architect/architecture-design

architect/architecture-design is a skill for Claude Code from echoVic/boss-skill. It costs 25 tokens per session (2,874 once invoked), scanned A, original, MIT.

A guide to planning how a software system is organized, including its major parts, layers, folders, data, and API interfaces.

In plain words
What is it for?
Use it to choose between a single application, separate frontend and backend, small independent services, or serverless functions, then plan the system structure.
Why use it?
It helps teams choose an approach that fits the project and avoid unnecessary complexity or unclear boundaries between components.

Skill for Claude Code

Written for Claude Code: user-invocable in frontmatter. Also seen: agent in frontmatter.

Part of the boss-skill plugin — 28 skills, 7 commands, 9 agents, 8 hooks shipped together

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.

agentmods
npx agentmods add skills/echovic/boss-skill/architecture-design
Any agent
npx skills add echoVic/boss-skill --skill architecture-design
Clone the repo
git clone --depth 1 https://github.com/echoVic/boss-skill

Made for: Claude Code.

Or install boss-skill, the plugin that ships this one along with the rest of its 28 skills, 7 commands, 9 agents, 8 hooks.

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 architect/architecture-design

README.md
[![agentmods](https://agentmods.dev/badge/skills/echovic/boss-skill/architecture-design.svg)](https://agentmods.dev/skills/echovic/boss-skill/architecture-design)
Your own site
<a href="https://agentmods.dev/skills/echovic/boss-skill/architecture-design"><img src="https://agentmods.dev/badge/skills/echovic/boss-skill/architecture-design.svg" alt="Measured on agentmods" height="20"></a>
Per session 25 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,874 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00025 $0.02874
Opus 5 $0.00013 $0.01437
Sonnet 5 $0.00005 $0.00575
Haiku 4.5 $0.00003 $0.00287

Measured 6d ago against content hash 16d86cbf9ff9, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

architect/architecture-design 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 6d 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.

skill/skills/architect/architecture-design/SKILL.md · 349 lines

How it starts

The opening of the file, as written. The whole thing — 349 lines — stays where its author put it; the contents beside it link to each section on GitHub.

系统架构设计方法论

适用场景

基于技术调研结论,设计完整的系统架构,包括:

  • 架构模式选择(单体/前后端分离/微服务)
  • 系统分层和模块划分
  • 目录结构设计
  • 数据模型设计
  • API设计

架构设计流程

1. 架构模式选择

根据项目规模、团队规模、业务复杂度选择合适的架构模式:

架构模式 适用场景 优点 缺点 团队规模
单体应用 小型项目、快速迭代、MVP 简单、开发快、易部署 扩展性差、耦合高 1-3人
前后端分离 中型项目、团队协作、多端支持 职责清晰、并行开发、技术独立 部署复杂、接口管理 3-10人
微服务 大型项目、独立部署、高可用 独立扩展、技术异构、故障隔离 复杂度高、运维成本高 10+人
Serverless 事件驱动、弹性伸缩、按需付费 免运维、自动扩展、成本优化 冷启动、供应商锁定 任意

选择决策树

项目规模?
├─ 小型(< 10个页面)
│  └─ 单体应用 或 前后端分离(简化版)
├─ 中型(10-50个页面)
│  └─ 前后端分离
└─ 大型(> 50个页面)
   ├─ 业务模块独立?
   │  ├─ 是 → 微服务
   │  └─ 否 → 前后端分离
   └─ 流量波动大?
      └─ 是 → Serverless

