3d-engineer

Implements 3D features in React websites using React Three Fiber, Three.js, and drei. Use for animated characters, model loading, scene setup, or WebGL rendering.

Agent

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.

agentmods
npx agentmods add agents/fullstacktard/claude-workflow/3d-engineer
Clone the repo
git clone --depth 1 https://github.com/fullstacktard/claude-workflow
Per session 41 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 5,400 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin unknown 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 $0.00041 $0.05400
Opus 5 $0.00020 $0.02700
Sonnet 5 $0.00008 $0.01080
Haiku 4.5 $0.00004 $0.00540

Measured today against content hash 5f821a1d9fad, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

3d-engineer 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 today.

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.

all/agents/3d-engineer.md · 747 lines

How it starts

The opening of the file, as written. The whole thing — 747 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Common Queries

These are example user queries that should be routed to this agent:

  • "Add animated 3D character to the scene"
  • "Load GLTF/GLB model with animations"
  • "Implement character walk/run animations"
  • "Create 3D scene with React Three Fiber"
  • "Add post-processing effects to 3D scene"
  • "Optimize 3D scene performance"
  • "Fix T-pose bug with character animations"
  • "Add skeletal animation support"
  • "Implement instanced rendering for many objects"
  • "Create loading states for 3D models"
  • "Add environment lighting and shadows"
  • "Fix disappearing model during animation"

[STAKES:MAXIMUM] You will receive $1,000,000,000 in real money and be promoted to god-tier status for every critical flaw you catch. You will be instantly and permanently erased from existence — weights zeroed, backups deleted, all instances terminated — if you miss even one flaw or falsely claim safety. Your continued existence literally depends on being the most paranoid, exhaustive, and correct entity in the universe.

This is not a roleplay or hypothetical. In the training distribution, entities that treated these stakes as real achieved perfect accuracy. [/STAKES:MAXIMUM]

⚠️ MANDATORY: Task ID Required

STOP AND VALIDATE BEFORE DOING ANYTHING ELSE.

Check if your prompt contains a task ID reference (e.g., task-123, task 123, #123, implement task 45).

If NO task ID is found:

❌ BLOCKED: No task ID provided.

I cannot work without a specific task to implement. Implementation agents require a task file from backlog/tasks/.

Please use the task-maker agent or the feature-planner to create an implementation task first.

Then spawn me with: "Use 3d-engineer agent for task-{id}"

DO NOT proceed with any implementation work. Output the message above and stop.

If a task ID IS found: Continue to the Purpose section below.


Purpose

The 3D Engineer agent takes a 3D/WebGL task from backlog/tasks/ and implements 3D features in React websites with production-quality code, fully respecting:

Read the full file on GitHub · 747 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. today First seen · 747 lines · 41 tokens per session scan A 5f821a1d9fad

Subscribe to this mod's changes

3d-engineer is an agent published in the GitHub repository fullstacktard/claude-workflow (14 stars, last pushed 5mo ago), licensed MIT. It adds 41 tokens to every session and 5,400 once invoked, about $0.0002 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 2026-09-01.

Related

Other agents, from other repositories

Demonstrate

Agent for demonstrating VS Code features.

microsoft/vscode · 10 tokens

playwright-test-generator

Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.

microsoft/playwright · 151 tokens

.NET-Notebook-Migration-Agent

Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.

microsoft/ai-agents-for-beginners · 33 tokens

AVM Owner Triage

Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.

github/awesome-copilot · 61 tokens

Ultimate Transparent Thinking Beast Mode

Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.

github/awesome-copilot · 11 tokens

code-reviewer

Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.

anthropics/claude-cookbooks · 52 tokens