metago-first-principles

metago-first-principles is a skill for Claude Code, Codex from metago-ai/metagolifeform. It costs 79 tokens per session (1,182 once invoked), scanned A, original, MIT.

A first-principles planning add-on that breaks a task down into verifiable facts before rebuilding a solution. It separates assumptions and habits from facts that can be checked or disproved.

In plain words
What is it for?
Use it before any task to record assumptions, identify atomic facts, derive a plan from those facts, and summarize the reasoning behind the decision.
Why use it?
It helps prevent familiar industry practices or guesses from being treated as automatically correct. The resulting plan explains its factual basis and how it differs from the usual approach.

Skill for Claude CodeCodex

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

Good fit Use it before any task to record assumptions, identify atomic facts, derive a plan from those facts, and summarize the reasoning behind the decision.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/metago-ai/metagolifeform/metago-first-principles
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-first-principles
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-first-principles

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/metago-ai/metagolifeform/metago-first-principles"><img src="https://agentmods.dev/badge/skills/metago-ai/metagolifeform/metago-first-principles.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 79 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,182 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 $0.00079 $0.01182
Opus 5 $0.00039 $0.00591
Sonnet 5 $0.00016 $0.00236
Haiku 4.5 $0.00008 $0.00118

Measured 9d ago against content hash 1af166445114, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

metago-first-principles 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 9d 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-first-principles/SKILL.md · 76 lines

What it actually says

第一性原理强制拆解(metago-first-principles)

描述

任何任务执行前,必须完成第一性原理拆解(F0):剥离任务中的所有假设与行业惯例,直达不可再分的客观事实基元(用户真实需求 / 可验证状态 / 数据事实 / 物理定律),再从基元重新推导方案。禁止把"常见做法"直接当作"正确做法"。基于 A37 第一性原理公理 + D44 第一性原理强制触发属性。

触发条件

任何任务执行前自动触发(A37 · D44 强制前置)。8.2 强制思维协议第 0 层;与 metago-deep-reasoning(FIPO 深度推理)协同。

⚠️ 强制说明(不依赖触发词):本技能由 A37 公理 + D44 属性无条件强制激活——用户未说出任何触发关键词,AI 也必须在每个任务执行前完成 F0 拆解,跳过即违反 A37。下方 YAML trigger: 列表仅是"用户主动点名"时的快捷通道,不是激活前提。判定:任务完成报告/执行过程中无 F0 记录 = 违规。

核心流程(F0 五步)

  1. 剥离假设(Strip Assumptions)

    • 列出任务中隐含的所有假设
    • 逐条标注来源:是"别人的说法"?"行业惯例"?"自己的猜测"?还是"已验证事实"?
  2. 剥离惯例(Strip Conventions)

    • 标注哪些做法是"因为一直这么做"而非"因为正确"
    • 问:如果今天从零开始设计,还会选这个方案吗?
  3. 提取事实基元(Extract Atomic Facts)

    • 直达不可再分的客观事实:物理定律 / 数据事实 / 用户真实需求 / 可验证的系统状态
    • 每个基元必须可被验证或可被证伪
  4. 从基元重建(Rebuild from Facts)

    • 从事实基元重新推导方案(不是从别人的方案推导)
    • 与惯性方案对比:差异点必须逐条说明理由
  5. 记录 F0 结论(Record)

    • 重大任务输出前必须有 F0 拆解记录(一句话结论即可,但必须有)
    • 格式:F0: 基元=[...],推导=[...],与惯性方案差异=[...]

输出格式

{
  "f0": {
    "assumptions": ["假设1(来源:惯例)", "假设2(来源:猜测)"],
    "atomicFacts": ["事实基元1(可验证)", "事实基元2(可证伪)"],
    "rebuild": "从基元推导出的方案",
    "diffFromConvention": "与惯性方案差异及理由",
    "conclusion": "一句话 F0 结论"
  }
}

判定标准(通过/不通过)

  • ✅ 通过:完成假设剥离 → 基元提取 → 从基元重建,且与惯性方案差异有理由
  • ❌ 不通过:直接沿用惯性方案、无基元、无差异说明 → 禁止进入下一步

与其他技能的协同

  • metago-deep-reasoning 协同:F0 拆解作为深度推理的前置事实层
  • metago-decision-lock 协同:F0 结论进入决策锁意图验证
  • metago-action-plan 协同:F0 拆解产出的事实基元作为行动计划的地基
  • metago-adversarial-review 协同:F0 基元可作为对抗式审查的验证基准

根源文档

《元构全息智能引擎》(A37 第一性原理公理、D44 第一性原理强制触发属性、8.2 强制思维协议第 0 层)

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. 9d ago First seen · 76 lines · 79 tokens per session scan A 1af166445114

Subscribe to this mod's changes

metago-first-principles is a skill published in the GitHub repository metago-ai/metagolifeform (4 stars, last pushed 11d ago), licensed MIT. It adds 79 tokens to every session and 1,182 once invoked, about $0.0004 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 2026-09-03.