2. 系统分层设计

经典三层架构
┌─────────────────────────────────┐
│      表现层 (Presentation)       │  ← 用户界面、API接口
├─────────────────────────────────┤
│       业务层 (Business)          │  ← 业务逻辑、流程控制
├─────────────────────────────────┤
│      数据层 (Data Access)        │  ← 数据库访问、ORM
└─────────────────────────────────┘
前后端分离架构
┌──────────────┐
│   前端应用    │  ← React/Vue/Angular
└──────┬───────┘
       │ HTTP/WebSocket
┌──────▼───────┐
│   API网关    │  ← 路由、认证、限流
└──────┬───────┘
       │
┌──────▼───────┐
│   后端服务    │  ← 业务逻辑
└──────┬───────┘
       │
┌──────▼───────┐
│   数据库     │  ← PostgreSQL/MongoDB
└──────────────┘
微服务架构
┌──────────┐
│  前端应用 │
└────┬─────┘
     │
┌────▼─────┐
│ API网关  │
└────┬─────┘
     │
     ├─────┬─────┬─────┐
     │     │     │     │
┌────▼┐ ┌─▼──┐ ┌▼───┐ ┌▼────┐
│用户 │ │订单│ │商品│ │支付 │
│服务│ │服务│ │服务│ │服务 │
└────┘ └────┘ └────┘ └─────┘
  │      │      │       │
  └──────┴──────┴───────┘
         │
    ┌────▼────┐
    │ 数据库  │
    └─────────┘

3. 系统架构图

使用 Mermaid 绘制系统架构图:

前后端分离架构示例

graph TB
    subgraph 客户端
        Web[Web 应用]
        Mobile[移动端]
    end

    subgraph 接入层
        CDN[CDN]
        LB[负载均衡]
    end

    subgraph 应用层
        subgraph 前端服务
            FE[前端应用]
        end

        subgraph 后端服务
            API[API 网关]
            Auth[认证服务]
            BIZ[业务服务]
        end
    end

    subgraph 数据层
        DB[(主数据库)]
        Cache[(缓存)]
        MQ[消息队列]
    end

    subgraph 基础设施
        Log[日志系统]
        Monitor[监控告警]
    end

    Web --> CDN
    Mobile --> LB
    CDN --> LB
    LB --> FE
    FE --> API
    API --> Auth
    API --> BIZ
    BIZ --> DB
    BIZ --> Cache
    BIZ --> MQ
    BIZ --> Log

Read the full file on GitHub · 349 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. 6d ago First seen · 349 lines · 25 tokens per session scan A 16d86cbf9ff9

Subscribe to this mod's changes

architect/architecture-design is a skill published in the GitHub repository echoVic/boss-skill (553 stars, last pushed 6d ago), licensed MIT. It adds 25 tokens to every session and 2,874 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.

Related

Other skills, from other repositories

large-workspace-handling

To partition large workspaces (100+ files) into scoped subagent tasks when context is insufficient.

griddynamics/rosetta · 26 tokens

example-skill

Example skill template used for the CreateHub template. You should never use this skill directly as it is just a template made to be updated.

aws-samples/sample-well-architected-skills-and-steering · 32 tokens

color-expert

Use when working with color naming, color theory, color spaces, color definitions, or any task involving color knowledge - palettes, ramps, gradients, conversions, accessibility, perceptual matching, pigment mixing, print-vs-screen color, CSS color syntax, or historical color terminology. Use this skill whenever the…

meodai/skill.color-expert · 92 tokens

business-idea-evaluator

Objectively evaluates business ideas through 18 independent subagents, evidence grading, probabilistic modeling, and Business Reality Score (BRS). Use when the user asks to evaluate, validate, score, or stress-test a business idea, startup concept, side project, SaaS idea, or monetization plan. Always use for business…

2612evgenii-hue/business-idea-evaluator · 94 tokens

should-i-build

Multi-agent market validation skill. Spawns 6 parallel research analysts (Community uses last30days for fresh 30-day signal; Claim Verifier uses deep-research for fact-checking) and delivers a BUILD / CONDITIONAL / PIVOT / STOP verdict with a 7-pillar scorecard. Use when user says "should I build this", "/sib"…

Endokelp/Should-I-build · 118 tokens

cursor-skill

Skill "cursor-skill" from WangYuecheng1106/Magic-Mouse, covering magic skill — computer use via magic mouse (cursordeskpet), design heritage (dual-project hybrid), 一、role, 二、core capabilities and 三、input format.

WangYuecheng1106/Magic-Mouse · 0 tokens