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.
npx skills add HermeticOrmus/LibreGameDev-Claude-Code --skill procgen-patternsgit 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/skills/hermeticormus/libregamedev-claude-code/procgen-patterns)<a href="https://agentmods.dev/skills/hermeticormus/libregamedev-claude-code/procgen-patterns"><img src="https://agentmods.dev/badge/skills/hermeticormus/libregamedev-claude-code/procgen-patterns/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/hermeticormus/libregamedev-claude-code/procgen-patterns"><img src="https://agentmods.dev/badge/skills/hermeticormus/libregamedev-claude-code/procgen-patterns.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 | $0.00047 | $0.02898 |
| Opus 5.5 | $0.00019 | $0.01159 |
| Sonnet 5.5 | $0.00009 | $0.00580 |
| Haiku 4.5 | $0.00005 | $0.00290 |
Grade A, and why
procgen-patterns 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 20d 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 — 307 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Procgen Patterns
FastNoiseLite Terrain Generation
# Layered noise terrain heightmap - Godot 4
class_name TerrainGenerator extends Node
@export var width: int = 128
@export var height: int = 128
@export var seed: int = 0
@export var base_frequency: float = 0.01
@export var octaves: int = 5
@export var lacunarity: float = 2.0 # Frequency multiplier per octave
@export var gain: float = 0.5 # Amplitude multiplier per octave
func generate_heightmap() -> Image:
var noise := FastNoiseLite.new()
noise.noise_type = FastNoiseLite.TYPE_SIMPLEX
noise.fractal_type = FastNoiseLite.FRACTAL_FBM
noise.seed = seed
noise.frequency = base_frequency
noise.fractal_octaves = octaves
noise.fractal_lacunarity = lacunarity
noise.fractal_gain = gain
var img := Image.create(width, height, false, Image.FORMAT_R8)
for y in height:
for x in width:
var value := (noise.get_noise_2d(x, y) + 1.0) * 0.5 # Normalize to [0,1]
img.set_pixel(x, y, Color(value, 0, 0))
return img
func sample_height(world_pos: Vector2) -> float:
# Used at runtime for placing objects at correct heights
var noise := FastNoiseLite.new()
noise.seed = seed
noise.frequency = base_frequency
return (noise.get_noise_2d(world_pos.x, world_pos.y) + 1.0) * 0.5
BSP Dungeon Generator
# Binary Space Partitioning dungeon - produces structured room layouts
class_name BSPDungeon extends RefCounted
class BSPNode:
var rect: Rect2i
var left: BSPNode
var right: BSPNode
var room: Rect2i # Only set on leaf nodes
func _init(r: Rect2i) -> void:
rect = r
const MIN_LEAF_SIZE := 10
const MIN_ROOM_SIZE := 4
var _rng: RandomNumberGenerator
var _rooms: Array[Rect2i] = []
var _corridors: Array[Array] = [] # Array of [Vector2i, Vector2i] pairs
func generate(bounds: Rect2i, seed: int) -> void:
_rng = RandomNumberGenerator.new()
_rng.seed = seed
_rooms.clear()
_corridors.clear()
var root := BSPNode.new(bounds)
_split(root, 0)
_create_rooms(root)
_connect_rooms(root)
func _split(node: BSPNode, depth: int) -> void:
if depth > 5:
return
var split_horizontal := _rng.randi() % 2 == 0
var min_size := MIN_LEAF_SIZE * 2
if node.rect.size.x < min_size and node.rect.size.y < min_size:
return # Too small to split
if node.rect.size.x > node.rect.size.y:
split_horizontal = false # Force vertical split for wide nodes
var split_pos: int
if split_horizontal:
split_pos = _rng.randi_range(MIN_LEAF_SIZE, node.rect.size.y - MIN_LEAF_SIZE)
node.left = BSPNode.new(Rect2i(node.rect.position, Vector2i(node.rect.size.x, split_pos)))
node.right = BSPNode.new(Rect2i(
node.rect.position + Vector2i(0, split_pos),
Vector2i(node.rect.size.x, node.rect.size.y - split_pos)
))
else:
split_pos = _rng.randi_range(MIN_LEAF_SIZE, node.rect.size.x - MIN_LEAF_SIZE)
