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-topdown-prompt/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-topdown-prompt)<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.
<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>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 | $0.00051 | $0.02523 |
| Opus 5.5 | $0.00020 | $0.01009 |
| Sonnet 5.5 | $0.00010 | $0.00505 |
| Haiku 4.5 | $0.00005 | $0.00252 |
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 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.
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: How it starts
The opening of the file, as written. The whole thing — 305 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_PREFIXand 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.*_promptinstead
Inputs
- 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"
- Genre + setting cues (optional) — medieval / sci-fi / ancient / post-apoc / modern / fantasy
- 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.
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 · +3 lines · +51 tokens per session e176a751531a
- 1mo ago First seen · 302 lines · 0 tokens per session scan B 35eba1baf47c
yume-topdown-prompt is a skill published in the GitHub repository kamwoh/yume (25 stars, last pushed 10d ago), licensed MIT. It adds 51 tokens to every session and 2,523 once invoked, about $0.0002 per session on Opus 5.5. 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.
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.