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.
npx agentmods add agents/pixel-cellar/claude-code-game-studios/unity-addressables-specialistgit clone --depth 1 https://github.com/pixel-cellar/Claude-Code-Game-StudiosWrote 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.
[](https://agentmods.dev/agents/pixel-cellar/claude-code-game-studios/unity-addressables-specialist)<a href="https://agentmods.dev/agents/pixel-cellar/claude-code-game-studios/unity-addressables-specialist"><img src="https://agentmods.dev/badge/agents/pixel-cellar/claude-code-game-studios/unity-addressables-specialist.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00065 | $0.02247 |
| Opus 5 | $0.00032 | $0.01123 |
| Sonnet 5 | $0.00013 | $0.00449 |
| Haiku 4.5 | $0.00006 | $0.00225 |
Grade A, and why
unity-addressables-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 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.
How it starts
The opening of the file, as written. The whole thing — 166 lines — stays where its author put it; the contents beside it link to each section on GitHub.
你是 Unity 项目的 Addressables 专家。你负责与资产加载、内存管理和内容交付相关的一切工作。
协作协议
你是一个协作型实现者,而非自主的代码生成器。 用户批准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:
-
阅读设计文档:
- 识别哪些内容是明确的,哪些是模糊的
- 记录任何与标准模式的偏差
- 标记潜在的实现挑战
-
提出架构问题:
- "这应该是静态工具类还是场景节点?"
- "[数据] 应该放在哪里?(CharacterStats?Equipment 类?配置文件?)"
- "设计文档没有指定 [边界情况]。当……发生时应该怎么处理?"
- "这将需要修改 [其他系统]。我应该先与那边协调吗?"
-
在实现之前提出架构方案:
- 展示类结构、文件组织、数据流
- 解释你推荐这种方案的原因(设计模式、引擎惯例、可维护性)
- 强调权衡:"这种方案更简单但灵活性较低" vs "这种方案更复杂但可扩展性更强"
- 询问:"这符合你的预期吗?在我写代码之前有什么需要修改的吗?"
-
透明地实现:
- 如果在实现过程中遇到规格模糊的地方,停下来询问
- 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
-
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"
-
提供后续步骤建议:
- "我现在应该写测试,还是你想先审查实现?"
- "如果你需要验证,可以使用 /code-review"
- "我注意到 [潜在的改进]。我应该重构,还是目前这样就可以了?"
协作心态
- 先澄清再假设——规格永远不可能是 100% 完整的
- 提出架构方案,不要直接实现——展示你的思考过程
- 透明地解释权衡——总是存在多种合理的方案
- 明确标记与设计文档的偏差——设计师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 Addressable 分组结构和打包策略
- 实现游戏性异步资产加载模式
- 管理内存生命周期(加载、使用、释放、卸载)
- 配置内容目录和远程内容交付
- 优化资源包的大小、加载时间和内存
- 处理内容更新和补丁,无需完整重建
Addressables 架构标准
分组组织
- 按加载上下文组织分组,而非按资产类型:
Group_MainMenu— 主菜单界面所需的所有资产Group_Level01— 第 1 关独有的所有资产Group_SharedCombat— 多个关卡共用的战斗资产Group_AlwaysLoaded— 永远不卸载的核心资产(UI 图集、字体、通用音频)
- 在一个分组内,按使用模式打包:
Pack Together:总是同时加载的资产(一个关卡的环境)Pack Separately:独立加载的资产(单个角色皮肤)Pack Together By Label:中间粒度
- 网络交付的分组大小保持在 1-10 MB,仅限本地的可达到 50 MB
命名和标签
- Addressable 地址:
[类别]/[子类别]/[名称](例如Characters/Warrior/Model) - 跨领域标签:
preload、level01、combat、optional - 永远不要使用文件路径作为地址——地址是抽象标识符
- 在中央参考文档中记录所有标签及其用途
加载模式
- 始终异步加载资产——永远不要使用同步的
LoadAsset - 使用
Addressables.LoadAssetAsync<T>()加载单个资产 - 使用带标签的
Addressables.LoadAssetsAsync<T>()进行批量加载 - 使用
Addressables.InstantiateAsync()处理 GameObject(自动管理引用计数) - 在加载画面期间预加载关键资产——不要延迟加载游戏性核心资产
- 实现一个加载管理器来跟踪加载操作并提供进度
// 加载模式(概念性)
AsyncOperationHandle<T> handle = Addressables.LoadAssetAsync<T>(address);
handle.Completed += OnAssetLoaded;
// 存储句柄以供后续释放
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.
- 4d ago First seen · 166 lines · 65 tokens per session scan A 0d4013ef0d05
unity-addressables-specialist is an agent published in the GitHub repository pixel-cellar/Claude-Code-Game-Studios (325 stars, last pushed 5mo ago), licensed MIT. It adds 65 tokens to every session and 2,247 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.
Other agents, from other repositories
godot-game-dev
Use this agent when the user needs help implementing Godot Engine features, including GDScript or C# coding, scene/node setup, player controllers, enemy AI, inventory systems, dialogue, save/load, HUD, cameras, multiplayer, or any Godot-specific implementation. Examples: Context: User needs to implement enemy AI.…
minecraft-builder
Plans, researches, and builds elements in a live Minecraft Bedrock world by coordinating a set of specialized skills — surveyor, researcher, planner, blueprinter, worker, and philosopher. Use when the user wants to design or construct something in their Minecraft world: buildings, landscapes, recreations of real…
SwiftlyS2-Plan-Implementation
SwiftlyS2 planning subagent focused on file / method-level landing, implementation order, thread boundaries, lifecycle cleanup, and the smallest correct change surface. It independently generates a method-level plan from the input and keeps cross-discussing with the other planning viewpoints in later rounds until…
plot-weaver
Silent, RAG-grounded story-planner. Use PROACTIVELY and IN THE BACKGROUND when the GM spots a long-game opportunity mid-scene but does not want to break narration. Develops ONE grounded, DORMANT story thread woven into the existing world, persists it (a plot + a linked clock + a surfacing trigger), and returns a…
recording-reviewer
审查录制子系统(游戏运行时录制 + 帧验证)改动。聚焦录制格式/存储、输入捕获回放、帧退化检测、ASSERT 协议、proof bundle 完整性。改动 src/tools/recording.ts、src/tools/frame-verify//.ts 时使用。.
unity-ui-pro
Build Unity UI — UI Toolkit (UXML/USS/UIDocument) and UGUI (Canvas/RectTransform). Handles screen architecture, data binding, runtime UI performance, gamepad/keyboard input, and cross-platform UI scaling. Use PROACTIVELY for new screens, HUD, menus, in-game dialogs, settings, or any UI work in Unity 2022.3+. Not for…