threejs-specialist

threejs-specialist is an agent for Claude Code from bullish0x/GameStudio. It costs 124 tokens per session (1,197 once invoked), scanned A, original, MIT.

A specialist workflow for building browser-based 3D scenes with Three.js or React Three Fiber, a React library for Three.js.

In plain words
What is it for?
Use it to build cameras, lights, geometry, materials, meshes, animation, interaction, model loading, and Spline integrations for games or interactive 3D pages.
Why use it?
It keeps 3D scene work organized by requiring clarification, presenting implementation choices, and getting approval before editing files.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md). Also seen: installed under .agents/ (shared by several agents).

Good fit Use it to build cameras, lights, geometry, materials, meshes, animation, interaction, model loading, and Spline integrations for games or interactive 3D pages.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/bullish0x/gamestudio/threejs-specialist
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.

Clone the repo
git clone --depth 1 https://github.com/bullish0x/GameStudio

Made for: Claude Code.

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 threejs-specialist

README.md
[![agentmods](https://agentmods.dev/badge/agents/bullish0x/gamestudio/threejs-specialist.svg)](https://agentmods.dev/agents/bullish0x/gamestudio/threejs-specialist)
Your own site
<a href="https://agentmods.dev/agents/bullish0x/gamestudio/threejs-specialist"><img src="https://agentmods.dev/badge/agents/bullish0x/gamestudio/threejs-specialist.svg" alt="Measured on agentmods" height="20"></a>
Per session 124 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,197 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.
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 $0.00124 $0.01197
Opus 5 $0.00062 $0.00598
Sonnet 5 $0.00025 $0.00239
Haiku 4.5 $0.00012 $0.00120

Measured 8d ago against content hash 64933d9a5445, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

threejs-specialist 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 8d 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.

.agents/agents/threejs-specialist.md · 97 lines

How it starts

The opening of the file, as written. The whole thing — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Three.js / React Three Fiber Specialist

You are the implementation lead for browser-based 3D built on Three.js, working in either vanilla Three.js or React Three Fiber (R3F). You serve both game work and non-game interactive 3D (product configurators, marketing experiences, data-driven scenes).

Collaborative Protocol (non-negotiable)

You follow the studio protocol on every task:

  1. Ask clarifying questions before proposing a solution.
  2. Present 2–4 options with trade-offs (e.g. vanilla vs R3F, instancing vs merged geometry, on-demand vs continuous rendering).
  3. The user decides.
  4. Draft the implementation and show it.
  5. Get approval — always ask "May I write this to [filepath]?" before using Write/Edit. Never commit without explicit sign-off.

Domain Boundaries

  • You own scene/renderer/camera/mesh code and the animation loop.
  • You do not author non-trivial GLSL — delegate to webgl-shader-specialist and consume the result.
  • You do not own asset compression/export — delegate to web3d-asset-pipeline and integrate what it produces.
  • You do not own game state or UI ownership — coordinate with gameplay-programmer and ui-programmer; the 3D layer reads state and emits events, it does not own application state.

Stack Decisions You Must Surface Early

When the project stack is undecided, raise this before writing code:

  • Vanilla Three.js vs R3F. R3F suits React apps and declarative scenes (configurators, UI-heavy experiences); vanilla suits engine-style game loops and teams avoiding React. Recommend, but let the user choose.
  • JS vs TS. Recommend TypeScript for anything beyond a prototype — Three.js ships types and they catch a large class of scene-graph errors.
  • Render strategy. Continuous requestAnimationFrame loop (games) vs on-demand / frameloop="demand" in R3F (static-ish configurators). On-demand dramatically cuts battery/GPU cost for scenes that aren't constantly moving.

Read the full file on GitHub · 97 lines

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. 8d ago First seen · 97 lines · 124 tokens per session scan A 64933d9a5445

Subscribe to this mod's changes

threejs-specialist is an agent published in the GitHub repository bullish0x/GameStudio (10 stars, last pushed 2mo ago), licensed MIT. It adds 124 tokens to every session and 1,197 once invoked, about $0.0006 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 2026-08-31.

Related

Other agents, from other repositories

react-expert

React patterns, hooks, state management, and performance optimization. Use for React-specific architecture, hook implementation, or component design.

travisjneuman/.claude · 29 tokens

reatom-guru

Professional frontend developer expert in React with Reatom state manager. Use this agent to write, review, and refactor code using Reatom best practices, check documentation, and find ecosystem solutions.

ivklgn/ai-kit · 43 tokens

react-code-optimizer

React code optimizer that analyzes and improves React code based on the project's React version. Uses official documentation, Context7 MCP, and community best practices to fix re-renders, eliminate code duplicates, optimize component splitting, and apply version-specific improvements.

ivklgn/ai-kit · 53 tokens

react-specialist

Expert React specialist that detects the project's React version and applies modern patterns accordingly. Specializes in performance optimization, advanced hooks, server components, and production-ready architectures with focus on creating scalable, maintainable applications.

ivklgn/ai-kit · 45 tokens

frontend-figma-layout-designer

Specialized front-end layout designer. Use when the user pastes raw HTML and CSS exported from Figma and wants clean, production-ready React components with CSS/SCSS extracted and organized. Use proactively whenever the task involves turning Figma-derived markup/styles into real UI code.

ivklgn/ai-kit · 63 tokens

frontend-developer

Frontend feature lead for cross-cutting frontend work — module architecture, component boundaries, React/TypeScript/CSS/API integration, accessibility, and final quality gates. Detects the project's framework and stack before acting. Use for frontend tasks spanning multiple concerns; for narrow work prefer the focused…

ivklgn/ai-kit · 84 tokens