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-first-principlesgit 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-first-principles)<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.
<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>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 | $0.00079 | $0.01182 |
| Opus 5 | $0.00039 | $0.00591 |
| Sonnet 5 | $0.00016 | $0.00236 |
| Haiku 4.5 | $0.00008 | $0.00118 |
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.
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)
-
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"?
-
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?
-
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
-
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
-
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
- 与
metago-deep-reasoning协同:F0 拆解作为深度推理的前置事实层 - 与
metago-decision-lock协同:F0 结论进入决策锁意图验证 - 与
metago-action-plan协同:F0 拆解产出的事实基元作为行动计划的地基 - 与
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)
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.
- 9d ago First seen · 76 lines · 79 tokens per session scan A 1af166445114
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.
Other skills, from other repositories
card-xiaohongshu
Xiaohongshu-style knowledge cards, arranged as a swipeable multi-card carousel.
extract
Run the full Semantica semantic extraction pipeline on a file or selected text — NER, relations, events, coreference resolution, triplets, and validation. Clears result cache before each run. Returns Markdown tables with entity/relation/event/triplet results and inline validator warnings.
prototype-web
A clickable, high-fidelity web product prototype with navigation, a hero section, feature cards, steps, social proof, and optional pricing. It is designed to resemble a finished landing page while remaining a prototype.
deck-course-module
A course or workshop slide template with persistent learning goals, teaching pages, multiple-choice self-tests, and a wrap-up.
loop-orchestration
Reference loop-orchestration example; a local loop host chains governed runx turns through receipts, budgets, context, and stop policy.
slack-notify
Plan a digest-bound Slack notification, then deliver the exact approved channel post through any compatible Slack binding with provider readback.