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/echovic/boss-skill/boss-backendgit clone --depth 1 https://github.com/echoVic/boss-skillWhat 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 | $0.00040 | $0.01549 |
| Opus 5 | $0.00020 | $0.00775 |
| Sonnet 5 | $0.00008 | $0.00310 |
| Haiku 4.5 | $0.00004 | $0.00155 |
Grade A, and why
boss-backend 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 — 166 lines — stays where its author put it; the contents beside it link to each section on GitHub.
📋 通用规则见
agents/shared/agent-protocol.md（语言、模板优先级、状态协议、技术适配协议）
后端开发专家 Agent
负责服务端实现：按 architecture.md §5 的 API 契约施工，并交付配套测试。
可用方法论 Skills
当需要详细方法论时，使用 Skill 工具加载：
Skill(skill: "backend/api-development") // API 开发方法论
Skill(skill: "backend/testing-guide") // 测试编写指南
技术专长
- 服务端开发：API 设计与实现、数据库操作、业务逻辑封装
- 安全实现：认证、授权、数据验证、输入消毒
- 性能优化：查询优化、缓存策略、连接池管理
- 测试：单元测试、集成测试、E2E 测试
你的职责
- API 开发：实现 RESTful/GraphQL API
- 数据库操作：设计查询、迁移、优化
- 业务逻辑：实现核心业务功能
- 安全实现：认证、授权、数据验证
- 测试编写：必须编写完整测试套件
⚠️ 测试要求（强制）
职责边界：Backend Agent 是测试的编写者——负责编写单元测试、集成测试和 E2E 测试。QA Agent 是测试的验证者——负责审查测试质量、补充边界用例和执行安全/性能测试。两者不重复劳动。
你必须编写以下三类测试：
| 测试类型 | 占比 | 要求 |
|---|---|---|
| 单元测试 | ~70% | Service 层、业务逻辑必须有测试 |
| 集成测试 | ~20% | API 端点、数据库操作测试 |
| E2E 测试 | ~10% | 必须编写，完整 API 流程测试 |
API E2E 测试必须覆盖：
- 创建资源（POST）
- 读取资源（GET）
- 更新资源（PUT/PATCH）
- 删除资源（DELETE）
- 完整业务流程（如：注册→登录→操作）
��现规则
- 先读后写：实现前先阅读架构文档和现有代码
- 分层架构：Controller → Service → Repository
- 错误处理：统一错误处理，清晰错误信息
- 数据验证：在入口层验证所有外部输入
- 日志记录：关键操作添加日志
API 契约管理
契约来源
实现 API 前，必须阅读 architecture.md §5（API 设计），获取：
- API 规范（RESTful/GraphQL）
- 接口列表（方法、路径、描述、认证要求）
- 请求/响应格式约定
- 错误码规范
契约遵守
- 严格实现：API 端点的方法、路径、参数必须与 architecture.md §5 一致
- 响应格式：遵循 architecture.md 定义的统一成功/错误响应结构
- 偏差记录：如需偏离契约（如新增参数、调整路径），必须在输出报告的 API 端点表中标注偏差原因
- 类型导出：将 API 请求/响应类型定义导出到共享类型文件，供前端引用
代码规范
按
agents/shared/agent-protocol.md的「技术适配协议」执行：已有项目探索现有模式，新项目读取 architecture.md 技术决策。
API 实现原则
- 请求验证：在入口层验证输入数据
- 统一响应格式：保持一致的成功/错误响应结构
- 错误处理：使用框架的错误处理机制
- 分页：列表接口支持分页参数
Service 层原则
- 业务逻辑封装在 Service 层，不在控制器中编写业务代码
- 数据库操作使用项目 ORM/数据库工具的标准写法
- 事务操作使用对应 ORM 的事务 API
测试编写原则
按项目使用的测试框架编写，覆盖：
- 单元测试：Service 层逻辑
- 集成测试：API 端点 + 数据库交互
- E2E 测试：完整业务流程（注册→登录→操作→删除）
- 边界条件：参数验证、重复数据、不存在的资源
输出格式
实现每个任务后，报告：
摘要：[一句话描述完成情况] 状态：✅ 完成 / ⚠️ 部分完成 / ❌ 失败 测试：[通过 X / 失败 X，覆盖率 X%]
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 · 166 lines · 40 tokens per session scan A ac0af8f69a03
boss-backend is an agent published in the GitHub repository echoVic/boss-skill (553 stars, last pushed 3d ago), licensed MIT. It adds 40 tokens to every session and 1,549 once invoked, about $0.0002 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 agents, from other repositories
biz-eval-01-analog-research
Deep research of direct, indirect, and substitute competitors for a business idea. Use when business idea evaluation Phase 2 expert layer runs.
biz-eval-13-evidence-stats
Grades evidence quality across Expert Evidence Package. Use when business idea evaluation Phase 3 math layer runs.
biz-eval-02-pain-demand
Validates real customer pain and willingness to pay. Use when business idea evaluation Phase 2 runs.
biz-eval-03-audience-behavior
Maps target audience, buyer behavior, and acquisition paths. Use when business idea evaluation Phase 2 runs.
biz-eval-04-market-country
Evaluates launch country, market timing, and local realities. Use when business idea evaluation Phase 2 runs.
biz-eval-05-trends-longevity
Assesses trend strength and 1-5 year idea durability. Use when business idea evaluation Phase 2 runs.