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 v16git 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/v16)<a href="https://agentmods.dev/skills/r2h1/my-book-skills/v16"><img src="https://agentmods.dev/badge/skills/r2h1/my-book-skills/v16/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/v16"><img src="https://agentmods.dev/badge/skills/r2h1/my-book-skills/v16.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 | $0.00131 | $0.01987 |
| Opus 5 | $0.00066 | $0.00993 |
| Sonnet 5 | $0.00026 | $0.00397 |
| Haiku 4.5 | $0.00013 | $0.00199 |
Grade A, and why
逆行者转轮 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 — 144 lines — stays where its author put it; the contents beside it link to each section on GitHub.
逆行者转轮
R — 原文
'当失败来临时,你完全可以感到快乐,这意味着你的任务比你的水平高,你很快就会升级。因为你离自由更近了。顺理者在失败面前错过升级机会,逆行者会思考:我需要提高什么才能进入下一个等级?'
— 金承焕, 第八章
I — 方法论骨架
逆行者转轮是面对失败的认知转换框架——将失败重新定义为'升级信号'而非'惩罚':
- 失败=等级信号 — 当你设定了更高的目标,失败是理所当然的。失败不代表'你不行',只代表'你的当前等级不够挑战这个任务'。就像游戏里等级不够打不过Boss一样正常。
- 顺理者 vs 逆行者 — 面对失败,顺理者找借口责怪他人;逆行者问'我需要提高什么才能进入下一个等级?'。同一件事,不同的解读产生完全不同的结果。
- 七步法回溯 — 失败后不要盲目再试,而是回到七步法排查:是自我意识在防御?是Kluge在误指挥?是大脑训练不够?还是工具箱缺了某个技能?
- 绝望=大升级前兆 — 最绝望的时候恰恰是大升级即将到来的信号。作者在最痛苦时告诉自己:'上帝要把我塑造得多么伟大,才会给我这样的苦难?'
核心思维转换: 从'我失败了,我不行'转向'我的等级到了,该升级了'
A1 — 书中的应用
案例 1: 作者住院期间的转轮
- 问题: 入伍后发现合伙人和员工背叛,生意全毁,压力下患强直性脊柱炎住院6个月
- 方法论的使用: 最绝望时决定'上帝要把我塑造得多么伟大,才会给我这样的苦难',在医院大量读书
- 结论: 将绝望视为成长契机
- 结果: 读《从负数开始出发》后顿悟是自己的'气量太小',彻底停止抱怨,从零开始
案例 2: 作者承认气量太小
- 问题: 多次创业失败、被合伙人背叛、资产清零
- 方法论的使用: 彻底反思——不是运气不好,不是别人问题,'只是我的气量太小了'
- 结论: 承认自己的不足后,不再怨天尤人
- 结果: 心态彻底转变,开始脚踏实地从小事积累
案例 3: 首尔大学A的转轮缺失
- 问题: 面对失败从不自我反思,持续归咎于外部
- 方法论的使用: 从未使用——顺理者的失败模式
- 结论: 反面案例——把失败当惩罚而非信号
- 结果: 持续失败,人脉枯竭
A2 — 触发场景
用户会在什么情境下需要这个 skill?
- 用户遭遇重大失败或挫折后感到沮丧
- 用户在连续失败后开始怀疑自己
- 用户看到别人成功后感到嫉妒或不甘
语言信号
- '我失败了,我是不是不行?'
- '为什么我总是失败?'
- '这不公平'
- '我已经努力了但没用'
与相邻 skill 的区分
- 与
元认知提升法的关系: 元认知帮用户'准确判断自己当前等级',逆行者转轮帮用户'在失败后使用这个信息制定升级计划' - 与
摆脱自我意识的关系: 失败触发自我意识防御(想找借口/怪别人),逆行者转轮提供了替代反应模式
E — 可执行步骤
当 skill 被激活后,agent 应按以下步骤执行:
-
重新框架失败
- 引导用户:'失败代表你在挑战更高等级的任务。如果你没失败,说明你在做已经会的事情。'
- 帮用户区分'失败'和'失败者'——失败是事件,不是身份
- 完成标准: 用户能说出'这次失败不是因为我不行,而是因为等级不够'
-
七步法回溯排查
- 引导用户逐一检查:自我意识在作祟?Kluge在误指挥?大脑训练不够?工具箱缺技能?
- 找出最薄弱的环节
- 完成标准: 确定了一个需要提升的短板
- 判停条件: 如果用户把所有问题都归因于一个环节,提醒其他可能性
-
制定升级计划
- 针对找到的短板,制定一个具体的提升计划
- 回到对应的skill(如需要训练大脑就用22战略,需要打破防御就用自我意识三步法)
- 完成标准: 用户有一个明确的下一次再挑战计划
B — 边界
不要在以下情况使用此 skill
- 用户面临的是真实创伤(亲人去世、严重疾病)——此时需要的是情感支持而非认知重构
- 用户将'失败是升级信号'简化为'所以我不需要努力'——这是对概念的滥用
- 用户的问题是系统性压迫(如职场排挤)而非个人能力不足——此时需要的是环境改变而非个人升级
作者在书中警告的失败模式
- ce21: 顺理者的失败循环——怪别人、怪社会、怪父母
- ce04: 找替罪羊代替自我反思
- ce19: 自我意识僵尸——固化到无可救药
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 · 144 lines · 131 tokens per session scan A d9bb70f5397e
逆行者转轮 is a skill published in the GitHub repository R2h1/my-book-skills (2 stars, last pushed 27d ago), licensed MIT. It adds 131 tokens to every session and 1,987 once invoked, about $0.0007 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
accint-commitments
Triage acc's open promises and close them with honest real-world verdicts via accact(runtime="outcome").
ai-efficiency-audit
Audit a person's or team's weekly workflow, identify which tasks AI can realistically take over, and produce an evidence-based, manager-ready efficiency proposal with hours-saved ranges and a two-week pilot plan. Use this skill whenever the user mentions AI efficiency pressure from leadership, or says any of these …
weekly-report-alchemy
A tool that turns scattered work records—such as chat logs, code commits, calendar entries, and notes—into a structured weekly or monthly report.
screen-detox
A habit-change framework for reducing non-work screen use such as social media, short videos, games, and endless scrolling.
monkey-mind-meditation
A meditation and reflection guide for a busy or anxious mind. It treats recurring thoughts as something to observe and examine, while noting that acute serious mental-health problems need professional care.
company-brain
Your team's shared, AI-ready knowledge base — people, companies, meetings, SOPs, and decisions structured so Claude can answer questions on your team's behalf. Team-scope sibling to second-brain (which is personal-scope). Seven modes — capture (drop something into the right structured dir), compile (process into wiki…