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-surreal-miniature-absurdismgit 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-surreal-miniature-absurdism)<a href="https://agentmods.dev/skills/linkprint/local-ai-movie-workspace/h3-surreal-miniature-absurdism"><img src="https://agentmods.dev/badge/skills/linkprint/local-ai-movie-workspace/h3-surreal-miniature-absurdism/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-surreal-miniature-absurdism"><img src="https://agentmods.dev/badge/skills/linkprint/local-ai-movie-workspace/h3-surreal-miniature-absurdism.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 | $0.00587 |
| Opus 5.5 | $0.00030 | $0.00235 |
| Sonnet 5.5 | $0.00015 | $0.00117 |
| Haiku 4.5 | $0.00007 | $0.00059 |
Grade A, and why
h3-surreal-miniature-absurdism 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 2mo 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 Surreal Miniature Absurdism
Create an original impossible situation with internally consistent scale, physics, and comic escalation. Never copy a celebrity, named meme, or source scene.
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 H3 field order, timestamps, audio, and dialogue syntax. - Read references/style-blueprint.md before drafting.
Direct the Gag
- Define the normal material world first: surface, liquid, glass, metal, food, room light, and camera scale.
- State the impossible subject literally, including its exact size and what it is not. Keep its anatomy stable.
- Use one readable three-beat escalation: calm setup, physical disruption, payoff or reveal.
- Describe contact physics: displacement, compression, dripping, drag, weight, collision, and reaction.
- Keep the camera near the smallest subject until the reveal. Prefer one continuous macro tracking move over unrelated cuts.
- Give each speaking subject a stable ID and one short line only. Use
non_diegetic_music: N/Aunless music is essential. - End immediately after the visual payoff. Exclude subtitles, logos, watermarks, and extra text.
Mode and Render Rules
- Use T2VA by default. Use I2VA only when the supplied first frame already establishes the scale relationship.
- For independent identity, creature, and setting references, use native Ref2VA, pass the ordered files under
reference_imagesorreference_videos, and name every<Picture N>or<Video N>role in the prompt. - Keep one real render to 4–15 seconds. Default to 10 seconds for a complete gag.
- If resolution is unspecified, use
864x480;960x544is allowed when requested. If the user explicitly asks for 768p, use1344x768and never downgrade it. - Avoid real-person likenesses unless the user has supplied an authorized reference and the active workflow supports it.
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.
- 2mo ago First seen · 38 lines · 75 tokens per session scan A a226b3bc2811
h3-surreal-miniature-absurdism is a skill published in the GitHub repository linkprint/local-ai-movie-workspace (1 stars, last pushed 2mo ago), licensed MIT. It adds 75 tokens to every session and 587 once invoked, about $0.0003 per session on Opus 5.5. 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.
h3-surreal-miniature-absurdism compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| h3-surreal-miniature-absurdismlinkprint/local-ai-movie-workspace | Skill | 1 | 2mo ago | MIT | A | 75 | Codex |
| tape-opensenricoros/big-AGI | Skill | 7.2k | today | MIT | A | 60 | Claude Code |
| x-signal-agentomnara-ai/omnara | Skill | 3.4k | today | Apache-2.0 | A | 53 | Claude Code, Codex |
| agent-notesCherryHQ/cherry-studio | Skill | 53k | today | AGPL-3.0 | A | 51 | Claude Code, Codex |
| cherry-electron-devCherryHQ/cherry-studio | Skill | 53k | today | AGPL-3.0 | A | 68 | Claude Code, Codex |
| issue-reporterCherryHQ/cherry-studio | Skill | 53k | today | AGPL-3.0 | A | 35 | Claude Code |
| code-mate-antigravityCherryHQ/cherry-studio | Skill | 53k | today | AGPL-3.0 | A | 32 | Claude Code, Codex |