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 Shellishack/3d-web-game-dev-skills --skill procedural-scene-propsgit clone --depth 1 https://github.com/Shellishack/3d-web-game-dev-skillsWrote 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/shellishack/3d-web-game-dev-skills/procedural-scene-props)<a href="https://agentmods.dev/skills/shellishack/3d-web-game-dev-skills/procedural-scene-props"><img src="https://agentmods.dev/badge/skills/shellishack/3d-web-game-dev-skills/procedural-scene-props.svg" alt="Measured on agentmods" 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 | $0.00000 | $0.01045 |
| Opus 5 | $0.00000 | $0.00522 |
| Sonnet 5 | $0.00000 | $0.00209 |
| Haiku 4.5 | $0.00000 | $0.00104 |
Grade A, and why
procedural-scene-props 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 8d 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 — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Procedural Low-Poly Scene Props
Use this skill when adding lightweight procedural props to a stylized 3D world without relying on a full art pipeline.
Pattern
Build small prop helper functions that accept a scene, name, position, and a few scale/color options. Each helper returns a root transform or mesh. Parent child meshes to the root so the prop can be moved, animated, hidden, or disposed as one object.
Good helper categories:
- rocks from irregular polyhedrons or scaled spheres
- trees from cylinder trunks and clustered leaf shapes
- steam, smoke, or mist from translucent spheres or planes
- vehicles from simple boxes/cylinders
- characters from cylinders, spheres, and small accessories
- terrain patches from flattened boxes or ground planes
- beacons and markers from simple emissive meshes
import { Color3, MeshBuilder, StandardMaterial, TransformNode, Vector3, type Scene } from '@babylonjs/core'
function makeMat(scene: Scene, name: string, color: string) {
const material = new StandardMaterial(name, scene)
material.diffuseColor = Color3.FromHexString(color)
material.specularColor = Color3.Black()
return material
}
export function addLowPolyTree(scene: Scene, name: string, position: Vector3, height = 1) {
const root = new TransformNode(name, scene)
root.position = position
const trunk = MeshBuilder.CreateCylinder(`${name}-trunk`, { height: 1.1 * height, diameter: 0.18, tessellation: 6 }, scene)
trunk.parent = root
trunk.position.y = 0.55 * height
trunk.material = makeMat(scene, `${name}-trunk-mat`, '#6b4a2f')
for (let layer = 0; layer < 3; layer += 1) {
const leaves = MeshBuilder.CreateSphere(`${name}-leaves-${layer}`, { diameter: 1.0 - layer * 0.18, segments: 8 }, scene)
leaves.parent = root
leaves.position.y = (1.15 + layer * 0.32) * height
leaves.scaling = new Vector3(1, 0.55, 1)
leaves.material = makeMat(scene, `${name}-leaf-mat-${layer}`, '#3f8f58')
}
root.getChildMeshes().forEach((mesh) => { mesh.isPickable = false })
return root
}
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.
- 8d ago First seen · 92 lines · 0 tokens per session scan A 9f6063f6a586
procedural-scene-props is a skill published in the GitHub repository Shellishack/3d-web-game-dev-skills (5 stars, last pushed 3mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,045 tokens. 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
THREE.Terrain
Use this guide when an agent must build, modify, inspect, or document a terrain scene with THREE.Terrain. The library creates heightmapped Three.js terrain and provides procedural generators, filters, material blending, decoration tools, grass, image conversion, analysis, and seeded randomness.
cesiumjs-models-particles
CesiumJS models, glTF, and particle effects - Model, KHRmeshoptcompression, CAD glTF extensions, EdgeDisplayMode, ModelAnimation, ModelNode, ParticleSystem, emitters, GPM extensions. Use when loading compressed or CAD-style glTF/GLB models, controlling edge rendering, playing model animations, positioning particles…
cesiumjs-materials-shaders
CesiumJS materials and post-processing — Material, Fabric JSON, MaterialAppearance, ImageBasedLighting, PostProcessStage, PostProcessStageLibrary, bloom, depth of field, ambient occlusion, FXAA, tonemapping, BlendingState. Use when defining Fabric materials for entities or primitives, configuring PBR image-based…
battlenet-automation
Automate Battlenet tasks via Rube MCP (Composio). Always search tools first for current schemas.
houdini-gsplat-relighting
Houdini 22 Gaussian Splat relighting skill - prepare GSplats with SideFX Labs, relight them in Solaris/Karma, and rasterize them in Copernicus. Use when an agent must relight a captured splat while retaining typed scene and parameter control. Not for training or importing a new Gaussian Splat.
houdini-pipeline
Pipeline skill — generic, adapter-owned project and shot/package automation: set/query the project root, tag and read portable asset metadata, validate a scene for missing files / bad output dirs / dirty state / cook errors, collect file dependencies into a manifest (no copying), and export a shot/package manifest…