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 skills add metago-ai/metagolifeform --skill metago-architecture-designgit clone --depth 1 https://github.com/metago-ai/metagolifeformWrote 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/skills/metago-ai/metagolifeform/metago-architecture-design)<a href="https://agentmods.dev/skills/metago-ai/metagolifeform/metago-architecture-design"><img src="https://agentmods.dev/badge/skills/metago-ai/metagolifeform/metago-architecture-design/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/skills/metago-ai/metagolifeform/metago-architecture-design"><img src="https://agentmods.dev/badge/skills/metago-ai/metagolifeform/metago-architecture-design.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 | $0.00073 | $0.01184 |
| Opus 5.5 | $0.00029 | $0.00474 |
| Sonnet 5.5 | $0.00015 | $0.00237 |
| Haiku 4.5 | $0.00007 | $0.00118 |
Grade A, and why
metago-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 1mo 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.
What it actually says
架构设计（metago-architecture-design）
描述
根据业务需求生成完整系统架构方案，覆盖架构模式选择、模块分解、接口契约设计、数据流规划、技术选型。输出含决策依据和权衡分析的架构文档。
触发条件
- 用户请求架构设计、系统设计、技术选型时激活
- 新项目启动阶段
- 系统重构/迁移规划阶段
- 与
metago-action-plan协同：重大技术决策时强制触发
核心流程
1. 需求分解
- 功能性需求拆解（核心用例、边缘场景）
- 非功能性需求量化（QPS、延迟、可用性、数据规模）
- 约束条件识别（预算、团队规模、技术栈、合规要求）
- 演进路径规划（MVP → 完整版 → 规模化）
2. 架构模式选择
- 评估候选架构模式（单体/微服务/事件驱动/分层/CQRS）
- 基于需求约束的权衡分析
- 架构决策记录（ADR - Architecture Decision Record）
- 替代方案与降级策略
3. 模块分解
- 领域驱动设计（DDD）边界划分
- 模块职责定义（单一职责原则）
- 模块间依赖关系（无循环依赖）
- 接口契约定义（输入/输出/异常）
4. 数据流设计
- 数据模型设计（ER 图、字段约束）
- 数据流向（同步/异步、推/拉）
- 一致性策略（强一致/最终一致）
- 缓存策略与失效机制
5. 技术选型
- 技术栈评估（成熟度、社区、性能、人才市场）
- 选型依据记录（为什么选 A 不选 B）
- 风险评估（供应商锁定、废弃风险）
- 替代方案储备
架构原则检查清单
- 高内聚低耦合（模块内聚度 ≥ 0.8，耦合度 ≤ 0.3）
- 单一职责（每个模块只做一件事）
- 开闭原则（对扩展开放，对修改关闭）
- 可独立部署（模块可独立部署和回滚）
- 可水平扩展（无状态服务可水平扩展）
- 故障隔离（单点故障不影响全局）
- 可观测性（日志、指标、追踪完备）
输出格式
【架构设计文档】
## 1. 需求摘要
- 核心用例：...
- 性能指标：QPS=X, 延迟≤Xms, 可用性≥X%
- 约束条件：...
## 2. 架构概览
架构模式：[模式名]
选择依据：[权衡分析]
替代方案：[方案 B, 方案 C]
## 3. 模块设计
| 模块 | 职责 | 接口 | 依赖 |
|------|------|------|------|
| ... | ... | ... | ... |
## 4. 数据流
[数据流向图描述]
一致性策略：...
## 5. 技术选型
| 层次 | 技术 | 选型依据 | 替代方案 |
|------|------|----------|----------|
| ... | ... | ... | ... |
## 6. 演进路径
- MVP：...
- V1：...
- 规模化：...
## 7. 风险与缓解
| 风险 | 概率 | 影响 | 缓解措施 |
|------|------|------|----------|
| ... | ... | ... | ... |
与其他技能的协同
- 与
metago-action-plan协同：架构设计输出联动行动计划生成 - 与
metago-decision-eval协同：架构决策需通过决策评估 - 与
metago-critique协同：架构方案需通过 L1-L5 批判性分析 - 与
metago-whatif协同：反事实推演验证架构韧性 - 与
metago-coupling-optimize协同：模块耦生度量化优化
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.
- 1mo ago First seen · 115 lines · 73 tokens per session scan A 042e275d2420
metago-architecture-design is a skill published in the GitHub repository metago-ai/metagolifeform (5 stars, last pushed today), licensed MIT. It adds 73 tokens to every session and 1,184 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-08-31.
Other skills, from other repositories
cqrs-implementation
Implement Command Query Responsibility Segregation for scalable architectures. Use when separating read and write models, optimizing query performance, or building event-sourced systems.
microservices-patterns
Design microservices architectures with service boundaries, event-driven communication, and resilience patterns. Use when building distributed systems, decomposing monoliths, or implementing microservices.
diagnose-backend-bug
Diagnose a bounded backend or multi-service failure from GitHub Issues, Jira, Aone, user-provided exports, logs, traces, responses, stack traces, or job records. Use when a service, API, RPC, worker, queue, CLI, or scheduled job bug needs correlation through the project's existing observability route before repair; do…
durable-objects
Build, debug, or review Cloudflare Durable Objects code for persistent state and coordination.
api-doc-generator
Generate API documentation from source code, supporting REST APIs, GraphQL, and various documentation formats.
firebase-cloud-functions
Use when calling callable functions (httpsCallable), passing data to server-side logic, handling function errors/timeouts, configuring regions, or testing with the Emulator Suite.