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/mr-chen-05/rules-2.1-optimized/intelligent-recommendation-enginegit clone --depth 1 https://github.com/Mr-chen-05/rules-2.1-optimizedWrote 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/mr-chen-05/rules-2.1-optimized/intelligent-recommendation-engine)<a href="https://agentmods.dev/rules/mr-chen-05/rules-2.1-optimized/intelligent-recommendation-engine"><img src="https://agentmods.dev/badge/rules/mr-chen-05/rules-2.1-optimized/intelligent-recommendation-engine.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 | $0.00000 | $0.05546 |
| Opus 5 | $0.00000 | $0.02773 |
| Sonnet 5 | $0.00000 | $0.01109 |
| Haiku 4.5 | $0.00000 | $0.00555 |
Grade A, and why
intelligent-recommendation-engine 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.
How it starts
The opening of the file, as written. The whole thing — 654 lines — stays where its author put it; the contents beside it link to each section on GitHub.
🤖 智能推荐引擎
智能决策: 基于自然语言理解和上下文分析的项目阶段智能推荐系统
🎯 系统概述
智能推荐引擎是超级大脑系统的核心决策组件，通过分析用户输入、项目上下文和历史数据，为用户提供最适合的项目阶段推荐和工作流建议。
前置推荐：Context7 知识预载（Bug/新项目意图）
- 当意图为“问题解决（Bug/错误/异常/修复/排查/优化）”或“执行操作（开始新项目/新功能）”时，推荐在进入对应工作流前执行 Context7 知识预载。
- 推荐逻辑：
- 语义匹配到上述关键词或分类 → 触发“知识预载”建议
- 若系统检测 Context7 不可用 → 提示按 MCP 统一管理规则安装/启用
- 若用户明确选择跳过（轻量变更）→ 记录跳过原因并继续
- 与工作流协同：预载在 /analyze-issue、/implement-task、/frontend-dev、/backend-dev 之前执行，输出摘要写入 project.context.md（Pinned），并通过增强反馈机制确认后继续。
🧠 推荐算法架构
多层推荐模型
推荐层次:
L1_关键词匹配:
权重: 40%
方法: 基于预定义关键词库的快速匹配
优势: 响应快速、准确率高
L2_语义理解:
权重: 35%
方法: 基于NLP的语义分析和意图识别
优势: 理解复杂表达、上下文感知
L3_上下文分析:
权重: 20%
方法: 项目状态、历史轨迹、用户偏好分析
优势: 个性化推荐、连续性保证
L4_学习优化:
权重: 5%
方法: 基于反馈的模型参数动态调整
优势: 持续改进、适应性强
📚 关键词匹配系统
阶段关键词库
阶段1_需求分析:
高权重词 (权重: 3.0):
- "需求", "要求", "想要", "希望", "计划"
- "讨论", "分析", "了解", "确定", "明确"
- "目标", "目的", "用途", "场景", "用户"
- "功能", "特性", "能力", "作用", "效果"
中权重词 (权重: 2.0):
- "方案", "思路", "想法", "概念", "理念"
- "技术选型", "技术栈", "框架选择", "语言选择"
- "可行性", "评估", "调研", "研究", "探索"
低权重词 (权重: 1.0):
- "项目", "系统", "应用", "软件", "平台"
- "开始", "启动", "初始", "第一步", "首先"
排除词 (权重: -2.0):
- "实现", "开发", "编写", "代码", "编程"
- "部署", "上线", "发布", "运行", "启动"
- "测试", "调试", "修复", "优化", "改进"
阶段2_架构设计:
高权重词 (权重: 3.0):
- "架构", "结构", "框架", "设计", "模式"
- "搭建", "构建", "建立", "创建", "初始化"
- "组件", "模块", "服务", "接口", "API"
- "数据库", "存储", "缓存", "队列", "中间件"
中权重词 (权重: 2.0):
- "技术选型", "技术栈", "工具选择", "环境配置"
- "目录结构", "项目结构", "文件组织", "代码组织"
- "依赖管理", "包管理", "版本控制", "构建工具"
低权重词 (权重: 1.0):
- "准备", "配置", "安装", "设置", "环境"
- "规划", "计划", "方案", "策略", "思路"
排除词 (权重: -2.0):
- "业务逻辑", "具体实现", "细节功能", "算法实现"
- "用户界面", "前端页面", "交互逻辑", "事件处理"
阶段3_开发实现:
高权重词 (权重: 3.0):
- "实现", "开发", "编写", "编程", "代码"
- "功能", "逻辑", "算法", "方法", "函数"
- "组件", "模块", "类", "接口", "服务"
- "前端", "后端", "API", "数据库", "界面"
中权重词 (权重: 2.0):
- "集成", "对接", "连接", "调用", "交互"
- "处理", "操作", "管理", "控制", "执行"
- "验证", "校验", "检查", "过滤", "转换"
低权重词 (权重: 1.0):
- "完善", "补充", "添加", "扩展", "增强"
- "修改", "调整", "更新", "改进", "优化"
排除词 (权重: -2.0):
- "架构调整", "重构", "设计变更", "框架更换"
- "需求变更", "功能调整", "范围修改"
阶段4_测试优化:
高权重词 (权重: 3.0):
- "测试", "检测", "验证", "校验", "确认"
- "优化", "改进", "提升", "增强", "完善"
- "性能", "效率", "速度", "响应", "吞吐"
- "Bug", "错误", "问题", "异常", "故障"
中权重词 (权重: 2.0):
- "调试", "排查", "定位", "分析", "诊断"
- "修复", "解决", "处理", "修正", "纠正"
- "监控", "统计", "分析", "报告", "指标"
低权重词 (权重: 1.0):
- "检查", "审查", "评估", "评价", "质量"
- "稳定", "可靠", "安全", "兼容", "健壮"
排除词 (权重: -2.0):
- "新功能", "新需求", "功能扩展", "需求增加"
- "架构调整", "设计修改", "技术更换"
阶段5_部署运维:
高权重词 (权重: 3.0):
- "部署", "发布", "上线", "发布", "交付"
- "运维", "维护", "管理", "监控", "运营"
- "服务器", "云服务", "容器", "集群", "环境"
- "域名", "SSL", "CDN", "负载均衡", "备份"
中权重词 (权重: 2.0):
- "配置", "设置", "安装", "启动", "运行"
- "安全", "权限", "认证", "授权", "加密"
- "日志", "监控", "告警", "统计", "分析"
低权重词 (权重: 1.0):
- "文档", "说明", "手册", "指南", "教程"
- "培训", "交接", "移交", "支持", "维护"
排除词 (权重: -2.0):
- "代码修改", "功能调整", "逻辑变更", "算法优化"
- "界面调整", "交互修改", "样式更新"
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.
- 5d ago First seen · 654 lines · 0 tokens per session scan A 385c75f8458d
intelligent-recommendation-engine is a cursor rule published in the GitHub repository Mr-chen-05/rules-2.1-optimized (172 stars, last pushed 10mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 5,546 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
angular-20
This rule provides comprehensive best practices and coding standards for Angular development, focusing on modern TypeScript, standalone components, signals, and performance optimizations.
dev-standard
Apache Superset development standards and guidelines for Cursor IDE.
cli-error-handling
CLI command error handling patterns.
prefer-direct-imports-over-module-mocks
Prefer extracting a testable core over vi.mock / vi.resetModules when unit tests need to reach production logic entangled with config, env, or singletons.
control-plane-descriptors
Control plane descriptor and instance implementation patterns.
family-instance-domain-actions
Family instance domain action implementation patterns.