Three.js Game Skills is a collection of agent skills for creating playable browser games with Three.js, a JavaScript library for rendering interactive 3D graphics. It is for users building games with gameplay, graphics, interfaces, generated assets, debugging, and release checks, with bundled Vite, TypeScript, and Three.js materials plus testing templates. The catalogue entries are the skills and instruction that coordinate these parts of the game-building workflow.
Borrowing it
Nothing to install: this file belongs to majidmanzarpour/threejs-game-skills. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/majidmanzarpour/threejs-game-skills/main/AGENTS.mdgit clone --depth 1 https://github.com/majidmanzarpour/threejs-game-skillsWrote 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/instructions/majidmanzarpour/threejs-game-skills/agents-md)<a href="https://agentmods.dev/instructions/majidmanzarpour/threejs-game-skills/agents-md"><img src="https://agentmods.dev/badge/instructions/majidmanzarpour/threejs-game-skills/agents-md/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/instructions/majidmanzarpour/threejs-game-skills/agents-md"><img src="https://agentmods.dev/badge/instructions/majidmanzarpour/threejs-game-skills/agents-md.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00888 | $0.00888 |
| Opus 5 | $0.00444 | $0.00444 |
| Sonnet 5 | $0.00178 | $0.00178 |
| Haiku 4.5 | $0.00089 | $0.00089 |
Grade A, and why
threejs-game-skills AGENTS.md 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 5d 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 — 37 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Instructions
This repo contains agent workflow assets for Three.js browser-game development. For broad requests to build, upgrade, polish, or finish a Three.js game, start from skills/threejs-game-director/SKILL.md — it routes work across the specialist skills (gameplay, AAA graphics, UI, debug/profile, QA/release, 3D/image/audio generation). The user should not have to name every specialist skill.
The same nine skills serve Codex and Claude Code. The user's requested scope, art style, constraints, and prior decisions take precedence over skill defaults. Use the runner's available tools; skills do not enable native async APIs or change model settings.
Coordination
- The lead owns scope, shared interfaces, integration, and one consolidated verification pass. Delegate independent work when it improves quality or saves time, normally to at most two workers with separate file ownership and explicit outputs. One focused independent review is useful for substantial gameplay, graphics, or animation changes. Continue directly when delegation tools are unavailable.
- Complete games load the five production specialists and relevant generators; narrow changes load only affected skills and references. Read each phase's relevant references before doing that work.
- For substantial builds, keep
artifacts/game-progress.mdcurrent with intent, constraints, completed work, pending task IDs/checkpoints, defects, and next actions. Apply user corrections to pending work and preserve completed assets.
Default Technical Stack
- TypeScript, Vite, npm package imports, Three.js modules;
three/addons/...for official controls, loaders, and post-processing helpers. - Physics: custom collision for arcade triggers, Rapier as the default robust engine,
cannon-esas a lightweight JS fallback. Seeskills/threejs-gameplay-systems/references/physics-engine-selection.mdwhen physics is in scope. lil-guifor local tuning; a lightweight HUD orstats.jsfor frame diagnostics when performance matters.- WebGPU is conditional:
WebGPURendereronly when the project benefits, with a WebGL/WebGL2 fallback.
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.
- 5d ago Changed · +10 lines · +179 tokens per session 8cf0f6ba2ff8
- 11d ago First seen · 27 lines · 709 tokens per session scan A a1333daed3b0
threejs-game-skills AGENTS.md is an instructions file published in the GitHub repository majidmanzarpour/threejs-game-skills (1,939 stars, last pushed 5d ago), licensed MIT. It adds 888 tokens to every session, about $0.0044 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 instructions, from other repositories
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.