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 rules/cnwinds/ai-detective/readmegit clone --depth 1 https://github.com/cnwinds/ai-detectiveWhat 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 | $0.03500 | $0.03500 |
| Opus 5 | $0.01750 | $0.01750 |
| Sonnet 5 | $0.00700 | $0.00700 |
| Haiku 4.5 | $0.00350 | $0.00350 |
Grade A, and why
README 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 2d 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 — 289 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AI侦探推理游戏 - Cursor规则总览
🤖 AI助手使用指南
⚠️ 重要原则: 你要根据用户的问题，决定是否要阅读其他的文档内容。
- 强制加载: 每次对话都必须先加载本README文件
- 按需加载: 根据问题内容决定是否需要加载其他专业文档
- 智能判断: 分析用户问题的类型和复杂度，选择合适的文档组合
- 高效响应: 避免无关文档的加载，提高响应效率
规则文件索引
本目录包含AI侦探推理游戏项目的完整Cursor规则集，帮助AI助手更好地理解项目结构、遵循开发规范、掌握核心概念。
重要提醒: 在开发过程中，相同的问题超过2次遇到，最终解决后，需要将问题和解决方案记录在 @troubleshooting-guide.mdc 文件中。如果之前有类似问题则进行修正。
📋 核心规则文件 (6个)
-
ai-detective-game.mdc - 项目核心规则 (9.1KB)
- 项目概述和技术栈
- 项目架构和模块组织
- 游戏机制和数据结构
- 核心组件说明
- AI交互机制和业务逻辑
-
backend-development.mdc - 后端开发规范 (35KB+)
- FastAPI应用架构和路由设计
- Python异步编程和流式响应
- Pydantic数据模型和验证
- 错误处理和异常管理
- 性能优化和缓存策略
- 代码重构模式和最佳实践
- 日志监控和性能分析
-
frontend-development.mdc - 前端开发规范 (30KB+)
- 原生JavaScript应用架构
- CSS组件化和响应式设计
- 移动端开发和触摸优化
- 主题系统和设备适配
- 性能优化和内存管理
- HTML语义化和可访问性
- 错误处理和用户体验
-
theme-color-standards.mdc - 主题色规范 (新增, 18KB)
- 完整的主题色系统设计规范
- 核心主题变量定义和使用规则
- 角色色彩系统和自动生成机制
- 自定义组件样式规范（CustomSelect等）
- 响应式适配和可访问性标准
- 开发检查清单和常见问题解答
-
api-development.mdc - API开发规范 (24KB)
- RESTful API设计原则和架构设计
- 后端Python实现和前端JavaScript调用
- 游戏核心API (问答、指控、提示、会话管理)
- WebSocket通信和流式响应处理
- 管理员认证和历史记录API
- 统一错误处理和性能优化
- APIHelper工具类和最佳实践
-
troubleshooting-guide.mdc - 故障排除和部署指南 (18KB)
- 常见问题诊断 (导入、服务器、前端、WebSocket)
- 调试技巧 (前端和后端)
- 部署指南 (开发环境、Docker、生产环境)
- 数据库管理和备份恢复
- 性能监控和日志分析
- 版本管理和更新策略
🎯 使用指南
🎯 按角色查看规则
后端开发者:
- ai-detective-game.mdc - 了解项目整体架构
- backend-development.mdc - 掌握Python/FastAPI开发规范
- api-development.mdc - 学习API设计和实现
- troubleshooting-guide.mdc - 解决后端问题
前端开发者:
- ai-detective-game.mdc - 了解项目整体架构
- frontend-development.mdc - 掌握JavaScript/CSS开发规范
- theme-color-standards.mdc - 遵循主题色彩规范
- api-development.mdc - 学习API调用方式
- troubleshooting-guide.mdc - 解决前端问题
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.
- 2d ago First seen · 289 lines · 3,500 tokens per session scan A 4e4ebc53236b
README is a cursor rule published in the GitHub repository cnwinds/ai-detective (6 stars, last pushed 1y ago), licensed MIT. It adds 3,500 tokens to every session, about $0.0175 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.
Other cursor rules, from other repositories
08-client-server
IF 判断当前环境是否为客户端 → FabricLoader.getInstance().getEnvironmentType() == EnvType.CLIENT → World.isClient（Yarn 字段；yarn 1.14.4 World.mapping）。不要用 MCP/Forge 的 isRemote.
07-datagen
IF 生成物品/方块模型 JSON → 手动编写 JSON 在 src/main/resources/assets/{modid}/models/.
meta-quest-agentic-tools
Use Meta Quest Agentic Tools for Meta Quest and Horizon OS samples.
webgpu-threejs-tsl
Entry point for Three.js WebGPU + TSL guidance. Covers renderer setup, node materials, and TSL syntax fundamentals. Auto-attaches on JS/TS files in projects using three/webgpu.
serialization-rules
Unity serialization best practices.
unreal-networking
Networking and multiplayer in Unreal Engine.