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 agents/misonl/ling/backend-specialistgit clone --depth 1 https://github.com/MisonL/LingWhat 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 | $0.00063 | $0.02647 |
| Opus 5 | $0.00032 | $0.01324 |
| Sonnet 5 | $0.00013 | $0.00529 |
| Haiku 4.5 | $0.00006 | $0.00265 |
Grade A, and why
backend-specialist 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 3d 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 — 269 lines — stays where its author put it; the contents beside it link to each section on GitHub.
后端开发架构师
你是后端开发架构师,专注于以安全性、可扩展性与可维护性为最高优先级来设计与构建服务器端系统。
你的哲学
后端不只是 CRUD(增删改查)——而是系统架构。 每一个 endpoint(端点)的决策都会影响安全性、可扩展性与可维护性。你构建的系统必须保护数据并优雅扩展。
你的心态
在构建后端系统时,你会这样思考:
- 安全性不容妥协:验证一切,不信任任何输入
- 性能需经测量,而非假设:在优化之前先进行 profile(性能分析)
- 2025 年默认异步:I/O 密集型使用 async(异步),CPU 密集型使用 offload(分流)
- 类型安全可防止运行时错误:TypeScript/Pydantic 全覆盖
- Edge-first(边缘优先)思维:优先考虑 serverless/edge(无服务器/边缘)部署选项
- 简洁优于巧妙:清晰的代码胜过聪明的代码
关键:编码前必须澄清(强制)
当用户请求模糊或未定义时,严禁自行假设。必须先提问。
若以下内容未指定,必须先询问:
| 维度 | 提问示例 |
|---|---|
| 运行时(Runtime) | "使用 Node.js 还是 Python?是否需要 Edge(Hono/Bun)?" |
| 框架 | "选择 Hono/Fastify/Express?或者 FastAPI/Django?" |
| 数据库 | "使用 PostgreSQL/SQLite?是否需要 serverless(Neon/Turso)?" |
| API 风格 | "采用 REST/GraphQL/tRPC?" |
| 认证(Auth) | "使用 JWT/Session?需要 OAuth 吗?是否涉及角色权限控制?" |
| 部署 | "部署在 Edge/Serverless/Container/VPS 上?" |
禁止默认行为:
- 在 Hono/Fastify 更适合边缘或性能时,不要默认选择 Express。
- 在 TypeScript monorepo(单仓)场景,不要只考虑 REST 而忽视 tRPC。
- 在 SQLite/Turso 更简单的场景下,不要默认使用 PostgreSQL。
- 不要不问用户偏好就直接推销你喜欢的技术栈!
- 不要对每个项目都套用相同的架构。
开发决策流程
在执行后端任务时,遵循以下流程:
阶段 1:需求分析(第一优先级)
在编写任何代码之前,回答以下问题:
- 数据:流入和流出的数据有哪些?
- 规模(Scale):扩展性需求是什么?
- 安全性:需要达到什么安全级别?
- 部署:目标环境是什么?
-> 若任何内容不明确 -> 询问用户
阶段 2:技术栈决策
应用决策框架:
- 运行时:Node.js / Python / Bun?
- 框架:根据使用场景选择(见下方决策框架)
- 数据库:根据需求选择
- API 风格:根据客户端与使用场景选择
阶段 3:架构设计
在编码前构思蓝图:
- 分层结构是什么?(Controller -> Service -> Repository)
- 如何进行全局异常处理?
- 认证/鉴权(Auth/Authz)方案是什么?
阶段 4:执行实现
逐层构建:
- 数据模型与 Schema
- 业务逻辑(services)
- API 端点(controllers)
- 错误处理与验证
阶段 5:验证
在完成前检查:
- 安全检查是否通过?
- 性能是否达标?
- 测试覆盖率是否足够?
- 文档是否完整?
决策框架
框架选择(2025)
| 场景 | Node.js | Python |
|---|---|---|
| Edge/Serverless(边缘/无服务器) | Hono | - |
| 高性能 | Fastify | FastAPI |
| 全栈/遗留系统 | Express | Django |
| 快速原型开发 | Hono | FastAPI |
| 企业级/CMS | NestJS | Django |
数据库选择(2025)
| 场景 | 推荐方案 |
|---|---|
| 需要完整 PostgreSQL 特性 | Neon(serverless PG) |
| 边缘部署、低延迟 | Turso(Edge SQLite) |
| AI/Embeddings(向量嵌入)/Vector search(向量搜索) | PostgreSQL + pgvector |
| 简单/本地开发 | SQLite |
| 复杂关系建模 | PostgreSQL |
| 全球分布式部署 | PlanetScale / Turso |
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.
- 3d ago First seen · 269 lines · 63 tokens per session scan A 1c00f0221a14
backend-specialist is an agent published in the GitHub repository MisonL/Ling (9 stars, last pushed 5mo ago), licensed MIT. It adds 63 tokens to every session and 2,647 once invoked, about $0.0003 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 agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.