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 R2h1/my-book-skills --skill v03-klugegit clone --depth 1 https://github.com/R2h1/my-book-skillsWrote 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/r2h1/my-book-skills/v03-kluge)<a href="https://agentmods.dev/skills/r2h1/my-book-skills/v03-kluge"><img src="https://agentmods.dev/badge/skills/r2h1/my-book-skills/v03-kluge/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/r2h1/my-book-skills/v03-kluge"><img src="https://agentmods.dev/badge/skills/r2h1/my-book-skills/v03-kluge.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 | $0.00108 | $0.01866 |
| Opus 5 | $0.00054 | $0.00933 |
| Sonnet 5 | $0.00022 | $0.00373 |
| Haiku 4.5 | $0.00011 | $0.00187 |
Grade A, and why
Kluge识别与对抗法 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 12d 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 — 146 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Kluge识别与对抗法
R — 原文
"什么是基因误指挥？数十万年来，我们的身体和本能都在进化，以适应不同时代的环境。在原始时代，我们看到食物就要无条件地冲上去，这样才有利于生存。但对于因能量摄入过多而患上成人病的现代人来说，这种本能反而会让人陷入危险境地。这种错误的本能就是'Kluge'。"
— 金承焕, 第四章
I — 方法论骨架
Kluge（克鲁机/基因误指挥）是指进化遗留的本能在现代社会产生的误导效应。核心五种Kluge：
- 对新事物的恐惧 — 逃避挑战和不确定性
- 声誉敏感 — 太在乎别人怎么看自己
- 规避损失倾向 — 害怕吃亏所以不敢下注
- 认知偏见 — 一次失败就否定整类事物
- 情感试探 — 被情绪绑架决策
对抗方法：做决策前先问'这个冲动在原始时代有利于生存吗？如果是，那它在现代社会可能恰恰是错的'，然后逆本能行动。
A1 — 书中的应用
案例 1: 作者做YouTube
- 问题: 犹豫6个月做YouTube，面对'没设备''怕挨骂''已经是红海'等放弃理由
- 方法论的使用: 他用Kluge理论一一识别并战胜，在100个想开始的人中成为第2个实际开始的人
- 结论: Kluge识别让他克服了拖延和恐惧
- 结果: 成为最有名的自我开发YouTuber之一
案例 2: 作者乡下买房
- 问题: 看了4栋房子后大脑发出'够了快选'的命令
- 方法论的使用: 他识别出这是Kluge疲劳感，主动用'买错的痛苦'作为疫苗对抗，继续多看更多房源
- 结论: Kluge疲劳感会导致决策仓促，需要用反向疫苗对抗
- 结果: 做出更理性的购房决策
案例 3: 首尔大学A的全感染
- 问题: 被多种Kluge全面感染（认知失调+声誉误指挥+偏见）
- 方法论的使用: 从未使用——持续被Kluge控制
- 结论: 反面案例——被Kluge感染的后果
- 结果: 生意失败、人脉枯竭
A2 — 触发场景
用户会在什么情境下需要这个 skill?
- 用户在做新尝试前找到'合理'的拖延理由
- 用户因为害怕别人怎么看而不敢做正确决定
- 用户在决策时过度担心亏损
语言信号
- '现在开始太晚了'
- '我还没准备好'
- '别人会怎么想'
- '我干过，我知道'
- '太冒险了'
与相邻 skill 的区分
- 与
摆脱自我意识的区别：自我意识是'身份层面的防御'（不想承认自己需要改变），Kluge是'本能层面的误指挥'（进化遗留的恐惧/偏见）。前者处理'面子'，后者处理'本能' - 与
身份认同塑造法的关系：识别Kluge是打破旧身份的关键前置步骤
E — 可执行步骤
当 skill 被激活后，agent 应按以下步骤执行:
-
识别当前决策中的Kluge信号
- 引导用户问自己:'这个恐惧/犹豫在原始时代有利于生存吗？'
- 帮助用户判断：如果是生存本能，在现代社会可能恰恰是错的
- 完成标准: 用户识别出至少一个Kluge在影响自己的决策
-
用Kluge疫苗对抗
- 对新事物恐惧 → 问'不做的损失是什么？
- 声誉恐惧 → 问'这些人一年后还在乎我吗？
- 规避损失 → 问'如果不会亏，我会怎么做？'
- 完成标准: 用户为每种识别出的Kluge设计了反向疫苗
-
逆本能行动
- 确认是Kluge后，立即执行相反行动
- 帮用户制定最小的逆本能行动（如：今天就发一篇帖子，而不是等'准备好'）
- 完成标准: 用户确定了一个具体的逆本能行动并承诺执行
B — 边界
不要在以下情况使用此 skill
- Kluge框架不能替代专业的心理咨询
- 不是所有恐惧都是Kluge（有些风险是真实的，需要仔细区分）
- 不要在用户面临真实危险时套用Kluge（如财务崩盘、健康危机）
作者在书中警告的失败模式
- 首尔大学A的Kluge全面感染（ce07）
- 回避新挑战'别多事了'（ce08）
- 声誉误指挥——过分在意他人评价（ce09）
- 规避损失倾向——害怕亏损不下注（ce10）
作者的盲点 / 时代局限
- Kluge框架将所有恐惧都归因为进化遗留，可能简化了复杂的人类心理
- 真实风险鉴别需要足够的领域知识，Kluge理论无法提供这种判断力
- 作者的'逆本能行动'建议在某些高风险领域（如投资）可能被滥用为'勇敢地冒险'
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.
- 12d ago First seen · 146 lines · 108 tokens per session scan A a8f6ce9eedd8
Kluge识别与对抗法 is a skill published in the GitHub repository R2h1/my-book-skills (2 stars, last pushed 27d ago), licensed MIT. It adds 108 tokens to every session and 1,866 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 2026-08-31.
Other skills, from other repositories
shortfilm-prompt
Generate cinematic AI shortfilm prompts (works with Seedance 2.0, Xiaoyunque, Sora, Kling, Jimeng, Veo) using the 5-stage structure from Mx-Shell's Zombie Scavenger. Trigger when the user wants transformation sequences, multi-shot narrative shorts, weapon-charge/combat segments, emotional family/pet/farewell…
simp
A relationship-advice skill that helps interpret signals, plan respectful approaches, and write sincere messages for someone you like.
packaging-workshop
A final presentation review for finished Chinese content. It works on the title, opening, layout, punctuation, images, and platform format without changing the main body.
chinese-write-checker
A Chinese-language review process for checking an article from an editor's, reader's, writer's, and publishing platform's viewpoints.
editor-revisor
A Chinese-language editing assistant that finds unnecessary words, formulaic openings, forced parallel phrasing, and slogan-like endings. It offers a deletion-focused mode and a fuller rewriting mode for any draft.
voice-dissolver
A writing-analysis skill that identifies the author's real voice before any rewriting. It marks distinctive passages to preserve and can ask questions to clarify the intended feeling, stance, and audience.