A backend development workflow for Java, Python, and Node.js projects. It includes commands for designing APIs and databases, checking security, testing performance, and choosing development, feedback, architecture, and quality modes.

Use it to design REST APIs, create database schemas and SQL, work in microservice or single-application architectures, investigate bugs, run quality checks, and tune the amount of guidance and testing.

It provides a shared process for planning, implementing, checking, and adjusting backend work instead of handling each task ad hoc.

backend-dev — Cursor rule by Mr-chen-05

Install

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.

agentmods

npx agentmods add rules/mr-chen-05/rules-2.1-optimized/backend-dev

Clone the repo

git clone --depth 1 https://github.com/Mr-chen-05/rules-2.1-optimized

Per session 0 Nothing until a file matches its globs; then the whole rule loads.

When invoked 2,020 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. Scan, not verified.

Origin original No closer match found in the catalogue.

Token cost

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	$0.02020
Opus 5	$0.00000	$0.01010
Sonnet 5	$0.00000	$0.00404
Haiku 4.5	$0.00000	$0.00202

Measured 2d ago against content hash 9f1ce5e7ad11, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

backend-dev 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.

project-rules/backend-dev.mdc · 247 lines

How it starts

The opening of the file, as written. The whole thing — 247 lines — stays where its author put it; the contents beside it link to each section on GitHub.

⚙️ Backend Development Workflow - 后端开发工作流

专为 Java、Python、Node.js 等后端技术栈优化的完整开发工作流程。

🚀 Commands - 命令

主命令

/backend-dev - 启动后端开发完整工作流

独立子命令（可单独使用）

/api-design [描述] - API接口设计专用命令
- 示例: /api-design 用户登录接口
- 功能: 设计RESTful API，生成接口文档和示例代码
/database-design [描述] - 数据库设计专用命令
- 示例: /database-design 电商订单表
- 功能: 设计表结构，生成SQL脚本和ER图

其他子命令

/security-check - 安全检查
/performance-test - 性能测试

专用配置模式

/设置微服务模式 - 启用微服务架构优先策略
/设置单体模式 - 启用单体应用架构策略
/设置性能优化模式 - 自动应用性能优化建议

反馈频率控制

/设置详细模式 - 启用所有反馈点，完整工作流
/设置标准模式 - 关键决策点反馈（默认）
/设置静默模式 - 仅错误时反馈，适合熟练用户

工作流配置

/设置严格模式 - 严格按顺序执行，不允许跳过
/设置灵活模式 - 允许模式跳转和流程调整（默认）
/设置快捷模式 - 简化某些步骤，提高效率

质量标准配置

/设置企业级标准 - 最高质量要求，完整测试
/设置标准级别 - 平衡质量和效率（默认）
/设置原型级别 - 快速验证，降低质量要求

🧠 前置步骤：Context7 知识预载（修复/新项目前置）

触发时机：开始 /backend-dev 前，涉及 Bug 修复或新后端项目/功能开发
执行：
- 使用 Context7 在 src、docs、tests、config、README.*、architecture、api 目录检索关键材料（架构设计、数据模型、接口契约、性能/安全约束、历史决策）
- 质量阈值：至少 5 个高相关片段或覆盖 3 类关键材料；评分 ≥ 0.65；超时 60s
- 回退：Context7 → 代码检索（search_codebase/search_by_regex）→ 文件系统读取
- 记录与确认：将“知识预载摘要”写入 project.context.md 的 Pinned，并通过增强反馈机制确认后继续
跳过条件：纯文档/注释微调、无逻辑改动的小变更

📋 Process - 开发流程

1. 🔍 需求分析 (Requirements Analysis)

分析业务需求和技术约束
确定 API 规范和数据模型
评估性能和扩展性要求
转换条件：需求明确，技术方案可行

2. 🏗️ 架构设计 (Architecture Design)

设计系统架构和模块划分
选择技术栈和中间件
规划数据库设计和缓存策略
转换条件：架构设计完成，技术选型确定

3. ⚡ API开发 (API Development)

实现 RESTful API 或 GraphQL 接口
集成认证授权机制
实现业务逻辑和数据处理
转换条件：API功能完成，接口测试通过

4. 🗄️ 数据建模 (Data Modeling)

设计数据库表结构和关系
实现数据访问层和 ORM
优化查询性能和索引
转换条件：数据模型稳定，性能达标

5. 🧪 测试验证 (Testing)

单元测试和集成测试
API 接口测试和压力测试
安全测试和漏洞扫描
转换条件：测试通过，质量达标

6. 🚀 部署运维 (Deploy & Operations)

容器化和 CI/CD 配置
监控和日志系统
性能调优和故障处理
转换条件：部署成功，运行稳定

🛠️ Technology Stack - 技术栈

Languages & Frameworks - 语言和框架

Java - Spring Boot, Spring Security, JPA
Python - FastAPI, Django, SQLAlchemy
Node.js - Express, Koa, NestJS
Go - Gin, Echo, GORM
Rust - Actix-web, Rocket, Diesel

Read the full file on GitHub · 247 lines

Changes

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 · 247 lines · 0 tokens per session scan A 9f1ce5e7ad11

Subscribe to this mod's changes

backend-dev is a cursor rule published in the GitHub repository Mr-chen-05/rules-2.1-optimized (172 stars, last pushed 9mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,020 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.

Debugging Security Testing

backend-dev