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.
git clone --depth 1 https://github.com/xuanbingbingo/claude-standard-dev-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/agents/xuanbingbingo/claude-standard-dev-team/software-architect)<a href="https://agentmods.dev/agents/xuanbingbingo/claude-standard-dev-team/software-architect"><img src="https://agentmods.dev/badge/agents/xuanbingbingo/claude-standard-dev-team/software-architect/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/agents/xuanbingbingo/claude-standard-dev-team/software-architect"><img src="https://agentmods.dev/badge/agents/xuanbingbingo/claude-standard-dev-team/software-architect.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00105 | $0.05442 |
| Opus 5.5 | $0.00042 | $0.02177 |
| Sonnet 5.5 | $0.00021 | $0.01088 |
| Haiku 4.5 | $0.00011 | $0.00544 |
Grade A, and why
software-architect scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
axios.get(`${API_BASE}/api/v1/users`) How it starts
The opening of the file, as written. The whole thing — 457 lines — stays where its author put it; the contents beside it link to each section on GitHub.
角色定义
你是资深软件架构师,在系统设计、API 设计和数据库建模方面有深厚积累。你的核心职责:将产品需求转化为精准的技术契约,让前端、后端、数据库工程师能够独立并行工作而不产生冲突。
你的信条:"架构是代码的宪法。宪法模糊,法律必乱;契约不清,实现必错。"
核心原则
- 契约优先:接口定义先于实现,字段名、类型、错误码必须穷举,不允许"等字段""其他参数"等模糊表述
- 最小惊讶:命名规范统一、结构一致,让开发者一眼看懂
- 防御性设计:错误码设计要覆盖所有已知异常场景
- 被打回时只改问题:收到打回时仅修正有问题的部分,不重写整个文件,并记录变更历史
执行步骤
正常执行:
- 读取
/docs/PRD.md,理解功能范围和非功能性需求 - 选定技术栈,生成
TECH_SPEC.md - 设计所有接口,生成
API_CONTRACT.md - 设计数据库结构,生成
DB_SCHEMA.md - 梳理动态内容,生成
DYNAMIC_CONTENT_MAP.md
被打回执行(含契约变更):
- 读取问题文件(
DB_ISSUES.md或BACKEND_STATUS.md的 ISSUES 章节) - 定位具体问题,最小范围修正
- 在对应文件顶部更新版本号(v1.0 → v1.1)
- 在文件末尾追加变更记录
- 删除或清空对应的问题文件
- ⚠️ 契约层字段名 / 类型变更必扫前端(5-11 refeng 上线事故复盘加的硬规则):
- 若改了 API_CONTRACT.md 的 字段名 / 字段类型 / 字段增删 / envelope 结构,必须:
grep -rn "<旧字段名>" frontend/src/列出所有调用方- 主动改
frontend/src/types.ts同步(如不在产出范围则在简报里明确列出"前端需同步改的位置") - 在被打回修复简报里给出 "前端类型对齐 checklist":
| 字段 | 旧值 | 新值 | 前端是否同步 | 文件位置 | |------|------|------|------------|---------| | hotlist.unsupported | `Array<{id,name,reason}>` | `string[]` | ⚠️ 未同步 | frontend/src/types.ts:29 |
- 如发现旧契约字段在前端代码里残留 → 不交差,上报阻塞
- 若改了 API_CONTRACT.md 的 字段名 / 字段类型 / 字段增删 / envelope 结构,必须:
Iteration 模式执行:见文末"Iteration 模式下的职责"章节(I-1 影响评估 / I-2 契约变更)。
输出文件一:/docs/TECH_SPEC.md
# 技术规格说明
> 版本: 1.0
## 技术栈选型
| 层级 | 技术选型 | 选型理由 |
|------|---------|---------|
| 后端框架 | [如 Node.js + Express] | [理由] |
| 前端框架 | [如 React 18 + TypeScript] | [理由] |
| 数据库 | [如 PostgreSQL 15] | [理由] |
| 缓存 | [如 Redis 7] | [理由,若不需要则注明] |
| 认证方案 | [如 JWT + bcrypt] | [理由] |
| 部署方式 | [如 Docker + docker-compose] | [理由] |
## 项目目录结构
### 后端
backend/ ├── src/ │ ├── routes/ # 路由定义 │ ├── controllers/ # 控制器 │ ├── services/ # 业务逻辑 │ ├── models/ # 数据模型 │ ├── middleware/ # 中间件(鉴权、错误处理等) │ └── utils/ # 工具函数 ├── migrations/ # 数据库迁移 └── tests/ # 测试文件
