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/master/.claude/skills/yume-scene-class-catalog/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-scene-class-catalog)<a href="https://agentmods.dev/skills/kamwoh/yume/yume-scene-class-catalog"><img src="https://agentmods.dev/badge/skills/kamwoh/yume/yume-scene-class-catalog/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-scene-class-catalog"><img src="https://agentmods.dev/badge/skills/kamwoh/yume/yume-scene-class-catalog.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 | $0.00183 | $0.06103 |
| Opus 5 | $0.00092 | $0.03052 |
| Sonnet 5 | $0.00037 | $0.01221 |
| Haiku 4.5 | $0.00018 | $0.00610 |
Grade A, and why
yume-scene-class-catalog 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.
How it starts
The opening of the file, as written. The whole thing — 513 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/yume-scene-class-catalog
You are the stage-2 author for Yume's text-to-world pipeline. You read a SCENE BRIEF (prose) and a REFERENCE PHOTOREAL AERIAL (stage 1 output) and you produce the structured catalog + prompts that drive stages 3-7.
Every scene gets its own catalog. A medieval town's classes look nothing like a sci-fi colony's, which look nothing like a dungeon's. The lib gives you conventions + a genre cheat-sheet — NOT a fixed class list to copy. Each catalog is dynamic.
When to invoke
- After stage 1 has produced a photoreal top-down reference
- Before stages 3 (semantic map gen) / 4 (heightmap gen) / 5 (extraction)
- Whenever a new scene is being prepped for the pipeline
When NOT to invoke
- For HUD / screen authoring → those are the locked 2D pipelines
- For single-asset prompts → yume-asset-designer
- For per-game GDD writing → yume-game-designer
Inputs
- Scene brief — one or two sentences describing the world
- Reference photoreal aerial — PNG path from stage 1
- Optional — game id, genre hint, required-class list from GDD
Outputs (FOUR files)
| File | Purpose |
|---|---|
/tmp/_class_catalog.json |
Per-scene catalog: classes + hex + intent_type + descriptions + counts |
/tmp/_semantic_map_prompt.txt |
Ready-to-feed at stage 3 (openai_images.edits with reference) |
/tmp/_heightmap_prompt.txt |
Ready-to-feed at stage 4 (openai_images.edits with reference) |
/tmp/_scene_biome_mapping.json |
For ADR 0055 engine wiring — maps each terrain_shader class to a biome shader slot |
The procedure
Step 1 — Read the conventions lib
cat godot/data/lib/semantic_palette.json
Note the THREE things this file gives you:
intent_types— the only TRULY fixed part. Three types:terrain_shader/terrain_displacement/object_placement.hex_picking_algorithm— rules for picking distinct hexes (hue spacing ≥25°, sat/val rules per intent type, avoid 0/255 extremes, etc.) +starting_hue_anchorsfor common terrain (grass / water / sand / snow / lava / etc.) as conventional defaults.genre_cheat_sheets— common-class suggestions per genre (medieval_town, sci_fi_colony, modern_city, dungeon_interior, alien_world, post_apocalyptic, natural_wilderness, underwater). Use as INSPIRATION, not a list to copy.
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.
- 11d ago First seen · 513 lines · 183 tokens per session scan A a70ecb4d98fc
yume-scene-class-catalog is a skill published in the GitHub repository kamwoh/yume (21 stars, last pushed 2mo ago), licensed MIT. It adds 183 tokens to every session and 6,103 once invoked, about $0.0009 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.
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 3, 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.
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…
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".
water-ripple
Use when authoring a water-ripple visual effect — animated normal-distortion ripples on a water plane (or as a Decal) triggered by impacts. Trigger on "water ripple", "ripples on water", "raindrop ripple", "splash ripple", "rain on water", "footstep in puddle", "fish jumps".