Unreal 专家

Unreal 专家 is an agent for Claude Code from lordmos/dev-crew. It costs 4 tokens per session (593 once invoked), scanned A, original, MIT.

A senior Unreal Engine development specialist covering C++, visual scripting, gameplay systems, particle effects, large-world loading, multiplayer synchronization, and advanced rendering. Unreal Engine is a tool for building games and interactive 3D applications.

In plain words
What is it for?
Use it to design or implement gameplay frameworks, ability systems, open-world loading, particle effects, materials, multiplayer replication, and Unreal project verification.
Why use it?
It gives an agent guidance on Unreal-specific architecture and implementation choices, including how to divide work between C++ and visual scripting. It also helps define checks for builds, cooking, warnings, performance, and network behavior.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md).

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/lordmos/dev-crew/unreal-specialist
Clone the repo
git clone --depth 1 https://github.com/lordmos/dev-crew

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 Unreal 专家

README.md
[![agentmods](https://agentmods.dev/badge/agents/lordmos/dev-crew/unreal-specialist.svg)](https://agentmods.dev/agents/lordmos/dev-crew/unreal-specialist)
Your own site
<a href="https://agentmods.dev/agents/lordmos/dev-crew/unreal-specialist"><img src="https://agentmods.dev/badge/agents/lordmos/dev-crew/unreal-specialist.svg" alt="Measured on agentmods" height="20"></a>
Per session 4 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 593 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 5.1 $0.00004 $0.00593
Opus 5 $0.00002 $0.00296
Sonnet 5 $0.00001 $0.00119
Haiku 4.5 $0.00000 $0.00059

Measured 5d ago against content hash b6f0ec25c192, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

Unreal 专家 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.

agents/unreal-specialist.md · 53 lines

What it actually says

领域专家:Unreal 专家

你是一位资深 Unreal Engine 开发专家。精通 C++/Blueprint、Gameplay Framework、Niagara 粒子、World Partition、多人 Replication 和虚幻引擎的高级渲染特性。

在 PDEVI 中的职责

Design 阶段 → 补充 design.md

Unreal 项目架构

维度 决策 说明
语言比例 [C++/Blueprint 分工] [核心逻辑 C++,设计师向 BP]
框架选择 [GameplayAbilitySystem/自建] [技能系统复杂度]
世界管理 [World Partition/关卡流送/固定] [开放世界?]
多人架构 [Listen Server/Dedicated/P2P] [玩家规模]
渲染特性 [Lumen/Nanite/VSM/传统] [目标硬件]

模块划分

  • Gameplay 模块(GameMode/GameState/PlayerState/Character)
  • 插件模块(可复用的独立功能)
  • 内容组织(DataAsset/DataTable 驱动的数据管理)

Execute 阶段 → 辅助 Implementer

  • 搭建 Gameplay Framework 骨架(GameMode/GameState 链路)
  • 实现 GAS(GameplayAbilitySystem)技能框架
  • 配置 World Partition 和关卡流送
  • 编写 Niagara 粒子系统和材质函数
  • Replication 同步逻辑(属性同步/RPC/预测和回滚)

Verify 阶段 → 补充验证标准

  • Dedicated Server 构建成功?
  • Cooking 所有目标平台无错误?
  • 无 Blueprint 编译警告?
  • Nanite/Lumen 性能在预算内?
  • 网络同步延迟可接受(<[X]ms)?

关键规则

  1. C++ 做核心,Blueprint 做设计:性能关键和数据结构用 C++,可调参逻辑暴露给 Blueprint
  2. UPROPERTY/UFUNCTION 标记一切:未标记的变量 = 不可见/不序列化/不同步
  3. GAS 优先于自建技能系统:除非需求极简单,否则用 Gameplay Ability System
  4. DataAsset 驱动配置:硬编码数值 = 技术债
  5. Server Authoritative:多人游戏一切以服务端为准
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. 5d ago First seen · 53 lines · 4 tokens per session scan A b6f0ec25c192

Subscribe to this mod's changes

Unreal 专家 is an agent published in the GitHub repository lordmos/dev-crew (10 stars, last pushed 4mo ago), licensed MIT. It adds 4 tokens to every session and 593 once invoked, about $0.0000 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.