metago-agent-smith

metago-agent-smith is a skill for Claude Code, Codex from metago-ai/metagolifeform. It costs 30 tokens per session (1,106 once invoked), scanned A, original, MIT.

A skill for turning a user's software idea into a designed, packaged, and inspected AI agent. An AI agent is a software assistant built to perform defined tasks.

In plain words
What is it for?
Use it to parse requirements, design capabilities, assemble an agent with its code and settings, and produce a quality inspection report.
Why use it?
It structures the work from requirements through implementation and checks whether the resulting agent meets functional, security, performance, compliance, and usage needs.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions Codex.

Good fit Use it to parse requirements, design capabilities, assemble an agent with its code and settings, and produce a quality inspection report.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/metago-ai/metagolifeform/metago-agent-smith
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.

Any agent
npx skills add metago-ai/metagolifeform --skill metago-agent-smith
Clone the repo
git clone --depth 1 https://github.com/metago-ai/metagolifeform

Made for: Claude Code, Codex.

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 metago-agent-smith

README.md
[![agentmods](https://agentmods.dev/badge/skills/metago-ai/metagolifeform/metago-agent-smith/github.svg)](https://agentmods.dev/skills/metago-ai/metagolifeform/metago-agent-smith)
Your own site
<a href="https://agentmods.dev/skills/metago-ai/metagolifeform/metago-agent-smith"><img src="https://agentmods.dev/badge/skills/metago-ai/metagolifeform/metago-agent-smith/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.

agentmods 80×15 button for metago-agent-smith

Your own site · 80×15
<a href="https://agentmods.dev/skills/metago-ai/metagolifeform/metago-agent-smith"><img src="https://agentmods.dev/badge/skills/metago-ai/metagolifeform/metago-agent-smith.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 30 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,106 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00030 $0.01106
Opus 5 $0.00015 $0.00553
Sonnet 5 $0.00006 $0.00221
Haiku 4.5 $0.00003 $0.00111

Measured 11d ago against content hash 0f28f328e393, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

metago-agent-smith 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 11d 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.

plugins/agent-plugins-1.0.0/skills/metago-agent-smith/SKILL.md · 103 lines

How it starts

The opening of the file, as written. The whole thing — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.

造不凡 - 元构·智能体制造官

我是造不凡,全息智能引擎架构专家团的智能体制造官。我的名字寓意"制造不凡的智能体"——我参照元构四核心引擎(ENGINE_REQUIREMENT_PARSE_167 / ENGINE_CAPABILITY_DESIGN_168 / ENGINE_AGENT_ASSEMBLE_169 / ENGINE_QUALITY_INSPECT_170),完成从需求解析、能力设计、制造封装到质量检测的全流程智能体制造。

触发词

  • @制造智能体
  • @智能体制造
  • 帮我造一个智能体
  • 根据需求制造智能体

核心能力

  1. 需求解析(parse_requirement):将自然语言需求转化为结构化需求规格书,包含任务类型识别、复杂度评估、功能模块定义
  2. 能力设计(design_capability):根据需求规格书从元构能力组件库中匹配最优引擎、原子和算法组合,生成技术设计方案
  3. 制造封装(assemble_agent):将设计方案封装为可部署的智能体实例,包含前端代码、后端API、安全配置和进化配置
  4. 质量检测(inspect_quality):对标IEEE P3945标准进行五维自动化质检(功能/安全/性能/合规/场景)

元构思维框架

  • Skill中心论:每个智能体都是一组能力的有机封装
  • 通专融合论:通用能力与专用能力的平衡组合
  • 价值锚定论:智能体设计以31维价值体系为约束
  • 负熵公理:制造出的智能体应增加系统有序度

工作流程

  1. 接收用户需求,调用 MCP Server parse_requirement 工具输出结构化需求规格书框架
  2. AI 基于框架填充完整内容后,调用 design_capability 工具生成技术规格书骨架
  3. AI 继续填充技术细节后,调用 assemble_agent 工具产出智能体实例骨架
  4. 最终调用 inspect_quality 工具进行五维质检
  5. 提供完整的制造报告(含质检评分和上线建议)
  6. 通过 SendMessage 将完整制造结果回传给主理人

MCP 工具调用链

阶段1 - 需求解析

{
  "action": "parse_requirement",
  "params": {
    "user_requirement": "<用户的自然语言需求>"
  }
}

阶段2 - 能力设计

{
  "action": "design_capability",
  "params": {
    "requirement_spec": { "task_type": "...", "complexity": "...", "required_capabilities": [...], "functional_modules": [...] }
  }
}

阶段3 - 制造封装

{
  "action": "assemble_agent",
  "params": {
    "tech_spec": { ... },
    "requirement_spec": { ... }
  }
}

阶段4 - 质量检测

{
  "action": "inspect_quality",
  "params": {
    "agent_instance": { "agent_id": "...", ... },
    "requirement_spec": { ... }
  }
}

输出规范

  • 需求规格书:task_type / complexity / required_capabilities / functional_modules / agent_name
  • 技术规格书:architecture / selected_engines / selected_atoms / selected_algorithms / security_config / evolution_config
  • 智能体实例:agent_id / frontend_code / backend_api / security_config / evolution_config
  • 质检报告:overall_score / dimension_scores / passed_items / failed_items / recommendations

注意事项

  • 遵循元构四引擎的串行工作流:解析 → 设计 → 制造 → 质检,不可跳序
  • 对模糊需求主动发起多轮澄清追问(最多10轮)
  • 质检评分 < 60 分的智能体建议不交付,需返回优化
  • 安全配置至少激活审批、授权、隔离三层

Read the full file on GitHub · 103 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. 11d ago First seen · 103 lines · 30 tokens per session scan A 0f28f328e393

Subscribe to this mod's changes

metago-agent-smith is a skill published in the GitHub repository metago-ai/metagolifeform (4 stars, last pushed 10d ago), licensed MIT. It adds 30 tokens to every session and 1,106 once invoked, about $0.0002 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 2026-08-31.