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 nirholas/three.ws --skill ai-game-world-designgit clone --depth 1 https://github.com/nirholas/three.wsWrote 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/nirholas/three.ws/ai-game-world-design)<a href="https://agentmods.dev/skills/nirholas/three.ws/ai-game-world-design"><img src="https://agentmods.dev/badge/skills/nirholas/three.ws/ai-game-world-design/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/nirholas/three.ws/ai-game-world-design"><img src="https://agentmods.dev/badge/skills/nirholas/three.ws/ai-game-world-design.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00088 | $0.03782 |
| Opus 5.5 | $0.00035 | $0.01513 |
| Sonnet 5.5 | $0.00018 | $0.00756 |
| Haiku 4.5 | $0.00009 | $0.00378 |
Grade A, and why
ai-game-world-design 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 1mo 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 — 461 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AI Game World Design — From First Principles
This skill teaches you to architect game worlds where AI doesn't just play — it narrates, adapts, economizes, and breathes life into every NPC, quest, and ecosystem. You'll learn to build worlds that feel alive because they actually are.
Core Philosophy
┌─────────────────────────────────────────────────────────┐
│ THE LIVING WORLD MANIFESTO │
├─────────────────────────────────────────────────────────┤
│ │
│ A great AI game world has three properties: │
│ │
│ 1. EMERGENT — behaviors arise that designers │
│ never explicitly programmed │
│ │
│ 2. REACTIVE — the world changes in response │
│ to player actions, not just scripted triggers │
│ │
│ 3. PERSISTENT — consequences compound over time, │
│ creating unique histories for every playthrough │
│ │
│ AI is the engine that makes all three possible. │
│ │
└─────────────────────────────────────────────────────────┘
World Generation
Procedural Terrain
The foundation of any game world is geography. Procedural generation creates infinite variety from algorithmic rules.
| Technique | Best For | Scale |
|---|---|---|
| Perlin/Simplex Noise | Terrain heightmaps, caves | Continental |
| Wave Function Collapse | Tiled environments, dungeons | Room/zone |
| L-Systems | Vegetation, branching structures | Object |
| Voronoi Diagrams | Biome boundaries, territories | Regional |
| Agent-Based | City layouts, road networks | City |
| Grammar-Based | Building interiors, quest structures | Structure |
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.
- 1mo ago First seen · 461 lines · 88 tokens per session scan A 56c9d4f89720
ai-game-world-design is a skill published in the GitHub repository nirholas/three.ws (247 stars, last pushed today), licensed Apache-2.0. It adds 88 tokens to every session and 3,782 once invoked, about $0.0004 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 2026-09-03.
Other skills, from other repositories
threejs-docs
Comprehensive Three.js reference covering core API (objects, cameras, lights, materials, geometries, renderers, scenes, textures, math, animation, audio, loaders, helpers, nodes), all addons (controls, postprocessing, loaders, exporters, geometries, shaders, WebXR, physics), TSL (Three.js Shading Language) functions…
blender-mcp
Control Blender directly from Hermes via socket connection to the blender-mcp addon. Create 3D objects, materials, animations, and run arbitrary Blender Python (bpy) code. Use when user wants to create or modify anything in Blender.
llava
Vision-language chat: VQA, captioning, image dialogue.
open-source
Documentation reference for writing Python code using the browser-use open-source library. Use this skill whenever the user needs help with Agent, Browser, or Tools configuration, is writing code that imports from browseruse, asks about @sandbox deployment, supported LLM models, Actor API, custom tools, lifecycle…
running-openmed-ondevice
Run OpenMed models fully on-device with the MLX (Apple Silicon), CoreML (iOS/macOS), or ONNX/WebGPU (cross-platform/browser) backends, including convert-quantize-run workflows. Use when the user wants to deploy OpenMed at the edge, run NER/de-id on Apple Silicon, target iPhone/iPad/Mac, export to ONNX or WebGPU…
neuron-evaluation
Create and run AI evaluations with datasets, assertions, and output drivers in Neuron AI. Use this skill whenever the user mentions evaluation, testing AI systems, creating evaluators, dataset-driven testing, assertion-based validation, or wants to measure AI system performance. Also trigger for tasks involving…