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-design/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-design)<a href="https://agentmods.dev/skills/kamwoh/yume/yume-design"><img src="https://agentmods.dev/badge/skills/kamwoh/yume/yume-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/kamwoh/yume/yume-design"><img src="https://agentmods.dev/badge/skills/kamwoh/yume/yume-design.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 | $0.00067 | $0.10732 |
| Opus 5.5 | $0.00027 | $0.04293 |
| Sonnet 5.5 | $0.00013 | $0.02146 |
| Haiku 4.5 | $0.00007 | $0.01073 |
Grade A, and why
yume-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 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 — 816 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/yume-design — text-to-game pipeline
Turn a prose game description into a runnable Yume game.
REVISION BANNER 2026-05-16 (ADR 0009 revision, tasks #109 + #110). The file layout in this skill below still mentions the legacy
world/rules.json+game/goals.jsonsplit in several places. Treat these as the CURRENT shape:
world/rules/*.json(directory of feature modules) — all rule authoring goes here. Filename prefix (01_,02_, ...) sets load order. Engine globs + concatenates alpha-sorted.- Single-file
world/rules.jsonstill works for small games (chess, sokoban). Pick whichever fits the game's size.game/goals.jsonis GONE. Its content moves toworld/rules/13_transitions.json(boot/day-boundary/win/lose signal-rules) +world/rules/14_objectives.json(HUD-text updates + tutorial overlays).- Declarative win:/lose: blocks live in
hud.json(HUD-driven overlay; the engine evaluates them per-frame and shows the win/lose panel automatically).game/flow.json(multi-level progression) is unchanged.- Skill ownership: yume-systems-designer writes all rule files. It also writes the declarative HUD win/lose blocks and game/flow.json (it absorbed yume-game-rules-designer on 2026-10-16).
Usage
/yume-design <prose description of the game>
/yume-design "a farming sim where moonlight grows crops faster" --style=pixel-art --name=<your-game>
/yume-design "a roguelike where vampires steal HP from light sources" --with-assets
/yume-design "explore a fortified river town and collect 5 lost relics" --scene --with-assets
Args (parsed from the user's prompt after /yume-design):
<prose>— the game description (free-form). Required.--style=<value>—pixel-art/low-poly-3d/ascii/realistic. Defaults to user-stated preference in prose, elsepixel-art.--name=<slug>— game folder name. Defaults to a slug derived from the prose (auto-suggest: ask user to confirm).--scene— generate a 3D world for the game first (the World layer, viacompose_world): a semantic-map + heightmap-driven map with biome ground, water, and placed environment props. The game's mechanics then layer ONTO that world. Default: no generated world (the game owns its own flat scene). NeedsOPENAI_API_KEY— if absent, the flag is DROPPED (graceful degrade to a flat code-draw scene + a warning), never a crash. See Phase 0 step 2a.--with-assets— after the game is built, auto-run the AI asset pipeline (tools.yume_assetgen) to replace code-draw visuals with generated textures + meshes. Default: skip (code-draw fallback). Needs an image key +TRIPO_API_KEY— if absent, the flag is DROPPED (graceful degrade to code-draw visuals + a warning).
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 Changed · -139 lines · -96 tokens per session 58f269785994
- 1mo ago First seen · 955 lines · 163 tokens per session scan A 9b2a48d74a47
yume-design is a skill published in the GitHub repository kamwoh/yume (25 stars, last pushed 10d ago), licensed MIT. It adds 67 tokens to every session and 10,732 once invoked, about $0.0003 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 2026-08-30.
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 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.