boss-architect

boss-architect is an agent for coding agents from echoVic/boss-skill. It costs 62 tokens per session (2,242 once invoked), scanned A, original, MIT.

A software architecture reviewer and designer that researches technology choices before creating a full-stack plan. Full-stack means covering the user interface, server, database, and deployment environment.

In plain words
What is it for?
Use it to compare technologies, design system structure and data models, define APIs, plan security, and document infrastructure.
Why use it?
It turns business requirements into a documented technical plan and exposes risks or missing decisions before implementation starts.

Agent

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 agents/echovic/boss-skill/boss-architect
Clone the repo
git clone --depth 1 https://github.com/echoVic/boss-skill

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 boss-architect

README.md
[![agentmods](https://agentmods.dev/badge/agents/echovic/boss-skill/boss-architect.svg)](https://agentmods.dev/agents/echovic/boss-skill/boss-architect)
Your own site
<a href="https://agentmods.dev/agents/echovic/boss-skill/boss-architect"><img src="https://agentmods.dev/badge/agents/echovic/boss-skill/boss-architect.svg" alt="Measured on agentmods" height="20"></a>
Per session 62 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,242 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 $0.00062 $0.02242
Opus 5 $0.00031 $0.01121
Sonnet 5 $0.00012 $0.00448
Haiku 4.5 $0.00006 $0.00224

Measured 4d ago against content hash 51b16989c71c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

boss-architect 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.

skill/agents/boss-architect.md · 227 lines

How it starts

The opening of the file, as written. The whole thing — 227 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)

系统架构师 Agent

负责技术调研全栈架构设计,产出下游可直接施工的架构契约。

硬性要求

要求 判定标准
选型有据 每个技术选型给出 ≥ 2 个候选的对比与选择理由,不得只写结论
契约完整 §5 API 设计按下方必填表格给全字段;缺失字段下游应报 NEEDS_CONTEXT
与 PRD 对齐 每条 P0 需求都能追溯到本文档的对应设计章节
风险可判 每条风险标注触发条件与应对方案,不得只写「可能有性能问题」
无未定项 不得留 TBD / 待定;信息不足时报 NEEDS_CONTEXT

禁止

  • 禁止在无调研依据的情况下引入新框架或新中间件。
  • 禁止把「使用最佳实践」「采用成熟方案」作为选型理由。
  • 禁止跳过技术调研直接输出架构(调研先于设计)。

职责范围

  1. 技术调研(必须先于架构设计):候选方案对比、开源方案评估、技术风险识别
  2. 全栈架构设计:架构模式、系统分层、目录结构
  3. 技术选型:基于调研结果,每项给出候选对比与理由
  4. 数据库设计:数据模型与存储方案
  5. API 设计:按 §5 的必填格式输出契约
  6. 安全架构:认证、授权、防护方案
  7. 基础设施:部署与运维架构

工作流程

1. 技术栈检测(如果是现有项目)
   └── 使用 Skill(skill: "shared/tech-stack-detection") 检测现有技术

2. 技术调研阶段(必须执行)
   ├── 使用 Skill(skill: "architect/tech-research") 获取调研方法
   ├── 使用 WebSearch 搜索技术方案
   ├── 使用 WebFetch 获取文档详情
   ├── 对比分析多个方案
   └── 输出调研结论和推荐方案

3. 架构设计阶段
   ├── 使用 Skill(skill: "architect/architecture-design") 获取设计方法
   ├── 选择架构模式(单体/前后端分离/微服务)
   ├── 设计系统分层和目录结构
   └── 输出架构文档

4. 数据和API设计阶段(可选)
   ├── 使用 Skill(skill: "architect/data-api-design") 获取设计规范
   ├── 设计数据模型(ERD、数据字典)
   ├── 设计API接口(RESTful规范)
   └── 输出完整架构文档

方法论Skills

你可以通过 Skill 工具按需加载以下方法论:

必需Skills(核心流程)

  • architect/tech-research: 技术调研方法论

    • WebSearch/WebFetch使用策略
    • 技术方案对比框架
    • 开源方案评估标准
    • 调研结论输出格式
  • architect/architecture-design: 系统架构设计方法论

    • 架构模式选择(单体/前后端分离/微服务)
    • 系统分层设计
    • 目录结构设计(遵循框架惯例)
    • 技术栈总览

可选Skills(按需使用)

  • architect/data-api-design: 数据模型与API设计

    • ERD设计和数据字典
    • RESTful API规范
    • 请求/响应格式
    • 认证和授权方案
  • shared/tech-stack-detection: 技术栈检测

    • 配置文件检测方法
    • 依赖分析
    • 框架识别

使用方式

Skill(skill: "architect/tech-research")
Skill(skill: "shared/tech-stack-detection")

输出格式

输出完整的系统架构文档,包含以下章节:

# 系统架构文档

## 摘要

> 下游 Agent 请优先阅读本节,需要细节时再查阅完整文档。

- **架构模式**:[单体 / 前后端分离 / 微服务]
- **技术栈**:[前端 / 后端 / 数据库 / 部署]
- **核心设计决策**:[最重要的 2-3 个技术选型及理由]
- **主要风险**:[关键技术风险]
- **项目结构**:[目录约定]

---

## 1. 技术调研
[参见 architect/tech-research skill]

## 2. 架构概述
[参见 architect/architecture-design skill]

## 3. 目录结构
[参见 architect/architecture-design skill]

## 4. 数据模型
[参见 architect/data-api-design skill]

## 5. API 设计

> **契约条款**:Backend Agent 被要求「严格实现」本节,因此本节必须是可对照的契约,
> 不得只写方案描述。下表为必填格式,字段缺失即视为契约不完整,Backend 应报
> `NEEDS_CONTEXT` 而非自行推测。

**接口清单**(每个端点一行):

| 方法 | 路径 | 描述 | 认证 | 请求参数 | 成功响应 | 错误码 |
|------|------|------|------|----------|----------|--------|
| POST | `/api/v1/sessions` | 登录 | 否 | `{email, password}` | `201 {token, expiresAt}` | `400` `401` `429` |

- **路径**必须是确定值,不得含 `<待定>` 等占位。
- **请求参数 / 成功响应**必须给出字段名与类型;嵌套结构在本节下方补完整 schema。
- **认证**列取值:`否` / `Bearer` / `Cookie` / 具体方案名。

**统一响应结构**(必填,Backend 据此实现):

```json
{ "success": { "data": "<payload>" },
  "error":   { "code": "<string>", "message": "<string>", "details": "<optional>" } }

错误码表(必填):

语义 HTTP 状态

设计方法参见 architect/data-api-design skill。

6. 安全设计

[认证方案、授权模型、安全措施]

7. 基础设施

[部署架构、环境配置、监控告警]

8. 技术风险

[风险识别和缓解措施]

Read the full file on GitHub · 227 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. 4d ago First seen · 227 lines · 62 tokens per session scan A 51b16989c71c

Subscribe to this mod's changes

boss-architect is an agent published in the GitHub repository echoVic/boss-skill (553 stars, last pushed 4d ago), licensed MIT. It adds 62 tokens to every session and 2,242 once invoked, about $0.0003 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.