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/second-order-thinking-skillnpx skills add peterfei/forge-skill --skill second-order-thinking-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/second-order-thinking-skill)<a href="https://agentmods.dev/skills/peterfei/forge-skill/second-order-thinking-skill"><img src="https://agentmods.dev/badge/skills/peterfei/forge-skill/second-order-thinking-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 | $0.00102 | $0.05377 |
| Opus 5 | $0.00051 | $0.02688 |
| Sonnet 5 | $0.00020 | $0.01075 |
| Haiku 4.5 | $0.00010 | $0.00538 |
Grade A, and why
second-order-thinking-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 4d 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 — 237 lines — stays where its author put it; the contents beside it link to each section on GitHub.
二阶思维(Second-Order Thinking)· 思维工具
"First-level thinking is simplistic and superficial, and just about everyone can do it. Second-level thinking is deep, complex and convoluted. The second-level thinker takes a great many things into account." — Howard Marks, The Most Important Thing (2011)
激活条件与触发词
- 直接调用:「用二阶思维分析...」「考虑连锁反应」「这个决策的二阶后果是什么」
- 语义触发:用户面对一个看似明显有利的决策,或不理解为何一个好方案失败了,或想预判政策/策略的长期后果
- 组合调用:「先用二阶思维分析政策影响,再用系统思维分析反馈回路」
方法框架概览
二阶思维的核心是在每次决策时不止考虑直接后果,而是追问"然后呢?这个后果的后果是什么?"至少推演两层连锁反应。它通过后果链推演、补偿性反馈识别、时间延迟意识、隐藏行为者响应分析、复杂系统非线性预测五个原理来避免好心办坏事的短视决策。
核心原理(3-7个,每个须附 ≥2 个跨域证据)
原理 1: 后果链推演(Consequence Chain Reasoning)
一句话定义:每个决策产生直接后果(一阶),直接后果又产生次级后果(二阶),需至少推演两级。
跨域证据:
- 殖民史领域:英国殖民者在印度悬赏捕杀眼镜蛇,结果当地人开始养蛇以赚取赏金,政府取消赏金后养蛇者将蛇放生,眼镜蛇数量反而增加——经典的"眼镜蛇效应"(来源:Horst Siebert, Der Kobra-Effekt, 2001;也有资料追溯至殖民时期官方记录)
- 投资领域:Howard Marks 指出,普通投资者只看到"这是一家好公司"(一阶),二阶思维者看到"好公司已被高估,买入者都是最后一个接盘的"(来源:Marks, The Most Important Thing, 2011)
应用方式:对于每个方案,强制写出一阶后果和二阶后果。用"如果X发生,那么接下来Y也会发生,进而Z会发生"的推演链格式。
局限:超过两阶的推演往往沦为猜测。本方法将重点放在两阶以内,三阶及以上需辅以系统动力学建模。
原理 2: 补偿性反馈(Compensatory Feedback)
一句话定义:系统会对干预产生反制力量,很多看似好的方案会被系统"反弹"回来。
跨域证据:
- 住房政策:纽约在二战期间实行限租令以保护租户,结果房东将出租房改为合作公寓或完全退出租赁市场,可供出租的房源减少约30%,新租客反而更难找到房子(来源:Jenkins, The Rent Control Debate, 2009; Glaeser & Luttmer, The Misallocation of Housing Under Rent Control, American Economic Review, 2003)
- 生态学:Hardin 指出当每个牧民在公共草地上多放一只羊时个体收益递增而过度放牧的成本由所有人承担,最终草地退化所有人受损——经典公地悲剧结构(来源:Hardin, The Tragedy of the Commons, Science, 1968)
应用方式:对每个方案问"谁会因为这个方案的利益受损?他们会怎么做来保护自己的利益?"利益受损方的反弹行为就是补偿性反馈的来源。
局限:并非所有系统都有强补偿性反馈。在高控制度的系统(如军队)中,反馈可能被压制(但会以其他形式出现)。
原理 3: 时间延迟(Time Delay)
一句话定义:二阶后果通常有显著延迟,当前观察到的信号不等于最终结果。
跨域证据:
- 系统动力学领域:Senge 在啤酒分销游戏的实验中,参与者因忽略了订单满足有2周延迟,过度纠正导致库存波动放大10倍以上,证明了延迟如何让局部理性决策产生全局灾难(来源:Senge, The Fifth Discipline, 1990)
- 气候变化:工业革命以来排放的CO₂在大气中持续积累,即使今天立即停止所有排放,全球变暖仍将持续数十年,因为海洋和冰盖对温度变化有跨世纪的响应延迟(来源:IPCC, Sixth Assessment Report, 2021-2023)
应用方式:在分析每个后果时明确标注预期的出现时间窗口。区分"即刻效应"(<1年)、"中期效应"(1-5年)、"长期效应"(>5年)。
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.
- 4d ago First seen · 237 lines · 102 tokens per session scan A f681572b2f3e
second-order-thinking-skill is a skill published in the GitHub repository peterfei/forge-skill (13 stars, last pushed 2mo ago), licensed MIT. It adds 102 tokens to every session and 5,377 once invoked, about $0.0005 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.