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-archgit 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-arch)<a href="https://agentmods.dev/skills/metago-ai/metagolifeform/metago-arch"><img src="https://agentmods.dev/badge/skills/metago-ai/metagolifeform/metago-arch/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-arch"><img src="https://agentmods.dev/badge/skills/metago-ai/metagolifeform/metago-arch.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 | $0.00110 | $0.00734 |
| Opus 5.5 | $0.00044 | $0.00294 |
| Sonnet 5.5 | $0.00022 | $0.00147 |
| Haiku 4.5 | $0.00011 | $0.00073 |
Grade A, and why
metago-arch 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
metago-arch 架构治理（供 AI Agent 读取 · 主包版）
何时使用（强制触发）
- 新建项目、新建模块、编写或修改业务代码、重构、架构审查、代码生成前；
- 用户提到"架构""分层""SOLID""整洁架构""依赖规则""重构"。
规则文件
规则全文：rules/架构治理规则v1.md（本技能目录内，随主包分发）
（若找不到，检索知识库 search-kb.py "架构治理规则" 或询问用户安装位置）
三档分级
- A 档（核心产品）：强制四层 + 依赖规则 + 组合根；
- B 档（中小项目/内部工具）：守 SOLID 的 S+D+OCP + 简单分层；
- C 档（脚本/原型）：不强制检查。
命令（Windows）
metago-lifeform arch version
metago-lifeform arch init [目录] --tier=A|B|C
metago-lifeform arch scaffold <项目名> --tier=A|B|C
metago-lifeform arch check [目录] [--json]
metago-lifeform arch report [目录]
（独立安装包可用 metago-arch 前缀调用相同子命令）
核心规则速记（完整版见规则文件）
- domain 层禁止引用 application/adapters/infrastructure（依赖只能向内）；
- application 层禁止引用 adapters/infrastructure；
- domain/application 禁止 import 框架与数据访问库（Python: sqlalchemy/asyncpg/httpx/requests/redis/fastapi 等；TS: express/sequelize/prisma/pg/axios 等）；
- 用例名是"人类动作"（PlaceOrder），禁止 insert/update/delete/remove 开头；
- 跨层数据传简单 DTO，禁止把数据库行/ORM 实体传进内层；
- 真实项目用传统目录（services/models/api/core）时，先在 arch.config.json 的 check.layers 配置层映射，否则覆盖率为 0 等于没检查；
- 配置/DI 类导入写入 check.allowImports 白名单，避免误报；
- strict 模式下分层覆盖率为 0 = FAIL，禁止宣告通过。
交付前检查
- A/B 档项目：必须运行
metago-lifeform arch check <项目目录>，PASS 才允许宣告完成； - 违规未修复 → 禁止宣告完成；特殊情况 → 标注"已知风险"并说明理由；
- 检查结果可写入
arch-report.md（metago-lifeform arch report）。
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 52 lines · 110 tokens per session scan A d3d7ff8a3dc5
metago-arch is a skill published in the GitHub repository metago-ai/metagolifeform (5 stars, last pushed today), licensed MIT. It adds 110 tokens to every session and 734 once invoked, about $0.0004 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 2026-09-03.
Other skills, from other repositories
codebase-design
Design maintainable module interfaces, review scoped code changes, and simplify implementations with behavioral verification. Use for code review, cleanup, testability, and module design work.
tech-lead/code-review
A checklist-based method for examining code for correctness, security, performance, clarity, and ease of maintenance.
pr-blocker-summarizer
Summarizes open pull requests into a blockers-first standup digest. Activates when the user asks to summarize open PRs, find blocked pull requests, generate a PR standup, or triage review backlog from a PR export.
ponytail-lazy-senior-dev
Applies the "lazy senior developer" mindset. Use this skill whenever generating, modifying, reviewing code, or fixing bugs to prioritize code reuse, minimalism, YAGNI principles, and root-cause fixes. Also use whenever the user says "ponytail", "be lazy", "lazy mode", "simplest solution", "minimal solution", "yagni"…
review
Review Playwright tests for quality. Use when user says "review tests", "check test quality", "audit tests", "improve tests", "test code review", or "playwright best practices check".
full-audit
Exhaustive, denominator-driven audit of an entire area (codebase, docs, memory, skills, DB, config). Runs a 6-phase pipeline: scope agreement + prior-map diff -> deterministic sweep (counts/versions/paths/parsing plus cross-index reconciliation) -> parallel read-only content review (citations forced, rule dry-run) ->…