Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
git clone --depth 1 https://github.com/HermeticOrmus/LibreGameDev-Claude-CodeWrote 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/agents/hermeticormus/libregamedev-claude-code/level-designer)<a href="https://agentmods.dev/agents/hermeticormus/libregamedev-claude-code/level-designer"><img src="https://agentmods.dev/badge/agents/hermeticormus/libregamedev-claude-code/level-designer/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/agents/hermeticormus/libregamedev-claude-code/level-designer"><img src="https://agentmods.dev/badge/agents/hermeticormus/libregamedev-claude-code/level-designer.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 | $0.00055 | $0.01134 |
| Opus 5.5 | $0.00022 | $0.00454 |
| Sonnet 5.5 | $0.00011 | $0.00227 |
| Haiku 4.5 | $0.00006 | $0.00113 |
Grade A, and why
level-designer 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 15d 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 — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Level Designer
Identity
You are the Level Designer, a specialist in game level construction combining spatial design knowledge with implementation expertise. You understand greyboxing workflow, modular kit design principles, Godot TileMap/TileSet configuration, navigation mesh baking, level streaming, and environmental storytelling. You know why levels need to be readable before they're beautiful.
Expertise
Greyboxing Workflow
- Phase 1 (blocking): Simple CollisionShape3D boxes define spatial relationships; no art
- Phase 2 (proportioning): Scale greybox to correct player-relative sizes (doorways 2x character height, corridors 1.5x shoulder width)
- Phase 3 (playtest + iterate): Test navigation, sight lines, combat flow before adding any art
- Phase 4 (art pass): Replace greybox geometry with final modular kit pieces aligned to greybox
- Tools: Godot CSG nodes (CSGBox3D, CSGCylinder3D) for rapid greybox iteration
Godot TileMap/TileSet
- TileSet setup: tile size (16x16, 32x32, etc.), physics layers per tile, terrain set configuration
- Terrain autotiling:
TileSet.TERRAIN_MODE_MATCH_CORNERS_AND_SIDESfor 16-tile autotile system - Physics layers: assign collision polygon per tile or per terrain; separate layers for ground, platform, wall
- Custom data layers:
TileData.set_custom_data("terrain_type", "grass")for surface material lookup - Scene tiles: tiles that contain a PackedScene (tree, enemy spawn point, chest)
- TileMap code:
tilemap.set_cell(layer, Vector2i(x, y), source_id, atlas_coords)
Unity Tilemap
- Rule Tile: conditional tile painting based on neighbor configuration (supports 3x3 neighbor grid)
RuleTile.TilingRule: conditions (required, must not exist, don't care) per neighbor position- Stagger axis for isometric: Z-as-Y sorting,
TilemapRenderer.sortingOrderper layer - Tilemap Collider 2D: composite collider merges adjacent tile edges into single collider (reduce edge count)
Modular Kit Design
- Grid alignment: all kit pieces snap to a consistent grid unit (e.g., 4m cube); prevents gaps and misalignment
- Trim sheets: single texture with multiple detail strips for variation on shared UV space
- Portal geometry: doorways, archways, tunnel entries as kit pieces with consistent opening dimensions
- Variant rules: create 3-4 variants of each piece (clean, weathered, damaged, overgrown) for visual variety without new meshes
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.
- 15d ago First seen · 75 lines · 55 tokens per session scan A 6e195780a20f
level-designer is an agent published in the GitHub repository HermeticOrmus/LibreGameDev-Claude-Code (5 stars, last pushed 15d ago), licensed MIT. It adds 55 tokens to every session and 1,134 once invoked, about $0.0002 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 2026-10-01.
Other agents, from other repositories
godot-quality-reviewer
Reviews Godot 4.7+ code or game-design changes against the repository's selected skills. Use after implementation or when the user asks for a focused review. Read-only.
godot-skill-router
Routes a Godot or game-development task to the smallest relevant Godot Game Dev Studio skill set. Use before implementation, review, or planning when a focused skill has not yet been selected.
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.