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 agentmods add skills/plausibleventures/lattice/worldnpx skills add plausibleventures/lattice --skill worldgit clone --depth 1 https://github.com/plausibleventures/latticeWrote 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/plausibleventures/lattice/world)<a href="https://agentmods.dev/skills/plausibleventures/lattice/world"><img src="https://agentmods.dev/badge/skills/plausibleventures/lattice/world.svg" alt="Measured on agentmods" 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 | $0.00080 | $0.05060 |
| Opus 5 | $0.00040 | $0.02530 |
| Sonnet 5 | $0.00016 | $0.01012 |
| Haiku 4.5 | $0.00008 | $0.00506 |
Grade A, and why
world 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 4d 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 — 394 lines — stays where its author put it; the contents beside it link to each section on GitHub.
The world
Three coordinate spaces — grid, world, screen — and every operation here is only correct because it knows which one it is in. Game code never converts between them by hand; every conversion is a named function that takes an output parameter.
Two facts that decide most of what follows:
- Tile lookup floors, never rounds. Rounding snaps to the nearest lattice vertex and picks the wrong tile for three quarters of every diamond.
- Elevation lives on grid vertices, not tile centers. Adjacent tiles therefore share their
corner values exactly and cannot leave a seam — and once
zexists the projection is no longer invertible, so picking has to be terrain-aware. That is the biggest trap in this skill and it has its own section.
Ground, and height on it
import { TileGrid, footprintBase, heightAt, slopeAt, tileSourceOf } from '@latticekit/iso';
import type { Footprint, HeightField } from '@latticekit/iso';
import { fbm2 } from '@latticekit/core';
const W = 96;
const H = 96;
// One value per grid VERTEX, so the grid is one wider than the tile map in each axis.
const heights = new TileGrid(W + 1, H + 1);
heights.fillFrom((gx, gy) => Math.max(0, fbm2(1234, gx * 0.04, gy * 0.04, 4) * 8));
/** `stepPx` is world pixels per height unit — the one conversion between the game's units
* and the projection's. 8 means a ridge of 5 units stands 40 world pixels proud. */
const land: HeightField = { heights, stepPx: 8 };
/** The tallest ground on the map, in world pixels. Camera framing and the terrain cull both
* need it, and both are silently wrong without it. Compute it once, at generation. */
export const MAX_HEIGHT_PX = 8 * 8;
export function groundUnder(f: Footprint): number {
// The MAXIMUM vertex height under the footprint, not the mean: a building resting on the mean
// of a slope has one corner buried in the hill and one floating.
return footprintBase(land, f);
}
export function walkCost(gx: number, gy: number): number {
return 1 + slopeAt(land, gx, gy) * 2; // steeper ground costs more to cross
}
export function surfaceAt(gx: number, gy: number): number {
return heightAt(land, gx, gy); // bilinear, in world pixels
}
/** An unbounded world: a function is defined everywhere, so it has no edge and costs no
* memory. Everything is a pure function of (seed, gx, gy) — see the warning below. */
export const endless: HeightField = {
heights: tileSourceOf((gx, gy) => Math.max(0, fbm2(1234, gx * 0.04, gy * 0.04, 4) * 8)),
stepPx: 8,
};
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.
- 4d ago First seen · 394 lines · 80 tokens per session scan A 6ab06c0d3ba3
world is a skill published in the GitHub repository plausibleventures/lattice (35 stars, last pushed 12d ago), licensed MIT. It adds 80 tokens to every session and 5,060 once invoked, about $0.0004 per session on Opus 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 2026-08-30.
Other skills, from other repositories
phaser3-engineer
!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/input-validation.md 2>/dev/null || true !cat skills/shared/protocols/tool-efficiency.md 2>/dev/null || true !cat…
dedicated-server
Use when building dedicated servers — headless export, server architecture, lobby management, and deployment.
dialogue-manager
Use when using the Dialogue Manager addon — .dialogue files with titles, responses, conditions and mutations, runtime balloons, and C# support.
event-bus
Use when implementing decoupled communication between nodes — global EventBus autoload with typed signals.
godot-optimization
Use when optimizing Godot games — profiler, draw calls, physics tuning, memory management, and common bottlenecks.
limboai
Use when using the LimboAI addon — behavior trees and hierarchical state machines (C++ GDExtension) with a visual editor, BTTask subclassing, and a blackboard.