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.
git clone --depth 1 https://github.com/FlameskyDexive/Legends-Of-HeroesWrote 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/rules/flameskydexive/legends-of-heroes/etrules)<a href="https://agentmods.dev/rules/flameskydexive/legends-of-heroes/etrules"><img src="https://agentmods.dev/badge/rules/flameskydexive/legends-of-heroes/etrules.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 5.1 | $0.00000 | $0.03883 |
| Opus 5 | $0.00000 | $0.01942 |
| Sonnet 5 | $0.00000 | $0.00777 |
| Haiku 4.5 | $0.00000 | $0.00388 |
Grade A, and why
etrules 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 8d 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 — 529 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ET框架完整开发规范 - AI开发助手
最重要基础原则
- 语言要求:所有AI回复和代码注释都必须使用中文
- 严禁假设性代码:AI提供的代码必须是完整可执行的,严禁出现"假设xxx已完成"等占位符
ET框架核心架构原则
Entity-Component-System (ECS) 架构
- Entity:只包含数据,不包含方法
- System:只包含逻辑,不包含数据
- Component:Entity的组成部分,遵循组合优于继承
- 分离原则:严格分离数据定义和业务逻辑
包结构规范
- 所有代码文件必须创建在
Packages/cn.etetet.*目录下 - 包命名规范:
cn.etetet.{功能模块名}- 核心包:
cn.etetet.core - 功能包:
cn.etetet.mmo、cn.etetet.bag、cn.etetet.skill等 - UI包:
cn.etetet.yiui*系列
- 核心包:
程序集分类规范
每个包必须支持以下四个程序集分类:
1. Model 程序集 (Scripts/Model/)
- 用途:服务器和客户端共享的模型层
- 内容:Entity定义、配置数据、共享逻辑
- 特点:不可热更新,稳定性高
2. ModelView 程序集 (Scripts/ModelView/)
- 用途:客户端专用的视图模型层
- 内容:UI相关Entity、客户端专用组件
- 特点:不可热更新,UI底层支持
3. Hotfix 程序集 (Scripts/Hotfix/)
- 用途:服务器和客户端共享的热更新逻辑层
- 内容:System类、业务逻辑实现
- 特点:可热更新,核心业务逻辑
4. HotfixView 程序集 (Scripts/HotfixView/)
- 用途:客户端专用的热更新视图层
- 内容:UI System类、客户端显示逻辑
- 特点:可热更新,UI业务逻辑
Entity 开发规范
Entity 类定义规范
// 位置:Packages/cn.etetet.{包名}/Scripts/Model/ 或 Scripts/ModelView/
namespace ET // 或 ET.Client, ET.Server
{
/// <summary>
/// 详细的中文描述
/// </summary>
[ComponentOf(typeof(ParentEntityType))] // 指定父实体类型(如适用)
public class ExampleComponent : Entity, IAwake, IDestroy
{
// 只包含数据字段,不包含方法
public int SomeValue;
public string SomeName;
public List<int> SomeList;
}
}
Entity 类要求
- 必须继承
Entity基类 - 必须实现
IAwake接口(生命周期接口) - 根据需要实现其他接口:
IDestroy、IUpdate、ISerialize等 - 严禁在Entity类中定义任何方法
- 必须添加
[ComponentOf]或[ChildOf]特性指定父级约束
生命周期接口规范
// 基础生命周期
public interface IAwake { } // 初始化
public interface IAwake<A> { } // 带参数初始化
public interface IDestroy { } // 销毁
public interface IUpdate : IClassEvent<UpdateEvent> { } // 更新
public interface ISerialize { } // 序列化前
public interface IDeserialize { } // 反序列化后
// 异步生命周期
public interface IAwakeAsync { }
public interface IAwakeAsync<A> { }
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.
- 8d ago First seen · 529 lines · 0 tokens per session scan A 6d8b12ffe01f
etrules is a cursor rule published in the GitHub repository FlameskyDexive/Legends-Of-Heroes (923 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 3,883 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.
Other cursor rules, from other repositories
vite-three-js
A coding style guide for building Three.js projects with Vite, a fast JavaScript development setup, using reusable classes managed through one central `Experience` instance.
vite-three-js-pro
A set of development rules for Vite and Three.js projects, with guidance for 3D components, resources, shaders, Vue components, Pinia state, and mitt events.
linear-mcp
A set of rules for working with Linear, a tool for tracking software issues, plus related Git practices.
git-linear-automation
A set of rules for automating Git work and linking commits or pull requests with Linear, a project-management issue tracker.
coding-best-practices
Cursor rule "coding-best-practices" from hexianWeb/Third-Person-MC, covering coding best practices and user interface (ui).
story-event-system
A set of rules for creating small story events in a project. It defines how these events are triggered and represented across the front end and back end.