h3-chibi-live-action-sticker

h3-chibi-live-action-sticker is a skill for Codex from linkprint/local-ai-movie-workspace. It costs 69 tokens per session (690 once invoked), scanned A, original, MIT.

A prompt-writing guide for MiniMax H3, a video-generation model, that places one flat 2D chibi character—a small cute cartoon figure—in an otherwise photoreal live-action scene.

In plain words
What is it for?
Use it for short mixed-media scenes where a cartoon mascot affects real food, desks, streets, hands, or props through a simple action and visible real-world reactions.
Why use it?
It keeps the boundary between the drawn character and the real world clear while making their physical interaction understandable.

Skill for Codex

Written for Codex: agents/openai.yaml present. Also seen: $skill-name invocation.

Good fit Use it for short mixed-media scenes where a cartoon mascot affects real food, desks, streets, hands, or props through a simple action and visible real-world reactions.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/linkprint/local-ai-movie-workspace/h3-chibi-live-action-sticker
Install

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.

Any agent
npx skills add linkprint/local-ai-movie-workspace --skill h3-chibi-live-action-sticker
Clone the repo
git clone --depth 1 https://github.com/linkprint/local-ai-movie-workspace

Made for: Codex.

Wrote 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.

agentmods badge for h3-chibi-live-action-sticker

README.md
[![agentmods](https://agentmods.dev/badge/skills/linkprint/local-ai-movie-workspace/h3-chibi-live-action-sticker/github.svg)](https://agentmods.dev/skills/linkprint/local-ai-movie-workspace/h3-chibi-live-action-sticker)
Your own site
<a href="https://agentmods.dev/skills/linkprint/local-ai-movie-workspace/h3-chibi-live-action-sticker"><img src="https://agentmods.dev/badge/skills/linkprint/local-ai-movie-workspace/h3-chibi-live-action-sticker/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.

agentmods 80×15 button for h3-chibi-live-action-sticker

Your own site · 80×15
<a href="https://agentmods.dev/skills/linkprint/local-ai-movie-workspace/h3-chibi-live-action-sticker"><img src="https://agentmods.dev/badge/skills/linkprint/local-ai-movie-workspace/h3-chibi-live-action-sticker.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 69 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 690 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00069 $0.00690
Opus 5 $0.00034 $0.00345
Sonnet 5 $0.00014 $0.00138
Haiku 4.5 $0.00007 $0.00069

Measured 12d ago against content hash 954eb509f061, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

h3-chibi-live-action-sticker 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.

images/workspace/admin-skills/h3-chibi-live-action-sticker/SKILL.md · 45 lines

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 Chibi Live-Action Sticker

Keep the drawn character unmistakably flat while the surrounding world remains fully photographic.

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-writing for exact H3 audiovisual structure.
  • Read references/style-blueprint.md before drafting.

Preserve the Mixed-Media Contract

  1. State that the chibi is the only flat 2D sticker character in the scene; everything else is photoreal live action.
  2. Lock its outline thickness, fill palette, head-to-body ratio, facial features, and absence of volume, pores, fur, or realistic shading.
  3. Give it one simple action arc with clear anticipation, contact, and reaction.
  4. Let the real world respond through crumbs, steam, droplets, shadows, utensil movement, or a human hand. Keep contact points explicit.
  5. Use a mostly static camera or a small slow push so the style boundary stays readable.
  6. Avoid morphing the real objects into drawings or turning the character into 3D CG.
  7. Keep dialogue optional and short; prefer synchronized foley and one playful musical motif.

Use Closed Prop Contracts and Beat Anchors

  • When a gag depends on a prop state, define the allowed object exhaustively. For example: one open-top glass jar, no lid, no cap, no removable cover, and no lid-like object anywhere in frame.
  • Bind irreversible story events to exact timestamps, such as contact at 00:03.000, consequence at 00:05.000, and cartoon reaction at 00:08.000.
  • Keep the human hand photoreal and anatomically connected whenever it enters. The hand performs the real-world action; the flat sticker reacts without gaining volume.
  • If silence is part of the comedy, state no music and use only room tone and synchronized object sounds.

Mode and Render Rules

  • Use T2VA by default. Use I2VA when an opening composition or mascot design must be anchored.
  • If multiple reference images are needed to lock mascot identity and environment separately, use native Ref2VA and bind the ordered images to distinct <Picture N> roles.
  • Keep the clip to one 4–15 second scene. A 10-second arc should use no more than three action beats.
  • Default to 864x480; allow 960x544 if requested. Explicit 768p means 1344x768 with no downgrade.
  • Exclude subtitles, logos, watermarks, extra drawn characters, photoreal skin on the mascot, and unexplained style changes.

Read the full file on GitHub · 45 lines

Files

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.

Changes

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.

  1. 12d ago First seen · 45 lines · 69 tokens per session scan A 954eb509f061

Subscribe to this mod's changes

h3-chibi-live-action-sticker is a skill published in the GitHub repository linkprint/local-ai-movie-workspace (1 stars, last pushed 14d ago), licensed MIT. It adds 69 tokens to every session and 690 once invoked, about $0.0003 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.

Related

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…

OSideMedia/higgsfield-ai-prompt-skill · 100 tokens

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…

OSideMedia/higgsfield-ai-prompt-skill · 165 tokens

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.

OSideMedia/higgsfield-ai-prompt-skill · 56 tokens

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…

OSideMedia/higgsfield-ai-prompt-skill · 191 tokens

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…

OSideMedia/higgsfield-ai-prompt-skill · 147 tokens

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.

OSideMedia/higgsfield-ai-prompt-skill · 56 tokens