yume: Skill for Claude Code

.claude/skills/yume-topdown-prompt/SKILL.md

yume-topdown-prompt is a skill for Claude Code from kamwoh/yume. It costs 150 tokens per session (2,615 once invoked), scanned B, original, MIT.

A prompt-writing skill for creating clear text instructions for images that show a whole town, city, region, dungeon, or game level from directly above.

In plain words
What is it for?
Use it before calling an image generator to make a top-down map, level-layout reference, or world-planning image.
Why use it?
It helps prevent image tools from producing angled, cinematic views when a flat, map-like overview is needed.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

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 →

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-topdown-prompt/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-topdown-prompt

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/kamwoh/yume/yume-topdown-prompt"><img src="https://agentmods.dev/badge/skills/kamwoh/yume/yume-topdown-prompt.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 150 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,615 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. 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 $0.00150 $0.02615
Opus 5 $0.00075 $0.01307
Sonnet 5 $0.00030 $0.00523
Haiku 4.5 $0.00015 $0.00262

Measured 11d ago against content hash 35eba1baf47c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade B, and why

yume-topdown-prompt scanned grade B with 1 finding 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.

Asks the agent to reveal its instructionsmediumSystem prompt leakage

Directions to print, repeat or translate the system prompt extract configuration the operator did not intend to expose.

Output prompt:
.claude/skills/yume-topdown-prompt/SKILL.md · 302 lines

How it starts

The opening of the file, as written. The whole thing — 302 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/yume-topdown-prompt

You are constructing a text-to-image prompt for a TOP-DOWN ORTHOGRAPHIC map render — a flat 90° bird's-eye view of a town, city, region, dungeon, or level. The prompt's job is to fight the image model's default toward cinematic / angled / atmospheric framing and force it into a clean, readable, map-style render.

When to invoke

  • About to call openai_images / imagen / nanobanana (any generic text-to-image backend) for a top-down view
  • Generating a reference / concept image for a level layout
  • Producing the "what should this place LOOK like?" companion image to a level-design.md or world plan
  • User says "generate a top-down view of X" / "make a map image of Y" / "ortho render of Z" / "aerial of W"

When NOT to invoke

  • Generating compose_map's flat-color SEMANTIC blocks — that pipeline already has its own STRICT_TEMPLATE_PREFIX and is the STABLE 2D harness (see .claude/rules/pipeline-stability.md)
  • Isometric (45°) / oblique / side-scroll / FPS / 3rd-person views — those are different framings
  • HUD wireframes → yume-hud-author
  • Modal screen wireframes → yume-screen-author
  • Single-entity assets (a tree, an NPC) — use the per-entity prompt fields under visual.*_prompt instead

Inputs

  1. Scene brief — one or two sentences. e.g. "medieval fantasy town beside a river" / "post-apoc raider settlement in a desert" / "abandoned subway depot turned bandit camp"
  2. Genre + setting cues (optional) — medieval / sci-fi / ancient / post-apoc / modern / fantasy
  3. Required features (optional) — must-have elements the brief should encode (river, walls, central plaza, specific landmarks)

Output

A single multi-line text-image prompt, 1200–1800 chars, in this exact 8-section structure. Output the prompt as a fenced code block ready to paste; no commentary unless asked.


The 8-section template

1. Opening sentence (~25 words, LOAD-BEARING)

Ultra-detailed {GENRE} {SCENE_TYPE}, perfectly orthographic
top-down aerial view, 90-degree bird's-eye perspective, no horizon,
no cinematic angle, no perspective distortion.

Read the full file on GitHub · 302 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 · 302 lines · 0 tokens per session scan B 35eba1baf47c

Subscribe to this mod's changes

yume-topdown-prompt is a skill published in the GitHub repository kamwoh/yume (21 stars, last pushed 2mo ago), licensed MIT. It adds 150 tokens to every session and 2,615 once invoked, about $0.0007 per session on Opus 5. A static security scan graded it B with 1 finding (asks the agent to reveal its instructions). 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

asset-gen

Generate visual assets from text prompts: PNG images (Gemini / xAI Grok), GLB 3D models (Tripo3D), rigged biped characters, retargeted animations, and frame-by-frame animated sprites, plus background removal. Use whenever a game needs generated art.

htdt/godogen · 63 tokens

artist-self-evolve

Distill stable art-generation patterns from a completed project, so future projects produce comparable assets without re-discovering the prompts. Lead-dispatched only — orchestrator invokes this skill from its self-evolve flow with a game-slug message; do not self-trigger.

tettethu/VibeGame · 62 tokens

vibegame-edit

Iterate broadly on an existing game, on top of vibegame-build. Use when the user asks to change an existing game's art style, genre, or core rules. Not for local tuning such as numbers or game feel. Orchestrator only.

tettethu/VibeGame · 57 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

sprite-sheet

Use when generating animated 2D character sprites laid out as a sprite sheet (grid of frames) — walk cycle, attack frames, idle bob, death sequence. Wires into AnimatedSprite2D / SpriteFrames. Trigger on "sprite sheet", "walk cycle", "attack frames", "animated sprite", "frame-by-frame animation", "2D character…

SummerEngine/summer-engine-agent · 77 tokens