Borrowing it
Nothing to install: this file belongs to kamwoh/yume. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/kamwoh/yume/dev/.claude/skills/yume-infinigen-scene/SKILL.mdgit clone --depth 1 https://github.com/kamwoh/yumeWrote 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/kamwoh/yume/yume-infinigen-scene)<a href="https://agentmods.dev/skills/kamwoh/yume/yume-infinigen-scene"><img src="https://agentmods.dev/badge/skills/kamwoh/yume/yume-infinigen-scene/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/kamwoh/yume/yume-infinigen-scene"><img src="https://agentmods.dev/badge/skills/kamwoh/yume/yume-infinigen-scene.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 | $0.00058 | $0.01800 |
| Opus 5.5 | $0.00023 | $0.00720 |
| Sonnet 5.5 | $0.00012 | $0.00360 |
| Haiku 4.5 | $0.00006 | $0.00180 |
Grade A, and why
yume-infinigen-scene 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.
How it starts
The opening of the file, as written. The whole thing — 142 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/yume-infinigen-scene
You orchestrate Yume's Infinigen World-layer pipeline (ADR 0074). From a
target game folder + a scene type, you produce a runnable, walkable
realistic natural world: a native-scale terrain ground with ecological
scatter (trees, rocks) drawn from a generated asset library. Everything is
real Infinigen geometry baked to .glb; the engine renders it through
existing primitives (visual.normalize:false + trimesh collider, ADR 0062).
The tool (tools/yume_infinigen/) does the heavy lifting; you drive it,
integrate the output, and run the visual + walkability gates.
When to invoke
- ✅ "Generate a realistic mountain/canyon/desert scene for
<game>." - ✅ "Make an Infinigen world to build my game onto."
- ✅ "Scatter real trees and rocks on procedural terrain."
- ❌ HUD/screen authoring →
yume-hud-author/yume-screen-author. - ❌ A single asset (one rock) →
python -m tools.yume_infinigen <game> --factory <X>directly. - ❌ A stylized hero-image-driven scene →
yume-create-scene(openai/Tripo). - ❌ A 2D semantic-map level →
yume-map-author.
Prerequisites (check FIRST, fail loud)
The backend is an EXTERNAL heavy dependency (its own py3.11 + bpy), like
Tripo. Two env vars must point at it; absent → STOP and tell the user:
export YUME_INFINIGEN_PYTHON=$HOME/infinigen311/bin/python # 3.11 + bpy
export YUME_INFINIGEN_REPO=/path/to/infinigen # the source repo
Terrain also needs a one-time build the minimal install skips (SDF
kernels, glm→SoilMachine, marching_cubes ext, landlab). If --terrain
fails with a missing .so / LutProvider / landlab, run the build steps
in tools/yume_infinigen/README.md § "One-time terrain build". Caves are
auto-patched at runtime.
The pipeline (4 steps)
1. ASSETS python -m tools.yume_infinigen <game> --factory <F> --seeds 0,1,2
2. TERRAIN python -m tools.yume_infinigen <game> --terrain --scene-type <T>
(also extracts ecological scatter → places step-1 assets)
3. INTEGRATE clear scene.json ground.mesh so the terrain IS the ground
4. VERIFY live --capture (visual gate) + a drop-a-body walkability check
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.
- 12d ago First seen · 142 lines · 58 tokens per session scan A a322e69169b6
yume-infinigen-scene is a skill published in the GitHub repository kamwoh/yume (25 stars, last pushed 10d ago), licensed MIT. It adds 58 tokens to every session and 1,800 once invoked, about $0.0002 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 2026-10-17.
Other skills, from other repositories
godot-engineer
!cat skills/shared/protocols/3d-spatial-foundations.md 2>/dev/null || true !cat skills/shared/game-visual-foundations.md 2>/dev/null || echo "=== Visual Foundations not loaded ===" !cat skills/shared/protocols/ux-protocol.md 2>/dev/null || true !cat skills/shared/protocols/game-test-protocol.md 2>/dev/null || true…
game-engineer
Meta-skill for game development that orchestrates specialized engine skills. Routes to the appropriate game engine skill (Unity, Unreal, Godot, Roblox, Phaser 4, Three.js) based on project requirements. Provides unified game development workflow.
self-evolve
Capture reusable patterns from a finished project and lift them into framework-level priors (contracts, modules, skeletons) that future projects inherit. Run only when the user explicitly requests self-evolution; the orchestrator executes the workflow.
qa-plan
Generate a QA test plan for a sprint or feature. Reads GDDs and story files, classifies stories by test type (Logic/Integration/Visual/UI), and produces a structured test plan covering automated tests required, manual test cases, smoke test scope, and playtest sign-off requirements. Run before sprint begins or when…
asset-audit
Audits game assets for compliance with naming conventions, file size budgets, format standards, and pipeline requirements. Identifies orphaned assets, missing references, and standard violations.
hybrid-prototype
Fast-lane prototype skill for the hybrid workflow. Builds a playable prototype in 2-3 days with minimal process overhead. Designed for discovery phase.