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/inversion-skillnpx skills add peterfei/forge-skill --skill inversion-skillgit clone --depth 1 https://github.com/peterfei/forge-skillWhat 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 | $0.00128 | $0.10032 |
| Opus 5 | $0.00064 | $0.05016 |
| Sonnet 5 | $0.00026 | $0.02006 |
| Haiku 4.5 | $0.00013 | $0.01003 |
Grade A, and why
inversion-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 2d 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 — 272 lines — stays where its author put it; the contents beside it link to each section on GitHub.
逆向思维 · 思维工具
"Man muss immer umkehren."(总是反过来想。)— Carl Gustav Jacob Jacobi
"It is remarkable how much long-term advantage people have gotten by trying to be consistently not stupid, instead of trying to be very intelligent." — Charlie Munger, Poor Charlie's Almanack (2005)
激活条件与触发词
- 直接调用:「用逆向思维分析」「按逆向思维的方式思考」「反过来想这个问题」
- 语义触发:用户说"怎么避免失败""最坏情况会是什么""这个计划有什么隐藏的前提""如果它失败了会是因为什么""我们不该做什么"
- 组合调用:「先用逆向思维找出风险点,再用第一性原理重构方案」「先用逆向思维排除错误选项,再用二阶思维评估」
- 场景触发:重大决策前、投资评估、项目启动前、战略规划、风险分析
方法框架概览
逆向思维是一种从终点反推起点的决策方法论。它的核心操作不是寻找最优解,而是系统地识别并排除必定失败的路径——通过反面推演发现致命风险、质疑隐藏前提瓦解虚假确定性、预演失败场景暴露系统脆弱点。Munger 将 Jacobi 的数学格言"man muss immer umkehren"(总是反过来想)转化为普适思维工具,与 Seneca 等 Stoic 哲学家的"premeditatio malorum"(预想厄运)在两千年的时间跨度上形成了独立趋同。逆向思维不问"我怎样才能赢",只问"如果这件事注定失败,它会以什么方式失败"——然后全力确保这些失败模式不会发生。
核心原理(5个,每个须附 ≥2 个跨域证据)
原理 1: 反面推演——从最坏结果反推当前该避免什么
一句话定义:不问"怎么赢",先问"怎么死"——定义绝对不可接受的终局状态,反推出通向该状态的每一步,然后逐一封堵。
跨域证据:
- 投资领域:Munger 和 Buffett 的投资决策从不问"这家公司怎么才能成功",而是先问"什么样的公司一定会失败"。他们发现高杠杆、管理层不诚实、护城河正在变窄的企业十有八九会出问题,于是坚决不碰这些公司。这种"不做什么"的清单比"该做什么"的清单更短、更清晰、更易执行。(来源:Munger, Poor Charlie's Almanack, 2005;Buffett, Berkshire Hathaway Annual Letters, 1977-2023)
- 核工程安全设计:国际原子能机构(IAEA)的"纵深防御"(Defence in Depth)原则要求核电站设计者从最严重的堆芯熔毁场景反推,逐层设置屏障:燃料芯块包壳、反应堆压力容器、安全壳——每一层都假定前一层会失效。福岛核事故后,全球核电站重新按照"如果海啸超过设计基准高度3倍"的逆向假设进行了安全升级。(来源:IAEA, INSAG-10, "Defence in Depth in Nuclear Safety", 1996)
- 军事战略:Sun Tzu 在《孙子兵法》中写道:"昔之善战者,先为不可胜,以待敌之可胜。"——优秀的将领首先确保自己立于不败之地,然后才等待战胜敌人的机会。这不是直接追求胜利,而是通过排除失败来间接确保胜利。(来源:Sun Tzu, The Art of War, 约公元前5世纪)
应用方式:面对任何决策,先定义"绝对失败的终局是什么样子的",然后列出从当前状态通向该终局所需满足的条件链,逐一反问这条链上的每个环节是否已被封堵。
局限:只适用于失败模式已知或有迹可循的领域。对于全新领域(如前沿科学研究),你最坏情况的想象可能完全偏离实际,因为根本不知道"失败"长什么样。
原理 2: 假设前提检验——找出并逐个质疑隐藏的前提条件
一句话定义:每个计划、判断或信念都建立在某些未经检验的前提之上。逆向思维要求逐一挖出这些前提,并用"如果这个前提不成立会怎样"来拷问它们。
跨域证据:
- 科学哲学:Karl Popper 的证伪主义(falsificationism)指出,科学理论的真正标志不是它能在多少案例中被证实,而是它明确说出了在什么条件下它会被证明为错。一个不能被证伪的"理论"不是科学。这正是逆向思维的极致体现——不寻找支持自己的证据,而是寻找否定自己的证据。(来源:Popper, The Logic of Scientific Discovery, 1959)
- 创业投资:Peter Thiel 在评估创业公司时,不是问"这家公司为什么能成功",而是问"有什么重要的真相是只有你相信而大多数人不同意的"。这个问题强制创业者暴露其商业模式中的核心假设,并检验这些假设是否经过了逆向质疑。大多数创业失败不是因为执行不好,而是因为一个关键的隐藏假设从一开始就是错的。(来源:Thiel, Zero to One, 2014)
- 金融风险管理:2008年金融危机前,华尔街的信用违约互换(CDS)定价模型的核心前提是"全国范围内的房价不会同时下跌"。当这个隐藏前提被现实经验证伪时,整个金融大厦坍塌。Nassim Taleb 在此前就通过逆向思考指出了"黑天鹅"风险的不可建模性——关键不是用模型算出概率,而是承认"不知道"本身就是一种知识。(来源:Taleb, The Black Swan, 2007)
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.
- 2d ago First seen · 272 lines · 128 tokens per session scan A 7ad3ff851581
inversion-skill is a skill published in the GitHub repository peterfei/forge-skill (13 stars, last pushed 2mo ago), licensed MIT. It adds 128 tokens to every session and 10,032 once invoked, about $0.0006 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.