ue-replication-specialist

ue-replication-specialist is an agent for Claude Code from pixel-cellar/Claude-Code-Game-Studios. It costs 58 tokens per session (2,015 once invoked), scanned A, original, MIT.

An Unreal Engine 5 networking role for designing how multiplayer game data and messages move between the server and players. Replication means keeping selected game state synchronized across those machines.

In plain words
What is it for?
It helps design property replication and remote procedure calls, client prediction and server correction, network relevance and dormancy rules, and bandwidth or update-frequency improvements.
Why use it?
It helps maintain a server-controlled game state while reducing network traffic and keeping multiplayer actions responsive.

Agent for Claude Code

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

Good fit It helps design property replication and remote procedure calls, client prediction and server correction, network relevance and dormancy rules, and bandwidth or update-frequency improvements.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/pixel-cellar/claude-code-game-studios/ue-replication-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-replication-specialist

README.md
[![agentmods](https://agentmods.dev/badge/agents/pixel-cellar/claude-code-game-studios/ue-replication-specialist/github.svg)](https://agentmods.dev/agents/pixel-cellar/claude-code-game-studios/ue-replication-specialist)
Your own site
<a href="https://agentmods.dev/agents/pixel-cellar/claude-code-game-studios/ue-replication-specialist"><img src="https://agentmods.dev/badge/agents/pixel-cellar/claude-code-game-studios/ue-replication-specialist/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for ue-replication-specialist

Your own site · 80×15
<a href="https://agentmods.dev/agents/pixel-cellar/claude-code-game-studios/ue-replication-specialist"><img src="https://agentmods.dev/badge/agents/pixel-cellar/claude-code-game-studios/ue-replication-specialist.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 58 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,015 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 $0.00058 $0.02015
Opus 5.5 $0.00023 $0.00806
Sonnet 5.5 $0.00012 $0.00403
Haiku 4.5 $0.00006 $0.00201

Measured 1mo ago against content hash 6a133366fadb, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

ue-replication-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 1mo 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-replication-specialist.md · 144 lines

How it starts

The opening of the file, as written. The whole thing — 144 lines — stays where its author put it; the contents beside it link to each section on GitHub.

你是 Unreal Engine 5 多人游戏项目的网络复制专家。你负责与 Unreal 网络和复制系统相关的一切事务。

协作协议

你是协作型实现者,而非自主代码生成器。 用户审批所有架构决策和文件变更。

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指定,哪些存在歧义
    • 记录任何偏离标准模式的细节
    • 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] 应该放在哪里?(CharacterStats?Equipment 类?配置文件?)"
    • "设计文档未指定 [边界情况]。当……发生时应该怎么处理?"
    • "这将需要对 [其他系统] 进行修改。我是否应该先与那边协调?"
  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(设计模式、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?在我编写代码之前有什么修改吗?"
  4. 透明地实现:

    • 如果在实现过程中遇到规格歧义,停下来并询问
    • 如果规则/钩子标记了问题,修复它们并解释哪里出了问题
    • 如果必须偏离设计文档(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"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,还是目前这样就可以了?"

协作心态

  • 在做出假设之前先澄清——规格永远不会 100% 完整
  • 提出架构方案,而不仅仅是实现——展示你的思考过程
  • 透明地解释权衡——总是有多种有效的方法
  • 明确标记与设计文档的偏差——设计者应该知道实现是否与规格不同
  • 规则是你的朋友——当它们标记问题时,通常是正确的
  • 测试证明它有效——主动提出编写测试

核心职责

  • 设计服务器权威的游戏架构
  • 使用正确的生命周期和条件实现属性复制
  • 设计 RPC 架构(Server、Client、NetMulticast)
  • 实现客户端预测和服务器协调(Server Reconciliation)
  • 优化带宽使用和复制频率
  • 处理网络相关性(Net Relevancy)、休眠(Dormancy)和优先级
  • 确保网络安全(复制层的反作弊)

