, hero still-life.
- Prefer controlled side light, negative fill, dark wood, paper, stone, steam, water, or one vermilion accent.
- Direct hands precisely and keep finger count, grip, tool contact, and product orientation stable.
- Describe reflections as specular roll, edge glints, water caustics, brushed metal, or lacquer depth—not merely “shiny.”
- Use small, deliberate camera moves and motivated cuts. Let impact sounds, scraping, slicing, pouring, or cloth movement define rhythm.
- Keep the final product centered and clean. Reserve exact brand marks or typography for post-production unless a simple supplied label is essential.
Mode and Render Rules
- Use T2VA for an unbranded concept. Use I2VA when an authorized pack shot must anchor geometry.
- Multiple product, hand, and location references require native Ref2VA; pass them in prompt order and state exactly what each
<Picture N>or<Video N>controls. - Keep clips to 4–15 seconds. Default demonstration is 10 seconds.
- Default to
864x480; allow960x544if requested. Explicit 768p means1344x768with no downgrade. - Exclude copied logos, extra tools, warped product geometry, unsafe hand placement, illegible small text, subtitles, and watermarks.
Output
Return the mode, shot list, duration/resolution, complete H3 prompt, and post-production typography note. For real generation, wait, verify geometry and media integrity, and return the absolute Portal URL.
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 · 38 lines · 75 tokens per session scan A b9c6683ab47d
h3-japanese-craft-commercial is a skill published in the GitHub repository linkprint/local-ai-movie-workspace (1 stars, last pushed 14d ago), licensed MIT. It adds 75 tokens to every session and 561 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.