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-creature-motion-replacementgit 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-creature-motion-replacement)<a href="https://agentmods.dev/skills/linkprint/local-ai-movie-workspace/h3-creature-motion-replacement"><img src="https://agentmods.dev/badge/skills/linkprint/local-ai-movie-workspace/h3-creature-motion-replacement/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-creature-motion-replacement"><img src="https://agentmods.dev/badge/skills/linkprint/local-ai-movie-workspace/h3-creature-motion-replacement.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 | $0.00528 |
| Opus 5 | $0.00037 | $0.00264 |
| Sonnet 5 | $0.00015 | $0.00106 |
| Haiku 4.5 | $0.00007 | $0.00053 |
Grade A, and why
h3-creature-motion-replacement 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 — 37 lines — stays where its author put it; the contents beside it link to each section on GitHub.
H3 Creature Motion Replacement
Treat this as a controlled edit: motion and staging come from the source, while creature identity and optional lighting come from separate references.
Route the Request
- For prompt writing or analysis, return a Ref2VA plan without rendering.
- Only attempt real replacement when the active generation tool explicitly supports video and image references.
- A true motion replacement must use native Ref2VA with the source motion clip under
reference_videos; never substitute T2VA and call it equivalent. - For an original no-reference demonstration, use the T2VA adaptation in the blueprint and clearly label it as a style demo, not motion replacement.
- Use
$h3-prompt-writingand read references/style-blueprint.md.
Separate Reference Jobs
<Video 1>supplies the source edit, camera motion, temporal structure, actor path, and prop timing.<Subject 1>supplies creature anatomy, scale, skin or fur, locomotion, and silhouette from its image reference.- Define a setting or lighting reference separately; never let it overwrite the source geometry unless requested.
- Mark retained props and contact events explicitly, including doors, handles, toys, floor contact, shadows, and impact timing.
- Replace human sounds with creature-specific footsteps, breathing, claws, fabric, or weight while preserving the timing of the source action.
- Keep anatomy stable and physically compatible with the interaction. Do not invent extra limbs or let the creature pass through objects.
Render Rules
- True replacement uses full-reference format, not the three-field T2VA format.
- A T2VA style demo may depict an original creature performing a simple domestic action with cinematic night lighting.
- Keep clips to 4–15 seconds. Default demo resolution is
864x480; explicit 768p means1344x768. - Exclude copyrighted characters, real-person likenesses, visible source watermarks, and unsupported claims of exact motion transfer.
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 · 37 lines · 75 tokens per session scan A 36a3b0d1b8ea
h3-creature-motion-replacement 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 528 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.