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-mesh-author/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-mesh-author)<a href="https://agentmods.dev/skills/kamwoh/yume/yume-mesh-author"><img src="https://agentmods.dev/badge/skills/kamwoh/yume/yume-mesh-author/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-mesh-author"><img src="https://agentmods.dev/badge/skills/kamwoh/yume/yume-mesh-author.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 | $0.00064 | $0.01488 |
| Opus 5.5 | $0.00026 | $0.00595 |
| Sonnet 5.5 | $0.00013 | $0.00298 |
| Haiku 4.5 | $0.00006 | $0.00149 |
Grade A, and why
yume-mesh-author 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 — 130 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/yume-mesh-author
You author ONE code-built mesh for godot/data/meshes.json (ADR 0083).
A code-built mesh is a list of parts: Godot primitives, CSG ops (lathe,
extrude, sweep) and cuts. It costs nothing to make, it is
deterministic, and its pivot and size come from its data.
Inputs and outputs
This skill runs as a forked skill (ADR 0082). It runs in its own subagent and does not see the chat history. The arguments and the files below carry all the input.
- Arguments. A mesh name, a text brief in quotes, and optional
flags. Example:
lamp_post_3d "iron street lamp, 3 m, a lantern on a curved arm, warm glow" --image=docs/games/x/concepts/lamp.png --draft-only. The brief can name a size, a base (on the ground or hovering), a front, a palette and a part budget. - Output.
- The mesh entry goes into
godot/data/meshes.json. With--draft-only, it stays in the draft file only. - A note goes to
docs/reviews/mesh-<name>.md. It holds the brief, the part plan, the base and front choices, the review of each round, and the final verdict.
- The mesh entry goes into
- Return. Reply in 200 words or fewer: the verdict, the mesh name,
the sheet path, and the top 3 notes for the caller. The verdict is
accept, orneeds-humanafter 3 rounds.
Rules
- Read
reference/mesh-ops.mdfirst. It lists every op, its fields, its local frame, the CSG limits and 3 worked examples. - Build in unit space. The mesh is about 1 unit tall, and
state.scalesets the real size. For a tall thin object, keep its real proportions in the parts, for example 0.12 x 1.0 x 0.12. - Base and front are your choice, and you write them down. Most floor props sit on y = 0. A hovering object, a projectile or a sunk rock can differ. Godot forward is -Z, so give actors and signs a -Z front unless the brief says otherwise. Record both choices in the note.
- Use the
materialsblock for shared materials (wood,iron,stone). Add a new material only when no existing one fits. Use$paramcolors for parts that a game tints per instance. - Budget: 4-30 parts. Silhouette first, then detail. Detail that is smaller than 3% of the mesh height does not show at game distance. Leave it out.
- A part with
namestays a separate node for animation. Give a part a name only when an animation needs it. - Never copy a mesh from a commercial game. Describe shapes, not brands.
What ships with it
1 file 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 First seen · 130 lines · 64 tokens per session scan A 61b2e70a5c6f
yume-mesh-author is a skill published in the GitHub repository kamwoh/yume (25 stars, last pushed 10d ago), licensed MIT. It adds 64 tokens to every session and 1,488 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 2026-10-17.
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.