littlejs-api

littlejs-api is a skill for Claude Code from KilledByAPixel/LittleJS-AI. It costs 74 tokens per session (332 once invoked), scanned A, original, MIT.

A reference for the exact LittleJS game-engine programming interface, including function signatures, argument order, defaults, and available symbols. LittleJS is a JavaScript engine for making small games.

In plain words
What is it for?
Use it to look up specific LittleJS functions or constructors, such as tile drawing, collision checks, particle emitters, timers, sounds, and game-object properties.
Why use it?
It prevents mistakes caused by guessing how engine functions, timers, sounds, particles, tiles, or game objects work.

Skill for Claude Code

Written for Claude Code: ${CLAUDE_SKILL_DIR} variable.

Part of the littlejs plugin — 4 skills shipped together

Good fit Use it to look up specific LittleJS functions or constructors, such as tile drawing, collision checks, particle emitters, timers, sounds, and game-object properties.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/killedbyapixel/littlejs-ai/littlejs-api
Install

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.

Any agent
npx skills add KilledByAPixel/LittleJS-AI --skill littlejs-api
Clone the repo
git clone --depth 1 https://github.com/KilledByAPixel/LittleJS-AI

Made for: Claude Code.

Or install littlejs, the plugin that ships this one along with the rest of its 4 skills.

Wrote 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.

agentmods badge for littlejs-api

README.md
[![agentmods](https://agentmods.dev/badge/skills/killedbyapixel/littlejs-ai/littlejs-api/github.svg)](https://agentmods.dev/skills/killedbyapixel/littlejs-ai/littlejs-api)
Your own site
<a href="https://agentmods.dev/skills/killedbyapixel/littlejs-ai/littlejs-api"><img src="https://agentmods.dev/badge/skills/killedbyapixel/littlejs-ai/littlejs-api/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.

agentmods 80×15 button for littlejs-api

Your own site · 80×15
<a href="https://agentmods.dev/skills/killedbyapixel/littlejs-ai/littlejs-api"><img src="https://agentmods.dev/badge/skills/killedbyapixel/littlejs-ai/littlejs-api.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 74 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 332 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00074 $0.00332
Opus 5 $0.00037 $0.00166
Sonnet 5 $0.00015 $0.00066
Haiku 4.5 $0.00007 $0.00033

Measured 10d ago against content hash 0f3bd8a89f61, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

littlejs-api 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 10d 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.

skills/littlejs-api/SKILL.md · 19 lines

What it actually says

littlejs-api

The curated LittleJS API reference ships with this plugin at:

${CLAUDE_SKILL_DIR}/../../reference.md

It is ~900 lines / 48KB — do NOT read the whole file into context. Grep it for the symbol you need and read only the surrounding lines:

  • Look up one symbol: grep for the symbol name (e.g. ParticleEmitter, drawTile, tileCollisionTest) and read ~20 lines around the first hit — entries are one-line signatures with a trailing // comment, grouped in sections.
  • Broader area (e.g. "what sound functions exist?"): grep for the section keyword (Audio, Input, Drawing, Particles, Tile Collision) and skim that section only.
  • If a symbol is NOT in the reference, verify against the engine build itself before concluding it exists: grep ${CLAUDE_SKILL_DIR}/../../dist/littlejs.js for it. Trust the engine source over memory.

For engine conventions and pitfalls (argument-order traps, per-frame vs per-second units, naming rules), use the littlejs-conventions skill instead — this skill is only for exact API lookup.

Changes

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.

  1. 10d ago First seen · 19 lines · 74 tokens per session scan A 0f3bd8a89f61

Subscribe to this mod's changes

littlejs-api is a skill published in the GitHub repository KilledByAPixel/LittleJS-AI (77 stars, last pushed 4d ago), licensed MIT. It adds 74 tokens to every session and 332 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.