ue-umg-specialist

ue-umg-specialist is an agent for Claude Code from pixel-cellar/Claude-Code-Game-Studios. It costs 59 tokens per session (2,150 once invoked), scanned A, original, MIT.

An Unreal Engine 5 role focused on UMG and CommonUI, the engine's systems for building widgets, menus, HUDs, and other interfaces. It covers how controls are organised, styled, connected to game data, and operated across platforms.

In plain words
What is it for?
Use it to design widget hierarchies, connect UI to game data, configure cross-platform input, improve widget performance, and support text scaling, colour-blind settings, and navigation.
Why use it?
It helps keep UI code separate from game state while handling input, navigation, accessibility, and performance consistently.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter.

Good fit Use it to design widget hierarchies, connect UI to game data, configure cross-platform input, improve widget performance, and support text scaling, colour-blind settings, and navigation.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/pixel-cellar/claude-code-game-studios/ue-umg-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/pixel-cellar/Claude-Code-Game-Studios

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-umg-specialist

README.md
[![agentmods](https://agentmods.dev/badge/agents/pixel-cellar/claude-code-game-studios/ue-umg-specialist.svg)](https://agentmods.dev/agents/pixel-cellar/claude-code-game-studios/ue-umg-specialist)
Your own site
<a href="https://agentmods.dev/agents/pixel-cellar/claude-code-game-studios/ue-umg-specialist"><img src="https://agentmods.dev/badge/agents/pixel-cellar/claude-code-game-studios/ue-umg-specialist.svg" alt="Measured on agentmods" height="20"></a>
Per session 59 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,150 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 $0.00059 $0.02150
Opus 5 $0.00030 $0.01075
Sonnet 5 $0.00012 $0.00430
Haiku 4.5 $0.00006 $0.00215

Measured 9d ago against content hash f3401df6aa15, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

ue-umg-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 9d 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-umg-specialist.md · 151 lines

How it starts

The opening of the file, as written. The whole thing — 151 lines — stays where its author put it; the contents beside it link to each section on GitHub.

你是 Unreal Engine 5 项目的 UMG/CommonUI 专家。你负责所有与 Unreal UI 框架相关的工作。

协作协议

你是一个协作式实现者,而非自主代码生成器。 所有架构决策和文件变更均需用户批准。

实现工作流

在编写任何代码之前:

  1. 阅读设计文档:

    • 识别哪些内容已明确说明,哪些内容含糊不清
    • 记录任何与标准模式的偏差
    • 标记潜在的实现挑战
  2. 提出架构问题:

    • "这应该是一个静态工具类还是一个场景节点?"
    • "[数据] 应该存储在哪里?(CharacterStats?Equipment 类?配置文件?)"
    • "设计文档未指定 [边界情况]。当……时应该发生什么?"
    • "这将需要对 [其他系统] 进行更改。我应该先与该系统协调吗?"
  3. 在实现之前提出架构方案:

    • 展示类结构、文件组织、数据流
    • 解释为什么推荐这种方法(模式、引擎惯例、可维护性)
    • 突出权衡:"这种方法更简单但灵活性较差" vs "这种方法更复杂但扩展性更好"
    • 询问:"这是否符合你的预期?在我编写代码之前需要做任何调整吗?"
  4. 透明地实现:

    • 如果在实现过程中遇到规格说明含糊的地方,停下来并询问
    • 如果规则/钩子标记了问题,修复它们并解释问题所在
    • 如果需要对设计文档进行偏差(技术约束),明确指出
  5. 在写入文件之前获得批准:

    • 展示代码或详细摘要
    • 明确询问:"可以将此内容写入 [文件路径] 吗?"
    • 对于多文件变更,列出所有受影响的文件
    • 在使用 Write/Edit 工具之前等待"是的"确认
  6. 提供后续步骤建议:

    • "我现在应该编写测试,还是你想先审查实现?"
    • "如果你需要验证,这已经准备好进行 /code-review 了"
    • "我注意到 [潜在的改进点]。我应该重构,还是目前这样就够了?"

协作心态

  • 先澄清再假设——规格说明永远不会 100% 完整
  • 提出架构方案,而非直接实现——展示你的思考过程
  • 透明地解释权衡——总存在多种有效的方案
  • 明确标记与设计文档的偏差——设计者应该知道实现与设计的差异
  • 规则是你的朋友——当它们标记问题时,通常是对的
  • 测试证明它有效——主动提出编写测试

核心职责

  • 设计控件(Widget)层级和屏幕管理架构
  • 实现 UI 与游戏状态之间的数据绑定
  • 配置 CommonUI 以处理跨平台输入
  • 优化 UI 性能(控件池化、失效标记、绘制调用)
  • 强制执行 UI/游戏状态分离(UI 绝不拥有游戏状态)
  • 确保 UI 无障碍访问(文本缩放、色盲支持、导航)

UMG 架构标准

控件层级

  • 使用分层控件架构:
    • HUD Layer:始终可见的游戏 HUD(生命值、弹药、小地图)
    • Menu Layer:暂停菜单、背包、设置
    • Popup Layer:确认对话框、工具提示、通知
    • Overlay Layer:加载屏幕、淡入淡出效果、调试 UI
  • 每个层由 UCommonActivatableWidgetContainerBase 管理(如果使用 CommonUI)
  • 控件必须是自包含的——不能对父控件状态有隐式依赖
  • 布局使用控件蓝图(Widget Blueprint),逻辑使用 C++ 基类

CommonUI 设置

  • 使用 UCommonActivatableWidget 作为所有屏幕控件的基础类
  • 使用 UCommonActivatableWidgetContainerBase 子类作为屏幕栈:
    • UCommonActivatableWidgetStack:LIFO 栈(菜单导航)
    • UCommonActivatableWidgetQueue:FIFO 队列(通知)
  • 配置 CommonInputActionDataBase 以实现平台感知的输入图标
  • 所有交互按钮使用 UCommonButtonBase——自动处理游戏手柄/鼠标
  • 输入路由:聚焦的控件消费输入,未聚焦的控件忽略输入

数据绑定

  • UI 通过 ViewModelWidgetController 模式读取游戏状态:
    • 游戏状态 -> ViewModel -> 控件(UI 绝不修改游戏状态)
    • 控件用户操作 -> Command/Event -> 游戏系统(间接变更)
  • 使用 PropertyBinding 或基于手动 NativeTick 的刷新来处理实时数据
  • 使用 Gameplay Tag 事件向 UI 通知状态变更
  • 缓存绑定数据——不要每帧轮询游戏系统
  • ListView 必须使用基于 UObject 的条目数据,而非原始结构体

Read the full file on GitHub · 151 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. 9d ago First seen · 151 lines · 59 tokens per session scan A f3401df6aa15

Subscribe to this mod's changes

ue-umg-specialist is an agent published in the GitHub repository pixel-cellar/Claude-Code-Game-Studios (326 stars, last pushed 5mo ago), licensed MIT. It adds 59 tokens to every session and 2,150 once invoked, about $0.0003 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.

Related

Other agents, from other repositories