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/inputnpx skills add plausibleventures/lattice --skill inputgit clone --depth 1 https://github.com/plausibleventures/latticeWhat 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 | $0.00090 | $0.04532 |
| Opus 5 | $0.00045 | $0.02266 |
| Sonnet 5 | $0.00018 | $0.00906 |
| Haiku 4.5 | $0.00009 | $0.00453 |
Grade A, and why
input 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 2d 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 — 376 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Input
Every way a person can touch a game — finger, mouse, pen, key — arrives as one replayable stream of intents in tile coordinates, bucketed to simulation ticks, behind one object that unbinds all of it.
The two properties that shape everything else:
- Input never learns what is in the world. There is no registry, no rect, no
pickableflag and no hit callback — so an implementation that caches hit boxes during the draw pass cannot be built on it, because there is nowhere to put them and nothing that would read one. (In the source game that cache made every collect bubble untappable in a backgrounded tab.)terrainis not an exception: a heightfield is the shape of the ground, a parameter of the projection in the same sense the camera is, and no hit box can be stored in one or recovered from it. - Gestures are delivered on simulation ticks, never on frames. So a tap cannot be dropped by a slow frame or fired twice on a fast one.
The five lines a game writes
import { createInput } from '@latticekit/input';
import type { Camera, HeightField } from '@latticekit/iso';
import type { Loop } from '@latticekit/loop';
export function wire(
canvas: HTMLCanvasElement,
camera: Camera,
loop: Loop,
land: HeightField,
maxHeightPx: number,
): void {
const input = createInput({
element: canvas,
camera,
step: loop, // the loop itself, so the step cannot drift
terrain: { field: land, maxHeightPx }, // or 'flat'. Never nothing — see below
actions: { place: ['tap', 'key:Space'], cancel: ['key:Escape'] },
});
input.onAction('place', (a) => {
if (!a.onGround) return; // the pointer was on the sky: gx/gy are NaN
void a.gx;
void a.gy;
});
loop.onUpdate((_dt, tick) => input.tick(tick));
loop.onRender((_alpha, _time, nowMs) => input.frame(nowMs));
// Under Vite: without this a hot reload leaves a zombie game drawing and not responding.
if (import.meta.hot) import.meta.hot.dispose(() => input.dispose());
}
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.
- 2d ago First seen · 376 lines · 90 tokens per session scan A db465d0b65e0
input is a skill published in the GitHub repository plausibleventures/lattice (35 stars, last pushed 10d ago), licensed MIT. It adds 90 tokens to every session and 4,532 once invoked, about $0.0005 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
gameobject-component-destroy
Destroy one or more Components from a target GameObject. Missing (null) components are skipped — they cannot be destroyed. Use 'gameobject-find' and 'gameobject-component-get' to identify the components first.
assets-create-folder
Create a new folder under a parent folder inside 'Assets/'. The parent path must start with 'Assets/' and every intermediate folder in it must already exist. Refreshes the AssetDatabase at the end and returns the GUID(s) of the created folder(s).
assets-prefab-instantiate
Instantiate a prefab into the currently active scene at an optional position/rotation/scale, parented under an optional scene GameObject path. Use 'assets-find' to locate the prefab asset first.
assets-prefab-save
Save the currently opened prefab edit stage back to its prefab asset without exiting the stage. Pair with 'assets-prefab-open' to enter the edit mode first.
console-get-logs
Retrieve Unity Editor logs from the MCP plugin's LogCollector, optionally filtered by log type or time window. Useful for debugging and monitoring Editor activity.
gameobject-component-list-all
List the fully-qualified C# type names of every concrete UnityEngine.Component subclass available in the project. Paginated (default 5/page, max 500). Use this to find a valid componentName for 'gameobject-component-add'.