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-interactive-creature-encyclopediagit 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-interactive-creature-encyclopedia)<a href="https://agentmods.dev/skills/linkprint/local-ai-movie-workspace/h3-interactive-creature-encyclopedia"><img src="https://agentmods.dev/badge/skills/linkprint/local-ai-movie-workspace/h3-interactive-creature-encyclopedia/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-interactive-creature-encyclopedia"><img src="https://agentmods.dev/badge/skills/linkprint/local-ai-movie-workspace/h3-interactive-creature-encyclopedia.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 | $0.00070 | $0.00678 |
| Opus 5.5 | $0.00028 | $0.00271 |
| Sonnet 5.5 | $0.00014 | $0.00136 |
| Haiku 4.5 | $0.00007 | $0.00068 |
Grade A, and why
h3-interactive-creature-encyclopedia 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 Interactive Creature Encyclopedia
Treat the UI as a locked spatial stage: every creature selection must atomically update the selected card, main creature, and exact main title.
Route the Request
- For prompt writing or refinement, return text only.
- Read references/style-blueprint.md and use $h3-prompt-writing.
- Invoke $h3-video-generation only when the user explicitly asks to render.
- A UI reference plus independent creature images requires native Ref2VA. Put the UI and creature images in
reference_imagesin prompt order and assign each<Picture N>a single explicit role. - For the selected eight-creature cursor-interaction recipe, use the exact role map and 15-second timeline in the reference file. Do not substitute images, card letters, creature names, or selection order.
Build the Encyclopedia
- Image 1 controls the complete interface only: layout, typography system, panels, icons, card positions, colors, chrome, spacing, and overall composition. It may not alter any creature.
- Images 2–9 independently control cards A–H and their matching creature identities. Never exchange anatomy, markings, palette, surface, card, or title.
- Keep camera, UI coordinate system, panels, icons, buttons, and all non-selected content completely fixed for the entire shot.
- Use exactly one cursor. Cursor click or drag changes only the selection highlight, main creature, exact main title, and selected creature motion.
- Update the main creature and main title in the same UI state transition. Never show a new creature with the previous title or vice versa.
- Keep interactions subtle until the final creature lunges and swallows the cursor; after the gulp, return that creature to idle without restoring the cursor.
- Add no extra text, buttons, cursor, cards, creature, panel, pop-up, scene cut, camera move, or UI distortion.
- Synchronize soft UI clicks, hover sounds, tiny creature reactions, the final aggressive vocalization, and one comedic swallow gulp.
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 · 70 tokens per session scan A a273d2b49fe1
h3-interactive-creature-encyclopedia is a skill published in the GitHub repository linkprint/local-ai-movie-workspace (1 stars, last pushed 2mo ago), licensed MIT. It adds 70 tokens to every session and 678 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-interactive-creature-encyclopedia compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| h3-interactive-creature-encyclopedialinkprint/local-ai-movie-workspace | Skill | 1 | 2mo ago | MIT | A | 70 | Codex |
| 3d-production-workflowholon-run/holon | Skill | 194 | today | Apache-2.0 | A | 48 | Claude Code, Codex |
| gltf-asset-pipelinePIXARTSeu/Synapse | Skill | 12 | 1mo ago | none | A | 98 | Claude Code, Codex |
| game-developerPIXARTSeu/Synapse | Skill | 12 | 1mo ago | none | A | 99 | Claude Code, Codex |
| playtest-reportDonchitos/Claude-Code-Game-Studios | Skill | 37k | 20d ago | MIT | A | 20 | Claude Code |
| godot-signals-groupsgamedev-skills/awesome-gamedev-agent-skills | Skill | 7.8k | 11d ago | Apache-2.0 | A | 95 | Claude Code |
| scenario-unreal-gameplayscenario-labs/skills | Skill | 3.5k | yesterday | MIT | A | 121 | Claude Code |