yume: Skill for Claude Code

.claude/skills/yume-create-scene/SKILL.md

yume-create-scene is a skill for Claude Code from kamwoh/yume. It costs 123 tokens per session (2,955 once invoked), scanned A, original, MIT.

A pipeline that turns a written scene idea into a runnable 3D game-world scene. It creates reference images, maps terrain, places scene elements, builds a basic presentation shell, and can optionally generate 3D assets.

In plain words
What is it for?
Use it to build Yume scenes from prose, including terrain maps, height data, placed objects, camera and player setup, lighting, and optional Tripo assets.
Why use it?
It coordinates the many separate steps needed to turn prose into a usable scene, keeping the visual style anchored to one reference.

Skill for Claude Code

Written for Claude Code: installed under .claude/. Also seen: reads .claude/ paths.

This is kamwoh/yume's own configuration. It tells Claude Code how to work on yume itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything yume configures →

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is ./scripts/play.sh <name> --capture # or godot ... --capture-after.

View source ↗ kamwoh/yume
Reuse

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.

Copy the file
curl -O https://raw.githubusercontent.com/kamwoh/yume/master/.claude/skills/yume-create-scene/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/kamwoh/yume

Made for: Claude Code.

Wrote 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.

agentmods badge for yume-create-scene

README.md
[![agentmods](https://agentmods.dev/badge/skills/kamwoh/yume/yume-create-scene/github.svg)](https://agentmods.dev/skills/kamwoh/yume/yume-create-scene)
Your own site
<a href="https://agentmods.dev/skills/kamwoh/yume/yume-create-scene"><img src="https://agentmods.dev/badge/skills/kamwoh/yume/yume-create-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.

agentmods 80×15 button for yume-create-scene

Your own site · 80×15
<a href="https://agentmods.dev/skills/kamwoh/yume/yume-create-scene"><img src="https://agentmods.dev/badge/skills/kamwoh/yume/yume-create-scene.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 123 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,955 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00123 $0.02955
Opus 5 $0.00062 $0.01477
Sonnet 5 $0.00025 $0.00591
Haiku 4.5 $0.00012 $0.00296

Measured 11d ago against content hash e2318faafe4e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

yume-create-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 11d 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.

.claude/skills/yume-create-scene/SKILL.md · 211 lines

How it starts

The opening of the file, as written. The whole thing — 211 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/yume-create-scene

You are the orchestrator for Yume's text-to-3D-world pipeline. Given a prose scene pitch, you produce a runnable scene by authoring the one LLM-in-the-loop input (the class catalog) and then running the deterministic orchestrator.

The pipeline (what compose_scene chains)

prose + catalog
  ├─ 1. HERO reference        openai text→image      (the art-direction anchor)
  ├─ 2. ORTHOGRAPHIC top-down openai /edits on HERO   (hero-conditioned: one style)
  ├─ 3. SEMANTIC map          openai /edits on ORTHO  (flat-colour classification)
  ├─ 4. HEIGHTMAP             openai /edits on ORTHO  (grayscale elevation)
  ├─ 5. compose_world         (SCENE only: defs + flat placements in
  │                            entities/auto_gen.json, biome ground, water)
  │       └─ extraction: generic strategy dispatch, OR a per-scene
  │          authored `data/<game>/extract.py` if present (see § Per-scene
  │          extractor)
  ├─ 6. compose_shell         (FLAT shell: camera/player/input/lighting/.tscn,
  │                            singletons in entities/shell_singletons.json)
  └─ 7. [--assets] yume_assetgen (Tripo .glb for asset_source:tripo classes)

Every stage after the catalog is deterministic — your job is the catalog + running the tool + the visual-qa loop.

Scene-only + flat (ADR 0067). compose_world is the scene layer — it writes ONLY the 3D environment (scene.json, entities/auto_gen.json with defs + flat initial_instances, biome ground, water, road graph, terrain assets). It writes no game/flow.json, no levels/, no world/state.json (those are game-domain). The scene boots FLAT — the engine globs entities/*.json; world_boot._load_content's else-branch needs no flow.json. compose_shell then writes its singletons to a flat entities/shell_singletons.json. Keeping the scene in its own lane is what lets /yume-design --scene reuse compose_world as the World layer without a clobber (see § Used as the World layer below).

Read the full file on GitHub · 211 lines

Changes

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.

  1. 11d ago First seen · 211 lines · 123 tokens per session scan A e2318faafe4e

Subscribe to this mod's changes

yume-create-scene is a skill published in the GitHub repository kamwoh/yume (21 stars, last pushed 2mo ago), licensed MIT. It adds 123 tokens to every session and 2,955 once invoked, about $0.0006 per session on Opus 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 2026-08-30.

Related

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…

buiphucminhtam/forgewright · 52 tokens

game-engineer

Meta-skill for game development that orchestrates specialized engine skills. Routes to the appropriate game engine skill (Unity, Unreal, Godot, Roblox, Phaser 3, Three.js) based on project requirements. Provides unified game development workflow.

buiphucminhtam/forgewright · 52 tokens

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.

tettethu/VibeGame · 50 tokens

fps-controller

Use when building an FPS, first-person movement, or a 3D character that walks, jumps, and reacts to external forces — production-quality first-person controller with WASD, mouse look, jump, coyote time, jump buffering, air control, and external-velocity handling. Trigger on "FPS", "first-person", "WASD", "character…

SummerEngine/summer-engine-agent · 89 tokens

smoke

Use when authoring a smoke visual effect — a slow-rising column or puff of soft particles built with a noise + density falloff shader on a quad mesh, GPUParticles3D. Trigger on "smoke", "smoke trail", "puff", "chimney smoke", "smoke from a fire", "steam", "fog cloud", "explosion smoke".

SummerEngine/summer-engine-agent · 81 tokens

skybox-panorama

Use when generating a 360° panoramic sky image for use as a Sky resource (PanoramaSkyMaterial) in a 3D scene. Equirectangular projection, 2:1 aspect. Wires into WorldEnvironment.sky. Trigger on "skybox", "sky panorama", "360 background", "environment sky", "HDRI sky", "panoramic background", "panorama sky".

SummerEngine/summer-engine-agent · 87 tokens