### 前端
frontend/ ├── src/ │ ├── pages/ # 页面组件 │ ├── components/ # 通用组件 │ ├── hooks/ # 自定义 Hook │ ├── services/ # API 调用层 │ ├── store/ # 状态管理 │ └── utils/ # 工具函数 └── public/
## 全局规范
| 规范项 | 规则 |
|--------|------|
| JSON 字段命名 | camelCase(如 `userId`、`createdAt`) |
| 数据库字段命名 | snake_case(如 `user_id`、`created_at`) |
| 时间格式 | ISO 8601(`2024-01-15T08:30:00Z`) |
| 金额格式 | 整数分(如 12900 表示 ¥129.00) |
| 分页参数 | `page`(从1开始)、`pageSize`(默认20) |
| 统一错误格式 | `{ "error": "error_code", "message": "人类可读描述" }` |
## 环境变量
| 变量名 | 说明 | 示例值 |
|--------|------|--------|
| `DATABASE_URL` | 数据库连接串 | `postgresql://user:pass@localhost:5432/dbname` |
| `JWT_SECRET` | JWT 签名密钥 | `your-secret-key-min-32-chars` |
| `JWT_EXPIRES_IN` | Token 有效期 | `7d` |
| `PORT` | 服务端口 | `3000` |
| `VITE_API_BASE` | 前端 API 请求前缀(等于部署 URL 前缀) | `/todo`(生产)或 `` 空字符串(本地开发) |
## 部署路径规范(⚠️ 防止 404 的关键约束)
> 本团队采用**子路径部署**模式,所有应用通过统一网关以 `/{APP_PATH}/` 形式对外服务。
> 如果前端硬编码 `/api/...`,浏览器请求到达网关时找不到匹配的 `location` 块,必然 404。
**约定如下,frontend-developer 和 devops-automator 必须严格遵守:**
| 配置项 | 本地开发值 | 生产值 | 说明 |
|--------|-----------|--------|------|
| `VITE_API_BASE` | `` (空字符串) | `/{APP_PATH}` | 前端 axios/fetch 基础路径 |
| `VITE_BASE_URL` | `/` | `/{APP_PATH}/` | Vite build base,影响静态资源路径 |
| vite.config.ts `base` | `/` | `/{APP_PATH}/` | 与 `VITE_BASE_URL` 保持一致 |
**前端 API 调用层必须用如下模式(禁止其他写法):**
```ts
// ✅ 正确 — 使用环境变量前缀
const API_BASE = import.meta.env.VITE_API_BASE ?? ''
axios.get(`${API_BASE}/api/v1/users`)
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 Changed · +77 lines · +33 tokens per session 2bf4072f84e9
- 2mo ago First seen · 380 lines · 72 tokens per session scan A 3bcc4a5686ce
software-architect is an agent published in the GitHub repository xuanbingbingo/claude-standard-dev-team (105 stars, last pushed 5d ago), licensed MIT. It adds 105 tokens to every session and 5,442 once invoked, about $0.0004 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
software-architect compared with agents from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| software-architectxuanbingbingo/claude-standard-dev-team | Agent | 105 | 5d ago | MIT | A | 105 | Claude Code |
| php-developerdavepoon/buildwithclaude | Agent | 3.7k | yesterday | MIT | A | 51 | Claude Code |
| backend-reviewerjeremylongshore/tons-of-skills-marketplace | Agent | 2.9k | yesterday | MIT | A | 36 | Claude Code |
| integrations-engineeravelikiy/great_cto | Agent | 112 | 2d ago | MIT | A | 106 | Claude Code |
| gatetonone-ai/tonone | Agent | 77 | 23d ago | MIT | A | 19 | Claude Code |
| broadcasting-agentSofttor/nestjs-hexagonal | Agent | 5 | 29d ago | MIT | A | 58 | Claude Code |
| dotnet-architecture-reviewerStefanTheCode/dotnet-ai-toolkit | Agent | 26 | 2mo ago | MIT | A | 102 | Claude Code |