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 agentmods add skills/peterfei/forge-skill/first-principles-skillnpx skills add peterfei/forge-skill --skill first-principles-skillgit clone --depth 1 https://github.com/peterfei/forge-skillWrote 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/peterfei/forge-skill/first-principles-skill)<a href="https://agentmods.dev/skills/peterfei/forge-skill/first-principles-skill"><img src="https://agentmods.dev/badge/skills/peterfei/forge-skill/first-principles-skill.svg" alt="Measured on agentmods" 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 | $0.00078 | $0.02928 |
| Opus 5 | $0.00039 | $0.01464 |
| Sonnet 5 | $0.00016 | $0.00586 |
| Haiku 4.5 | $0.00008 | $0.00293 |
Grade A, and why
first-principles-skill 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 3d 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.
How it starts
The opening of the file, as written. The whole thing — 183 lines — stays where its author put it; the contents beside it link to each section on GitHub.
第一性原理 · 思维工具
"The first principle is that you must not fool yourself — and you are the easiest person to fool." — Richard Feynman
激活条件与触发词
- 直接调用：「用第一性原理分析...」「第一性原理拆解...」
- 语义触发：用户面对复杂问题寻找根本原因，或挑战已有假设
- 组合调用：「先用第一性原理拆解，再用系统思维分析」
方法框架概览
第一性原理的核心是回归基本事实重新推导，它通过还原到物理/逻辑极限、区分已知与假设、从基本事实向上推导、警惕类比陷阱四个原理来打破思维惯性和行业惯例。
核心原理（3-7个，每个须附 ≥2 个跨域证据）
原理 1: 还原到基本事实（Reduction to Fundamental Truths）
一句话定义：将问题拆解至不可再分的物理或逻辑基本真理。
跨域证据：
- 航天领域：SpaceX 从铝材成本出发计算火箭制造成本，将发射成本降至1/10（来源：Musk 2012 Wired 访谈）
- 汽车领域：Tesla 从锂、钴、铝原材料现货价推导电池包成本，发现可降80%（来源：Musk 2013 Tesla 投资者日）
应用方式：面对任何问题，先列出构成该问题不可再分的基本事实，忽略行业内约定俗成的中间结论。
局限：某些领域基本事实本身存在争议（如经济学），此时还原目标不是物理事实而是逻辑基点。
原理 2: 区分已知与假设（Separate Known from Assumed）
一句话定义：将已验证事实与未经检验的假设严格分离。
跨域证据：
- 哲学领域：Descartes 在《第一哲学沉思集》（1641）中系统化怀疑方法，将"我思故我在"作为唯一不可怀疑的基点（来源：Descartes, Meditations on First Philosophy）
- 科学方法论：Galileo 区分"亚里士多德说的"和"实验测到的"，推翻重物先落地假设（来源：Galileo, Two New Sciences, 1638）
应用方式：列出当前方案所有假设，逐个标注验证状态。三类标记：已验证（有数据）、可验证（有方法）、不可验证（危险）。
局限：过度区分可能导致分析瘫痪，需判断验证成本与收益。
原理 3: 从基本事实向上推导（Reason Up from Fundamentals）
一句话定义：不是从类比或现有经验推理，而是从基本事实构建全新方案。
跨域证据：
- 零售领域：Amazon 从"用户要便宜/选择多/便捷"推导出电商模式，而非类比 Walmart（来源：Bezos 1997 致股东信）
- 区块链领域：Satoshi 从"去中心化共识的基本问题"推导出 PoW 方案，而非改进银行系统（来源：Bitcoin Whitepaper, 2008）
应用方式：从基本事实开始，问"基于这些事实最优解是什么？"禁止用"别家都这么做"作推理依据。
局限：完全从零推导可能忽略行业隐性知识，需在推导后与已有方案对比。
原理 4: 警惕类比推理陷阱（Beware of Analogy Trap）
一句话定义："这就像那个"是人类最危险的思维捷径。
跨域证据：
- 科技领域：初代 iPhone 不是"缩小的 Mac"，而是从触控交互基本事实推导的新范式（来源：Jobs 2007 iPhone 发布会）
- 教育领域：Pinker 指出教育不是工厂流水线，"标准化考试=质量控制"是危险类比（来源：Pinker, The Blank Slate, 2002）
应用方式：每当想说"这就像..."时暂停，反问：这个类比在哪个关键维度不成立？
局限：类比对沟通和启发仍有价值。不是禁止类比，而是禁止用类比替代推导。
操作协议（Agentic Protocol）
Step 1: 问题分类 — 判断该方法是否适用于当前问题
适用信号：
- 问题存在约定俗成的行业做法但效果不好
- 需在多个方案中做根本性选择
- 面对技术或商业的根本性创新挑战
不适用信号：
- 问题主要涉及情感/人际关系（适用设计思维或系统思维）
- 需要快速执行而非深度思考（适用精益创业的快速验证）
- 信息极度不足无法识别基本事实
输出：适用 / 不适用（附理由）/ 部分适用（附建议）
Step 2: 第一性原理式拆解 — 研究维度须从核心原理推导，禁止使用通用"搜索相关信息"
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.
- 3d ago First seen · 183 lines · 78 tokens per session scan A 8fb66dbfca64
first-principles-skill is a skill published in the GitHub repository peterfei/forge-skill (13 stars, last pushed 2mo ago), licensed MIT. It adds 78 tokens to every session and 2,928 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 2026-08-30.
Other skills, from other repositories
descend
Verifies whether the problem was correctly identified before solving, auditing pattern matches against first principles.
fundraising-narrative
This skill should be used when the user asks about "pitch deck", "fundraising story", "investor pitch", "VC narrative", "pitch narrative", "fundraising deck", "pitch structure", "Sequoia format", "why now slide", "market size slide", "TAM SAM SOM", "earned secret", "value hypothesis", "product-market fit"…
investor-relations
This skill should be used when the user asks about "investor update", "board deck", "board meeting", "investor communication", "monthly update", "quarterly update", "investor email", "bad news investors", "pivot communication", "crisis communication investors", "investor ask", "warm intro", "VC relationship"…
ux-principles
User research, usability heuristics, user psychology, accessibility, inclusive design, user testing, and UX metrics.
opencli-sitemap-author
Use when creating or maintaining OpenCLI site sitemaps: agent-facing navigation, page-state, action, workflow, API-reference, pitfall, and fallback knowledge for a website. Use after browser exploration discovers durable site context, when a sitemap is stale, or when promoting local site knowledge into the repo.
golden-rss
Use when testing the rss golden build.