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 KilledByAPixel/LittleJS-AI --skill littlejs-conventionsgit clone --depth 1 https://github.com/KilledByAPixel/LittleJS-AIWrote 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/killedbyapixel/littlejs-ai/littlejs-conventions)<a href="https://agentmods.dev/skills/killedbyapixel/littlejs-ai/littlejs-conventions"><img src="https://agentmods.dev/badge/skills/killedbyapixel/littlejs-ai/littlejs-conventions/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/killedbyapixel/littlejs-ai/littlejs-conventions"><img src="https://agentmods.dev/badge/skills/killedbyapixel/littlejs-ai/littlejs-conventions.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00214 | $0.01767 |
| Opus 5 | $0.00107 | $0.00883 |
| Sonnet 5 | $0.00043 | $0.00353 |
| Haiku 4.5 | $0.00021 | $0.00177 |
Grade A, and why
littlejs-conventions 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 12d 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 — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.
LittleJS engine conventions
Rules for the LittleJS engine's global API style: call engineInit, vec2, drawTile, etc. directly — no LJS. prefix, no ES-module imports (unless the project already uses the ESM build).
Startup and structure
engineInit(gameInit, gameUpdate, gameUpdatePost, gameRender, gameRenderPost, imageSources)starts the engine — define all five callbacks even if some are empty.gameInitmay beasync; the engine awaits it (putawait box2dInit()or a three.jsawait import(...)at the top).- Model entities as classes extending
EngineObject— the engine updates, moves, collides, and renders them automatically every frame:
class Player extends EngineObject
{
constructor(pos)
{
super(pos, vec2(1), tile(0), 0, CYAN); // pos, size, tileInfo, angle, color
}
update()
{
this.velocity = keyDirection().scale(.2); // arrows/WASD move the player
// engine applies physics (velocity, gravity, collision) after update()
// no super.update() call is needed
}
}
Spawn once in gameInit with new Player(vec2(0)); it draws itself — no manual draw call. Customize visuals via this.tileInfo / this.color / this.angle, or override render().
- Persisted settings/stats: use
readSaveData/writeSaveData(localStorage-backed, JSON-serialized) — don't hand-roll localStorage. Save data is always an object.readSaveDatareturns{...yourDefault, ...whatWasStored}, so a scalar default spreads to nothing:readSaveData('best', 0)yields{}, not0, and the next arithmetic on it isNaNwith no error. Always pass and read an object —readSaveData('save', {best:0}).best— and write the whole object back withwriteSaveData('save', {best:score}). - three.js 3D (the engine's built-in
ThreeJSPlugin/ThreeJSObject): three.js itself is not bundled. Declarelet THREE;at top level andTHREE = await import(...)at the top of an asyncgameInit, thennew ThreeJSPlugin(THREE)— construct noTHREE.*object before that import resolves (no top-levelnew THREE.Vector3(...)). Never declarelet threeJSin game code: the engine owns that global and the plugin constructor assigns it, so redeclaring it throws. CallsetGLEnable(false)so the LittleJS canvas draws only Canvas2D content (HUD text, particles) over the 3D scene.
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.
- 12d ago First seen · 65 lines · 214 tokens per session scan A dc8b6e34150d
littlejs-conventions is a skill published in the GitHub repository KilledByAPixel/LittleJS-AI (78 stars, last pushed 6d ago), licensed MIT. It adds 214 tokens to every session and 1,767 once invoked, about $0.0011 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
hearth-code
Write behavior in Hearth — Lua/JS scripts, the ctx API (input, timers, tweens, events, camera, audio, save), script modules and require, the dot-call and userdata pitfalls, deterministic RNG, and the check-script/edit-script iteration loop. Use when making things happen in a Hearth game (movement, AI, pickups, rules)…
pixi-vn-getting-started
Use when setting up a new or existing project on @drincs/pixi-vn, wiring the main.ts entry point, or calling the top-level Game API (Game.init, Game.start, Game.onEnd, Game.addOnError, Game.onNavigate, Game.clear) — this is the entry point every Pixi'VN project needs before touching canvas, narration, sound, storage…
gpt-pro
Operate ChatGPT Pro through Browser Use/Playwright or Computer Use. Use when the user asks Codex to ask GPT Pro, prompt GPT Pro, use ChatGPT Pro, send a prompt to ChatGPT Pro/GPT Pro, or wait for a GPT Pro result. Checks whether Browser Use/Playwright and/or Computer Use are available, asks for a first-run default…
cpp
C++ modern C++17/20/23 with STL, smart pointers, and performance optimization. Use for .cpp files.
jupyter-notebook
Iterative Python via live Jupyter kernel (hamelnb).
zoom-meeting-sdk-unreal
Zoom Meeting SDK for Unreal Engine wrapper integrations. Use when building Unreal projects that embed Zoom meetings with C++ and Blueprint wrappers, including wrapper-to-SDK mapping concerns.