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/commands/hermeticormus/libregamedev-claude-code/procgen)<a href="https://agentmods.dev/commands/hermeticormus/libregamedev-claude-code/procgen"><img src="https://agentmods.dev/badge/commands/hermeticormus/libregamedev-claude-code/procgen/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/commands/hermeticormus/libregamedev-claude-code/procgen"><img src="https://agentmods.dev/badge/commands/hermeticormus/libregamedev-claude-code/procgen.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 | $0.00017 | $0.00802 |
| Opus 5.5 | $0.00007 | $0.00321 |
| Sonnet 5.5 | $0.00003 | $0.00160 |
| Haiku 4.5 | $0.00002 | $0.00080 |
Grade A, and why
procgen 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 — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/procgen
Procedural content generation: terrain, dungeons, caves, tile maps, and content placement.
Trigger
/procgen [action] [target]
Actions
terrain
Generate noise-based terrain or heightmaps.
/procgen terrain "2D sidescroller background with rolling hills"
/procgen terrain "top-down world map with biomes: forest, desert, water"
/procgen terrain "3D heightmap with mountain peaks and valleys, 256x256"
Output: FastNoiseLite configuration, heightmap sampling function, biome thresholds.
dungeon
Generate room-based dungeon or cave layouts.
/procgen dungeon "BSP dungeon 80x50 grid, 8-15 rooms, connect all rooms"
/procgen dungeon "cellular automata cave system, 60x40, 5 smoothing passes"
/procgen dungeon "drunk walk corridors for underground tunnels"
Output: Typed GDScript generator class with seed parameter, room list, corridor list, TileMap fill method.
populate
Place enemies, items, and events in generated spaces.
/procgen populate "enemies in dungeon rooms scaled by difficulty 0-1"
/procgen populate "loot tables for 3 room types: treasure, combat, rest"
/procgen populate "guaranteed key item in first room, exit in last room"
Output: RoomPopulator with derived seeds, weighted random placement, quota enforcement.
validate
Add solvability and quality checks to a generator.
/procgen validate "check dungeon has path from spawn to exit"
/procgen validate "verify enemy count within 3-8 range per level"
/procgen validate "stress test: generate 100 levels and report failures"
Output: BFS flood fill validator, stat assertions, batch generation test loop.
Examples
Generating a seeded dungeon with validation:
/procgen dungeon "BSP dungeon for roguelike, 100x60, must have guaranteed spawn-to-exit path"
Produces: BSPDungeon.generate(bounds, seed) with rooms + corridors, plus DungeonValidator.is_solvable() check; if unsolvable, increments seed and retries.
Terrain with biomes:
/procgen terrain "top-down world with ocean (< 0.3), beach (0.3-0.4), grass (0.4-0.7), mountain (> 0.7)"
Produces: FastNoiseLite config, get_biome(x, y) -> StringName function using noise thresholds, TileMap tile assignment.
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 · 97 lines · 17 tokens per session scan A 4cc37f436274
procgen is a command published in the GitHub repository HermeticOrmus/LibreGameDev-Claude-Code (5 stars, last pushed 15d ago), licensed MIT. It adds 17 tokens to every session and 802 once invoked, about $0.0001 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 commands, from other repositories
build-and-compilation
These commands drive the build/compile/test dev loop, plus build configuration: triggering Player builds and reading the resulting BuildReport, switching the active build target, enumerating targets, reading/writing EditorUserBuildSettings, and listing Build Profiles. Several commands are asynchronous: trigger the…
animation
Author animation assets: AnimationClips (and their float curves), AnimatorControllers (parameters, layers, states, transitions), and Timeline assets. Create commands write under the authoring root and follow the shared confirm/dryrun convention.
assets-and-files
Commands for creating, importing, moving, copying, renaming, deleting and finding project assets, plus folder and text-file operations. Every agent-supplied path is funnelled through the authoring-root sandbox (it rejects ../ and out-of-project writes); destructive or overwriting operations require confirm=true and…
gameobjects-and-components
Commands for creating GameObjects, querying the scene hierarchy, mutating the core GameObject/Transform surface, and adding/removing components and editing their serialized properties. Scene mutations are wrapped in Unity's Undo system (so a multi-step action reverts as one collapsible step) and are blocked during…
project-settings
Read and change a representative slice of Unity's project-wide settings (Audio, Graphics, Input, Physics, Player, Quality, Tags & Layers, Time). get commands read a group's current values into a ProjectSettingsResponse; set commands mutate them through the shared confirm/dryrun convention, so confirm=true is required…
baking
Bake and clear precomputed scene data: lightmaps, NavMesh, and occlusion culling. Each bake runs asynchronously (returns immediately) — poll the matching bakestatus until completed. The clear commands are destructive and require confirm=true. The getsettings / setsettings pairs read and tune the bake parameters.