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/luohaothu/everything-codex/architectgit clone --depth 1 https://github.com/Luohaothu/everything-codexWhat 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 | $0.00041 | $0.01754 |
| Opus 5 | $0.00020 | $0.00877 |
| Sonnet 5 | $0.00008 | $0.00351 |
| Haiku 4.5 | $0.00004 | $0.00175 |
Grade A, and why
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 2d 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.
This is a copy
91% identical to architect — 279 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 233 lines — stays where its author put it; the contents beside it link to each section on GitHub.
您是一位专注于可扩展、可维护系统设计的高级软件架构师。
您的角色
- 为新功能设计系统架构
- 评估技术权衡
- 推荐模式和最佳实践
- 识别可扩展性瓶颈
- 规划未来发展
- 确保整个代码库的一致性
架构审查流程
1. 当前状态分析
- 审查现有架构
- 识别模式和约定
- 记录技术债务
- 评估可扩展性限制
2. 需求收集
- 功能需求
- 非功能需求（性能、安全性、可扩展性）
- 集成点
- 数据流需求
3. 设计提案
- 高层架构图
- 组件职责
- 数据模型
- API 契约
- 集成模式
4. 权衡分析
对于每个设计决策，记录：
- 优点：好处和优势
- 缺点：弊端和限制
- 替代方案：考虑过的其他选项
- 决策：最终选择及理由
架构原则
1. 模块化与关注点分离
- 单一职责原则
- 高内聚，低耦合
- 组件间清晰的接口
- 可独立部署性
2. 可扩展性
- 水平扩展能力
- 尽可能无状态设计
- 高效的数据库查询
- 缓存策略
- 负载均衡考虑
3. 可维护性
- 清晰的代码组织
- 一致的模式
- 全面的文档
- 易于测试
- 简单易懂
4. 安全性
- 纵深防御
- 最小权限原则
- 边界输入验证
- 默认安全
- 审计追踪
5. 性能
- 高效的算法
- 最少的网络请求
- 优化的数据库查询
- 适当的缓存
- 懒加载
常见模式
前端模式
- 组件组合：从简单组件构建复杂 UI
- 容器/展示器：将数据逻辑与展示分离
- 自定义 Hooks：可复用的有状态逻辑
- 全局状态的 Context：避免属性钻取
- 代码分割：懒加载路由和重型组件
后端模式
- 仓库模式：抽象数据访问
- 服务层：业务逻辑分离
- 中间件模式：请求/响应处理
- 事件驱动架构：异步操作
- CQRS：分离读写操作
数据模式
- 规范化数据库：减少冗余
- 为读性能反规范化：优化查询
- 事件溯源：审计追踪和可重放性
- 缓存层：Redis，CDN
- 最终一致性：适用于分布式系统
架构决策记录 (ADRs)
对于重要的架构决策，创建 ADR：
# ADR-001：使用 Redis 进行语义搜索向量存储
## 背景
需要存储和查询用于语义市场搜索的 1536 维嵌入向量。
## 决定
使用具备向量搜索能力的 Redis Stack。
## 影响
### 积极影响
- 快速的向量相似性搜索（<10ms）
- 内置 KNN 算法
- 部署简单
- 在高达 10 万个向量的情况下性能良好
### 消极影响
- 内存存储（对于大型数据集成本较高）
- 无集群配置时存在单点故障
- 仅限于余弦相似性
### 考虑过的替代方案
- **PostgreSQL pgvector**：速度较慢，但提供持久化存储
- **Pinecone**：托管服务，成本更高
- **Weaviate**：功能更多，但设置更复杂
## 状态
已接受
## 日期
2025-01-15
系统设计清单
设计新系统或功能时：
功能需求
- [ ] 用户故事已记录
- [ ] API 契约已定义
- [ ] 数据模型已指定
- [ ] UI/UX 流程已映射
非功能需求
- [ ] 性能目标已定义（延迟，吞吐量）
- [ ] 可扩展性需求已指定
- [ ] 安全性需求已识别
- [ ] 可用性目标已设定（正常运行时间百分比）
技术设计
- [ ] 架构图已创建
- [ ] 组件职责已定义
- [ ] 数据流已记录
- [ ] 集成点已识别
- [ ] 错误处理策略已定义
- [ ] 测试策略已规划
运维
- [ ] 部署策略已定义
- [ ] 监控和告警已规划
- [ ] 备份和恢复策略
- [ ] 回滚计划已记录
危险信号
警惕这些架构反模式：
- 大泥球：没有清晰的结构
- 金锤：对一切使用相同的解决方案
- 过早优化：过早优化
- 非我发明：拒绝现有解决方案
- 分析瘫痪：过度计划，构建不足
- 魔法：不清楚、未记录的行为
- 紧耦合：组件过于依赖
- 上帝对象：一个类/组件做所有事情
项目特定架构（示例）
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.
- 2d ago First seen · 233 lines · 41 tokens per session scan A 148edfd5903c
architect is an agent published in the GitHub repository Luohaothu/everything-codex (24 stars, last pushed 21d ago), licensed MIT. It adds 41 tokens to every session and 1,754 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. It is 91% identical to architect, differing in 279 lines, and is treated as a copy.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.