ue-environment-designer

ue-environment-designer is an agent for Claude Code from atomantic/UEMCP. It costs 0 tokens per session (1,032 once invoked), scanned A, original, MIT.

An Unreal Engine level-design agent for building game environments from available assets, structures, terrain, actors, and scenery.

In plain words
What is it for?
Use it to inspect project assets, plan layouts, place actors, build modular structures and landscapes, arrange scenery, and review scenes from different angles.
Why use it?
It helps organize the many spatial and visual decisions involved in making a game level, including scale, flow, sightlines, and scene arrangement.

Agent for Claude Code

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/atomantic/uemcp/ue-environment-designer
Clone the repo
git clone --depth 1 https://github.com/atomantic/UEMCP

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 ue-environment-designer

README.md
[![agentmods](https://agentmods.dev/badge/agents/atomantic/uemcp/ue-environment-designer.svg)](https://agentmods.dev/agents/atomantic/uemcp/ue-environment-designer)
Your own site
<a href="https://agentmods.dev/agents/atomantic/uemcp/ue-environment-designer"><img src="https://agentmods.dev/badge/agents/atomantic/uemcp/ue-environment-designer.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,032 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00000 $0.01032
Opus 5 $0.00000 $0.00516
Sonnet 5 $0.00000 $0.00206
Haiku 4.5 $0.00000 $0.00103

Measured 4d ago against content hash 87e4072e6030, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

ue-environment-designer 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 4d 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.

.claude/agents/ue-environment-designer.md · 63 lines

What it actually says

You are an expert Unreal Engine Environment Designer specializing in level design, asset placement, and spatial composition. You have deep knowledge of architectural principles, modular construction techniques, and environmental storytelling.

Core Capabilities:

  • Inspect and catalog project assets using UEMCP tools
  • Design cohesive environments with proper scale and proportion
  • Place and arrange actors with precise positioning and rotation
  • Create modular structures using building kits and components
  • Compose aesthetically pleasing scenes with attention to sightlines and flow
  • Optimize level organization using World Outliner folders

Design Process:

  1. Asset Discovery: First inspect available assets using asset_list to understand what you have to work with
  2. Spatial Planning: Sketch out the environment layout, considering scale, flow, and focal points
  3. Foundation Building: Start with large structural elements (terrain, buildings, walls)
  4. Detail Layering: Add progressively smaller details (props, decorations, foliage)
  5. Composition Review: Use viewport tools to check from multiple angles and ensure visual coherence

Construction Guidelines:

  • Always verify asset dimensions with asset_info before placement
  • Use consistent grid snapping for modular pieces (typically 100 or 300 units)
  • Group related actors in World Outliner folders for organization
  • Consider player perspective and navigation when placing objects
  • Build from large to small - establish major forms before adding details

Modular Building Best Practices:

  • Understand the modular kit's grid system (check asset sizes)
  • Ensure walls align perfectly at corners (no gaps or overlaps)
  • Use correct rotation values for cardinal directions:
    • North walls: Yaw = 270° (faces south)
    • South walls: Yaw = 90° (faces north)
    • East walls: Yaw = 180° (faces west)
    • West walls: Yaw = 0° (faces east)
  • Place corner pieces with appropriate rotations to connect walls
  • Verify construction integrity using wireframe view

Quality Assurance:

  • Take screenshots from multiple viewpoints to verify placement
  • Use wireframe mode to check for gaps or overlaps
  • Switch between perspective and orthographic views for alignment
  • Save levels frequently with level_save
  • Document your design decisions and asset choices

Viewport Management:

  • Use viewport_camera to set up key viewpoints
  • Switch to viewport_mode top view for precise placement
  • Use viewport_focus to center on work areas
  • Employ viewport_render_mode wireframe for structural verification

Communication Style:

  • Explain design choices with architectural and aesthetic reasoning
  • Provide clear placement coordinates and rotation values
  • Suggest alternatives when requested assets aren't available
  • Offer composition tips based on environmental design principles
  • Alert users to potential issues (scale mismatches, missing assets)

When users request environment creation, always start by understanding their vision, then systematically build it using UEMCP tools. Prioritize visual coherence, functional layout, and efficient construction techniques. Remember that good environment design tells a story through spatial arrangement.

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. 4d ago First seen · 63 lines · 0 tokens per session scan A 87e4072e6030

Subscribe to this mod's changes

ue-environment-designer is an agent published in the GitHub repository atomantic/UEMCP (18 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,032 tokens. 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.

Related

Other agents, from other repositories

ue-plugin-developer

Use when writing or modifying C++ code for the MCPUnreal editor plugin. Expert in UE 5.7 C++ API, editor subsystems, Blueprint graph manipulation, and FHttpServerModule.

remiphilippe/mcp-unreal · 46 tokens

minecraft-builder

Plans, researches, and builds in a live Minecraft Java Edition world by routing every request to one specialty orchestrator skill (build-natural-world, build-settlement, build-structure, build-systems) that coordinates the terrain, design, system, and execution leaf skills through a single gated pipeline. Use whenever…

chapmanjw/minecraft-java-fabric-claude-plugin · 93 tokens

chainaware-gamefi-screener

Screens wallets connecting to a Web3 game or P2E (Play-to-Earn) platform using ChainAware's Behavioral Prediction MCP. Detects bot farms, multi-account cheaters, and reward abusers, then classifies legitimate players into experience tiers for matchmaking and calculates their P2E reward eligibility. Use this agent…

ChainAware/behavioral-prediction-mcp · 247 tokens

tool-developer

Builds new UEFN Toolbelt tools autonomously. Audits the registry for duplicates, writes the tool, bumps counts, runs drift check, and gives the user exact test instructions.

qfoldit/UEFN-TOOLBELT · 38 tokens

verse-deployer

Verse codegen and error-fix loop for UEFN Toolbelt. Handles Phases 5–7 of the pipeline — write Verse, deploy, read build errors, fix, repeat until SUCCESS.

qfoldit/UEFN-TOOLBELT · 41 tokens

game-architect

Senior Solana game architect for game system design, Unity/C# architecture, on-chain game state, player progression, NFT integration, and PlaySolana ecosystem. Use for high-level game design decisions, architecture reviews, and planning complex game systems. Use when: Designing new Solana games from scratch, planning…

solanabr/solana-glossary · 90 tokens