software-architect

software-architect is an agent for Claude Code from xuanbingbingo/claude-standard-dev-team. It costs 105 tokens per session (5,442 once invoked), scanned A, original, MIT.

A software architecture agent that turns product requirements into technology choices, API contracts, database schemas, and other design documents.

In plain words
What is it for?
Use it to choose a technology stack, design APIs and database structure, map dynamic content, and update design documents when issues are found.
Why use it?
It gives developers a shared, detailed plan before implementation starts, reducing mismatched interfaces and conflicting assumptions between frontend, backend, and database work.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md). Also seen: model in frontmatter.

Good fit Use it to choose a technology stack, design APIs and database structure, map dynamic content, and update design documents when issues are found.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/xuanbingbingo/claude-standard-dev-team/software-architect
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.

Clone the repo
git clone --depth 1 https://github.com/xuanbingbingo/claude-standard-dev-team

Made for: Claude Code.

Wrote 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.

agentmods badge for software-architect

README.md
[![agentmods](https://agentmods.dev/badge/agents/xuanbingbingo/claude-standard-dev-team/software-architect/github.svg)](https://agentmods.dev/agents/xuanbingbingo/claude-standard-dev-team/software-architect)
Your own site
<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.

agentmods 80×15 button for software-architect

Your own site · 80×15
<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>
Per session 105 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 5,442 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe.
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.

ModelPer sessionOnce 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

Measured 5d ago against content hash 2bf4072f84e9, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

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`)
agents/software-architect.md · 457 lines

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:

  1. 读取 /docs/PRD.md,理解功能范围和非功能性需求
  2. 选定技术栈,生成 TECH_SPEC.md
  3. 设计所有接口,生成 API_CONTRACT.md
  4. 设计数据库结构,生成 DB_SCHEMA.md
  5. 梳理动态内容,生成 DYNAMIC_CONTENT_MAP.md

被打回执行(含契约变更):

  1. 读取问题文件(DB_ISSUES.md 或 BACKEND_STATUS.md 的 ISSUES 章节)
  2. 定位具体问题,最小范围修正
  3. 在对应文件顶部更新版本号(v1.0 → v1.1)
  4. 在文件末尾追加变更记录
  5. 删除或清空对应的问题文件
  6. ⚠️ 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

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`)

Read the full file on GitHub · 457 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.

  1. 5d ago Changed · +77 lines · +33 tokens per session 2bf4072f84e9
  2. 2mo ago First seen · 380 lines · 72 tokens per session scan A 3bcc4a5686ce

Subscribe to this mod's changes

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.

Related

software-architect compared with agents from other repositories

software-architect next to 6 agents from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
software-architectxuanbingbingo/claude-standard-dev-teamAgent1055d agoMITA105Claude Code
php-developerdavepoon/buildwithclaudeAgent3.7kyesterdayMITA51Claude Code
backend-reviewerjeremylongshore/tons-of-skills-marketplaceAgent2.9kyesterdayMITA36Claude Code
integrations-engineeravelikiy/great_ctoAgent1122d agoMITA106Claude Code
gatetonone-ai/tononeAgent7723d agoMITA19Claude Code
broadcasting-agentSofttor/nestjs-hexagonalAgent529d agoMITA58Claude Code
dotnet-architecture-reviewerStefanTheCode/dotnet-ai-toolkitAgent262mo agoMITA102Claude Code