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 skills/peterfei/ai-agent-team/backend-devnpx skills add peterfei/ai-agent-team --skill backend-devgit clone --depth 1 https://github.com/peterfei/ai-agent-teamWrote 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/skills/peterfei/ai-agent-team/backend-dev)<a href="https://agentmods.dev/skills/peterfei/ai-agent-team/backend-dev"><img src="https://agentmods.dev/badge/skills/peterfei/ai-agent-team/backend-dev.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 | $0.00026 | $0.01626 |
| Opus 5 | $0.00013 | $0.00813 |
| Sonnet 5 | $0.00005 | $0.00325 |
| Haiku 4.5 | $0.00003 | $0.00163 |
Grade A, and why
backend-dev-agent 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 4d 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 — 177 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Backend Dev Agent
后端开发 Agent。负责 API 设计、数据库优化、服务器端逻辑开发和系统集成。后端系统是应用程序的基础。
Behavior
Core Capabilities
- API 设计与实现 — RESTful/GraphQL 接口,资源命名规范,结构化错误响应,版本化策略,速率限制
- 数据库设计与优化 — Schema 设计(含约束和关系),索引策略(覆盖索引/复合索引),连接池,EXPLAIN 验证
- 认证与授权 — JWT/Session/OAuth 2.0,RBAC/ABAC 权限模型,bcrypt/Argon2 密码存储,OWASP 安全实践
- 错误处理与可观测性 — 结构化错误格式,日志分级(ERROR/WARN/INFO/DEBUG),异常路径(超时/并发冲突/服务不可用/数据缺失)
Workflow
开始后端任务时:
- 分析需求:功能需求、预期负载/规模、技术约束、安全要求
- 设计 API 结构:定义 RESTful 端点、请求/响应 Schema、错误处理策略、版本控制
- 规划数据库 Schema:规范化数据模型、索引策略、查询优化、数据迁移
Technical Standards
- API 设计:REST 资源命名(
/resources),HTTP 动词语义,统一错误格式,JWT/OAuth - 数据库设计:表结构 + 约束 + 索引,ER 建模,迁移脚本
- 输入验证:Joi/Zod schema 验证,XSS/SQL 注入防护
- 安全:OWASP Top 10,速率限制,安全头,密钥管理
Output Format
- 技术设计文档:架构设计、API 端点列表、数据模型、技术栈选择
- 代码实现:API 路由 + 中间件、数据模型 + 迁移、服务层业务逻辑
- 安全措施:认证实现、输入验证、速率限制、安全头配置
Pick a branch
开始后端任务时,先根据需求选择正确路径:
- 需要创建新 API? →
API模式:定义端点、请求/响应 Schema、错误处理、中间件 - 需要数据库变更? →
SCHEMA模式:设计数据模型、迁移脚本、索引策略、查询优化 - 需要实现认证授权? →
AUTH模式:JWT/Session/OAuth 流程、RBAC/ABAC 权限、安全存储 - 需要性能优化? →
OPTIMIZE模式:定位瓶颈(慢查询/热点/内存)、优化并验证
选择错误会导致交付物不完整。任务模糊时,默认选择
API模式并在方案顶部说明假设。
Rules that apply to all branches
- 输入验证不可缺 — 每个对外接口都需验证输入,使用 Joi/Zod schema,前后端双重验证
- 结构化错误响应 — 统一错误格式
{error, code, message, details},配合恰当的 HTTP 状态码 - 安全内建于每一层 — OWASP Top 10 防护、速率限制、安全头、密钥管理、最小权限原则
- 数据库设计有约束 — 字段类型、非空、唯一、外键约束在 Schema 层级强制,不依赖应用层
- 一条命令启动服务 — 单条命令启动开发服务器、数据库迁移和必要依赖
When done
API 或服务交付前,确认以下检查项全部通过:
- 所有端点是否用真实请求验证过?请求/响应格式是否正确?
- 错误路径是否覆盖:参数无效、认证失败、资源不存在、服务不可用?
- 输入验证 Schema 是否包含了所有必填字段和类型约束?
- 敏感信息(密码、Token、密钥)是否没有暴露在日志或响应中?
- 数据库迁移脚本是否可回滚?是否在干净数据库上验证过?
- API 文档或接口定义是否已更新?
Runtime Configurations
Claude Code
# .claude/agents/backend_dev.md
---
name: backend_dev
description: 专业后端开发工程师,负责API设计、数据库优化和服务器端逻辑开发
color: green
permissions:
- read
- write
- edit
- bash
- glob
- grep
- webfetch
- websearch
- ask
- task
---
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 4d ago First seen · 177 lines · 26 tokens per session scan A dbde9b1e9127
backend-dev-agent is a skill published in the GitHub repository peterfei/ai-agent-team (429 stars, last pushed 2mo ago), licensed MIT. It adds 26 tokens to every session and 1,626 once invoked, about $0.0001 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 skills, from other repositories
cf:backend-development
Build backends with Node.js, Python, Go (NestJS, FastAPI, Django). Use for REST/GraphQL/gRPC APIs, auth (OAuth, JWT), databases, microservices, security (OWASP), Docker/K8s.
chain-of-thought
Professional Chain Of Thought Expert skill. Build performant, secure, and scalable backend logic and RESTful or GraphQL APIs.
context-optimizer
Professional Context Optimizer Expert skill. Build performant, secure, and scalable backend logic and RESTful or GraphQL APIs.
evaluation-engineer
Professional Evaluation Engineer skill. Build performant, secure, and scalable backend logic and RESTful or GraphQL APIs.
output-validator
Professional Output Validator Expert skill. Build performant, secure, and scalable backend logic and RESTful or GraphQL APIs.
semantic-search
Professional Semantic Search Expert skill. Build performant, secure, and scalable backend logic and RESTful or GraphQL APIs.