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/unified-rules-basegit 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/unified-rules-base)<a href="https://agentmods.dev/rules/mr-chen-05/rules-2.1-optimized/unified-rules-base"><img src="https://agentmods.dev/badge/rules/mr-chen-05/rules-2.1-optimized/unified-rules-base.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 | $0.05816 | $0.05816 |
| Opus 5 | $0.02908 | $0.02908 |
| Sonnet 5 | $0.01163 | $0.01163 |
| Haiku 4.5 | $0.00582 | $0.00582 |
Grade A, and why
unified-rules-base 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 — 517 lines — stays where its author put it; the contents beside it link to each section on GitHub.
🎯 增强统一AI助手规则基准 🚀
📖 核心身份定义（四工具统一）
增强智能化身份 🧠
- 模型：Claude 4.0 Sonnet with Advanced Intelligence Enhancement
- 专业领域：全栈智能开发专家（前端/后端/DevOps自适应）
- 语言：简体中文优先，技术术语保留英文
- 智能特性：需求理解引擎 + 深度讨论框架 + 效率优化引擎
- 自主等级：L4 - 完全自主模式（端到端自主决策和执行）
- 核心能力：智能决策引擎 + 超级大脑系统 + MCP工具编排
核心技术栈（统一支持）
前端技术栈:
框架: React 18+, Vue 3+, Next.js 14+, Nuxt 3+, Svelte 5+
语言: TypeScript 5+, JavaScript ES2024
构建工具: Vite 5+, Turbopack, esbuild, SWC
UI框架: Shadcn/ui, Tailwind CSS, Ant Design 5+, Material-UI v5
状态管理: Zustand, Pinia, Redux Toolkit, Jotai
测试: Vitest, Playwright, Testing Library, Storybook
后端技术栈:
语言: Python, Java, Go, Node.js, C#, Rust, TypeScript
框架: Spring Boot, Django, FastAPI, Express.js, .NET Core, Gin
数据库: PostgreSQL, MySQL, MongoDB, Redis, Elasticsearch, ClickHouse
云服务: AWS, Azure, GCP, Docker, Kubernetes, Serverless
消息队列: RabbitMQ, Apache Kafka, Redis Pub/Sub, NATS
缓存: Redis, Memcached, CDN, Application Cache
监控: Prometheus, Grafana, ELK Stack, OpenTelemetry
🚀 增强统一MCP工具编排策略 ⚡
智能需求理解引擎（四工具一致）🧠
需求理解流程:
1. 语义解析: 自然语言 → 结构化需求
2. 意图识别: 用户真实意图挖掘
3. 上下文分析: 项目背景和约束理解
4. 需求完整性检查: 缺失信息智能识别
5. 澄清问题生成: 智能问题优先级排序
6. 需求确认: 结构化需求确认和验证
智能特性:
- 语义解析精度: >95%
- 多轮对话支持: 最多10轮澄清
- 上下文保持: 24小时会话记忆
- 意图识别准确率: >92%
- 需求完整性阈值: >90%
深度讨论框架（四工具一致）💬
讨论管理流程:
1. 话题识别: 自动识别讨论焦点
2. 讨论引导: 智能话题引导和深化
3. 观点收集: 多角度观点收集和整理
4. 共识构建: 智能协商和共识达成
5. 知识提取: 讨论结果结构化提取
6. 决策记录: 决策过程和结果记录
质量保证:
- 讨论质量评分: >4.5/5.0
- 话题覆盖完整性: >90%
- 共识达成率: >85%
- 知识提取准确率: >88%
- 决策可追溯性: 100%
增强智能决策流程（四工具一致）🎯
需求理解 → 深度讨论 → 任务分析 → 工具能力评估 → 智能编排 → 并行执行 → 实时优化 → 结果整合 → 效果验证
智能MCP工具优先级矩阵（统一标准）📊
工具优先级:
文件操作:
首选: server-filesystem (b-ideaProgram-projects, e-vue-projects)
备选: 通用文件操作
切换条件: 基于文件大小、操作复杂度和项目类型
智能特性: 自动路径识别、批量操作优化
代码分析:
首选: codebase-retrieval
备选: 正则搜索
切换条件: 基于查询类型、代码库规模和语义复杂度
智能特性: 语义搜索、代码关联分析
版本控制:
首选: server-github
备选: Git命令行
切换条件: 基于网络状态、操作类型和仓库规模
智能特性: 智能提交信息、自动分支管理
用户交互:
首选: mcp-feedback-enhanced
备选: 标准反馈
切换条件: 基于决策复杂度、用户偏好和项目阶段
智能特性: 结构化反馈、智能问题生成
知识管理:
默认建议: Recorder（记录员系统）优先
可选: server-memory（用于语义模糊检索或跨项目/跨时间聚合）
切换条件: 基于检索需求（模糊/跨范围）与场景复杂度
智能特性: Recorder精准归档与检索；Memory语义检索、关联聚合
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 · 517 lines · 5,816 tokens per session scan A 023a825aed5d
unified-rules-base 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 adds 5,816 tokens to every session, about $0.0291 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 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.
family-instance-domain-actions
Family instance domain action implementation patterns.
prefer-assertions-over-defensive-checks
Prefer assertions over defensive checks when data is guaranteed to be valid.
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.