node.left = BSPNode.new(Rect2i(node.rect.position, Vector2i(split_pos, node.rect.size.y)))
node.right = BSPNode.new(Rect2i(
node.rect.position + Vector2i(split_pos, 0),
Vector2i(node.rect.size.x - split_pos, node.rect.size.y)
))
_split(node.left, depth + 1)
_split(node.right, depth + 1)
func _create_rooms(node: BSPNode) -> void:
if node.left == null and node.right == null:
# Leaf: create a room with padding
var padding := 1
var max_w := node.rect.size.x - padding * 2
var max_h := node.rect.size.y - padding * 2
if max_w < MIN_ROOM_SIZE or max_h < MIN_ROOM_SIZE:
return
var w := _rng.randi_range(MIN_ROOM_SIZE, max_w)
var h := _rng.randi_range(MIN_ROOM_SIZE, max_h)
var x := node.rect.position.x + padding + _rng.randi_range(0, max_w - w)
var y := node.rect.position.y + padding + _rng.randi_range(0, max_h - h)
node.room = Rect2i(x, y, w, h)
_rooms.append(node.room)
return
if node.left:
_create_rooms(node.left)
if node.right:
_create_rooms(node.right)
func _connect_rooms(node: BSPNode) -> void:
if node.left == null or node.right == null:
return
var left_room := _get_room(node.left)
var right_room := _get_room(node.right)
if left_room != Rect2i() and right_room != Rect2i():
var start := left_room.get_center()
var end := right_room.get_center()
_corridors.append([start, end]) # L-shaped corridor between centers
_connect_rooms(node.left)
_connect_rooms(node.right)
func _get_room(node: BSPNode) -> Rect2i:
if node.room != Rect2i():
return node.room
var left_room := Rect2i()
var right_room := Rect2i()
if node.left:
left_room = _get_room(node.left)
if node.right:
right_room = _get_room(node.right)
if left_room == Rect2i():
return right_room
return left_room
func get_rooms() -> Array[Rect2i]:
return _rooms
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.
- 20d ago Changed · +5 lines · +47 tokens per session b6d5eea98f58
- 1mo ago First seen · 302 lines · 0 tokens per session scan A 3389d941f72b
procgen-patterns is a skill published in the GitHub repository HermeticOrmus/LibreGameDev-Claude-Code (5 stars, last pushed 20d ago), licensed MIT. It adds 47 tokens to every session and 2,898 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 2026-08-31.
Other skills, from other repositories
unity-pipeline
Drive a running Unity Editor or development Player from the command line via the unity-pipeline package — install the package, keep the editor ticking while unfocused, run the edit→recompile→runtests loop, evaluate C#, and hot-reload files at runtime. Use when an agent needs to control a live Unity instance, automate…
html-to-ugui
A pipeline for turning HTML interface prototypes into Unity UGUI Prefabs, which are reusable Unity interface objects. It uses browser-rendered layout data to preserve positions, images, text, controls, and device-adaptation intentions.
luban-dev
A guide for Luban, a game-configuration tool that turns spreadsheets and schemas into C# code and binary data for a TEngine project.
tengine-dev
A development guide for TEngine, a framework used to build Unity games. It covers the framework’s modules, user interfaces, events, asset loading, hot updates, configuration, and related tools.
unity-cli
A command-line tool for checking and operating a Unity project, including its open scenes, game objects, assets, tests, compilation, and build checks. Unity is a game engine and editor.
godot-master
Consolidated expert library for professional Godot 4.7+ game and application development. Orchestrates 94 Domain Skills through architectural workflows, anti-pattern catalogs, performance budgets, and Server API patterns. Use when: (1) starting a new Godot project, (2) designing game or app architecture, (3) building…