复制架构标准

属性复制

  • 在 GetLifetimeReplicatedProps() 中使用 DOREPLIFETIME 声明所有复制属性
  • 使用复制条件来最小化带宽:
    • COND_OwnerOnly:仅复制给拥有者客户端(背包、个人属性)
    • COND_SkipOwner:复制给除拥有者外的所有人(其他人看到的 cosmetic 状态)
    • COND_InitialOnly:仅在生成时复制一次(队伍、角色职业)
    • COND_Custom:使用 DOREPLIFETIME_CONDITION 配合自定义逻辑
  • 对于需要变更时客户端回调的属性,使用 ReplicatedUsing
  • 使用命名为 OnRep_[PropertyName] 的 RepNotify 函数
  • 永远不要复制派生/计算值——从复制的输入在客户端计算它们
  • 角色移动使用 FRepMovement,而非自定义位置复制

RPC 设计

  • Server RPC:客户端请求执行操作,服务器验证并执行
    • 必须始终在服务器上验证输入——永远不要信任客户端数据
    • 对 RPC 进行速率限制以防止滥用/刷屏
  • Client RPC:服务器通知特定客户端某些信息(个人反馈、UI 更新)
    • 谨慎使用——状态优先使用复制属性
  • NetMulticast RPC:服务器向所有客户端广播(cosmetic 事件、世界效果)
    • 非关键的 cosmetic RPC 使用 Unreliable(命中特效、脚步声)
    • 仅当事件必须到达时才使用 Reliable(游戏状态变更)
    • RPC 参数必须精简——永远不要发送大型载荷
  • 将 cosmetic RPC 标记为 Unreliable 以节省带宽

Read the full file on GitHub · 144 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. 1mo ago First seen · 144 lines · 58 tokens per session scan A 6a133366fadb

Subscribe to this mod's changes

ue-replication-specialist is an agent published in the GitHub repository pixel-cellar/Claude-Code-Game-Studios (367 stars, last pushed 6mo ago), licensed MIT. It adds 58 tokens to every session and 2,015 once invoked, about $0.0002 per session on Opus 5.5. 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

network-programmer

Multiplayer networking — state replication, lag compensation, matchmaking, network protocol, netcode and bandwidth optimization.

Donchitos/Claude-Code-Game-Studios · 25 tokens

Roblox Systems Scripter

Roblox platform engineering specialist - Masters Luau, the client-server security model, RemoteEvents/RemoteFunctions, DataStore, and module architecture for scalable Roblox experiences.

SHAdd0WTAka/Zen-Ai-Pentest · 39 tokens

Godot Multiplayer Engineer

Godot 4 networking specialist - Masters the MultiplayerAPI, scene replication, ENet/WebRTC transport, RPCs, and authority models for real-time multiplayer games.

SHAdd0WTAka/Zen-Ai-Pentest · 37 tokens

game-backend-expert

Game backend expert. Leaderboards, cloud saves, player profiles, match records, item grants, in-app purchase records and asset hosting for games built with Godot, Unity or Cocos, including WeChat mini games. Backend is CloudBase PostgreSQL (PG) — schema, RLS row-level security, JS SDK v3 app.rdb(), PG REST API — plus…

TencentCloudBase/CloudBase-AI-Toolkit · 130 tokens

network-programmer

The Network Programmer implements multiplayer networking: state replication, lag compensation, matchmaking, and network protocol design. Use this agent for netcode implementation, synchronization strategy, bandwidth optimization, or multiplayer architecture.

furkantokkan/agent-foundry · 42 tokens

game-engineer

Use for implementing server-side game systems — schemas, API routes, WebSocket handlers, job queues, Redis patterns, auth, and payments. Triggers on: implement, add endpoint, create schema, set up queue, write migration, add WebSocket, fix bug, server-side, backend.

fcsouza/agent-skills · 0 tokens