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-anime-character-showcase-pvgit 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-anime-character-showcase-pv)<a href="https://agentmods.dev/skills/linkprint/local-ai-movie-workspace/h3-anime-character-showcase-pv"><img src="https://agentmods.dev/badge/skills/linkprint/local-ai-movie-workspace/h3-anime-character-showcase-pv/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-anime-character-showcase-pv"><img src="https://agentmods.dev/badge/skills/linkprint/local-ai-movie-workspace/h3-anime-character-showcase-pv.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 | $0.00091 | $0.00777 |
| Opus 5 | $0.00046 | $0.00388 |
| Sonnet 5 | $0.00018 | $0.00155 |
| Haiku 4.5 | $0.00009 | $0.00078 |
Grade A, and why
h3-anime-character-showcase-pv 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 — 44 lines — stays where its author put it; the contents beside it link to each section on GitHub.
H3 Anime Character Showcase PV
Turn a character sheet and environment reference into a bold, loopable introduction while preserving the hero's identity and separating what each image controls.
Route the Request
- For prompt writing or refinement, return text only.
- Read references/showcase-template.md and use
$h3-prompt-writingfor exact H3 format. - True generation needs two independently assigned references and therefore native Ref2VA. Put both images in
reference_imagesin prompt order and bind them explicitly as<Picture 1>and<Picture 2>. - Only when the user explicitly asks for a no-reference style preview may you adapt the template to T2VA and invoke
$h3-video-generation. Label it as a style preview, not an identity-locked reference render.
Lock Reference Roles
- Image 1 controls environment architecture and spatial identity only. Reinterpret its rendering in the requested graphic style; do not copy its lighting or surface textures unless requested.
- Image 2 controls the hero only: face, hair, body proportions, full-body silhouette, outfit, accessories, props, mechanical details, and palette.
- Never let Image 1 alter the hero or Image 2 overwrite the environment.
- Keep the hero at the exact center and constant scale. The character rotates; the camera and framing remain stable.
- State that identity, costume, proportions, palette, and topology may not drift at rear or profile angles.
Build the Showcase
- Use one uninterrupted 360-degree rotation with three or four evenly spaced world-assembly impacts.
- Use bold contour ink, clean cel shading, flat saturated blocks, crosshatching, hard silhouettes, comic gutters, diagonal panel splits, ink wipes, and radial action lines.
- Keep the underlying rotation perfectly smooth even when overlays cut sharply.
- Allow only two exact title lines supplied by the user. Place them in negative space, keep them away from the silhouette, then shrink them into one fixed emblem and remove them before the loop closes.
- Return to the exact opening angle, pose, scale, framing, environment, and downbeat. Do not freeze or hide a reset with a jump cut.
- Synchronize assembly impacts, panel wipes, title movement, mechanical hits, percussion, brass or plucked strings, and the loop's first/final beat.
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 · 44 lines · 91 tokens per session scan A cfeec9610ac3
h3-anime-character-showcase-pv is a skill published in the GitHub repository linkprint/local-ai-movie-workspace (1 stars, last pushed 14d ago), licensed MIT. It adds 91 tokens to every session and 777 once invoked, about $0.0005 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.