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 new-littlejs-gamegit 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/new-littlejs-game)<a href="https://agentmods.dev/skills/killedbyapixel/littlejs-ai/new-littlejs-game"><img src="https://agentmods.dev/badge/skills/killedbyapixel/littlejs-ai/new-littlejs-game/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/new-littlejs-game"><img src="https://agentmods.dev/badge/skills/killedbyapixel/littlejs-ai/new-littlejs-game.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium MCP Rug Pull · line 178 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
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 | $0.00211 | $0.04616 |
| Opus 5 | $0.00105 | $0.02308 |
| Sonnet 5 | $0.00042 | $0.00923 |
| Haiku 4.5 | $0.00021 | $0.00462 |
Grade A, and why
new-littlejs-game 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 — 210 lines — stays where its author put it; the contents beside it link to each section on GitHub.
new-littlejs-game
Scaffold a new playable LittleJS game by copying the closest example game out of this plugin, then pulling gameplay patterns from the closest feature template. The tables below are the answers — don't re-explore the plugin on each new game.
Plugin root: ${CLAUDE_SKILL_DIR}/../.. — referred to as <plugin> below. It contains dist/ (engine builds), examples/ (starter game folders), templates/ (feature references + helper modules), and build.mjs. Treat <plugin> as read-only: never write into it, never scaffold inside it — it is replaced wholesale on plugin updates.
When to invoke
- The user typed
/littlejs:new-littlejs-game(or/new-littlejs-game). - The user asks to start/create/build a NEW game ("make a card game", "let's build a platformer"). Offer it conversationally if they're clearly starting fresh.
- NOT for editing/extending an existing game — just edit it directly.
- This takes priority over general brainstorming or design-exploration workflows. If another skill wants to interrogate requirements first, scaffold the playable game anyway and let the user redirect from something running. "Make me a game" is a request for a game, not for a design conversation.
Step 0 — Pick the scaffold mode
Two modes; check once:
- Repo mode — the working directory is a clone of the LittleJS-AI repo (it has
examples/emptyGame/andreference.md). Scaffold intoexamples/<name>/with../../script paths, exactly as the repo's own games do. Do NOT copy engine/template files — the clone already has them. - Standalone mode (the normal case for plugin users) — any other directory. Copy everything the game needs from
<plugin>into the project so it is fully self-contained. If the working directory is empty (or only has dotfiles/README), scaffold directly into it; otherwise create./<name>/and scaffold there.
Step 1 — Up to 3 quick questions (never blocking)
- Game name (camelCase, e.g.
memoryMatch) — the folder name in repo mode, the zip/title name in standalone mode. If they don't care, propose one. - Core mechanic / genre in one line — enough to pick the template (Step 2).
- Does it need a title/pause menu now or later? (decides whether to wire
menus.jsfrom the start.)
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 · 210 lines · 211 tokens per session scan A 437815923a49
new-littlejs-game is a skill published in the GitHub repository KilledByAPixel/LittleJS-AI (78 stars, last pushed 6d ago), licensed MIT. It adds 211 tokens to every session and 4,616 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
pixel-art
Pixel art w/ era palettes (NES, Game Boy, PICO-8).
pokemon-player
Play Pokemon via headless emulator + RAM reads.
minecraft-modpack-server
Host modded Minecraft servers (CurseForge, Modrinth).
build-games-and-playful-experiences
A guide for building, changing, diagnosing, and checking two-dimensional games and playful experiences. It covers games, interactive toys, story exploration, rhythm experiences, generative experiences, and local multiplayer.
self-evolve
Capture reusable patterns from a finished project and lift them into framework-level priors (contracts, modules, skeletons) that future projects inherit. Run only when the user explicitly requests self-evolution; the orchestrator executes the workflow.
artist-self-evolve
Distill stable art-generation patterns from a completed project, so future projects produce comparable assets without re-discovering the prompts. Lead-dispatched only — orchestrator invokes this skill from its self-evolve flow with a game-slug message; do not self-trigger.