fan-xing-fu-pan

fan-xing-fu-pan is a skill for Claude Code, Codex from ace3000chao/book2startup. It costs 164 tokens per session (2,427 once invoked), scanned A, original, MIT.

A seven-day self-review method based on the “Returning” theme of the I Ching, an ancient Chinese book of advice and reflection. It helps people notice when they are drifting and correct course early.

In plain words
What is it for?
Use it after a project setback, during weekly reflection, after a poor decision, or when repeated procrastination needs correction.
Why use it?
It provides a structured way to learn from setbacks without rushing to blame or waiting until a small problem becomes serious.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it after a project setback, during weekly reflection, after a poor decision, or when repeated procrastination needs correction.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/ace3000chao/book2startup/fan-xing-fu-pan
Install

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.

Any agent
npx skills add ace3000chao/book2startup --skill fan-xing-fu-pan
Clone the repo
git clone --depth 1 https://github.com/ace3000chao/book2startup

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for fan-xing-fu-pan

README.md
[![agentmods](https://agentmods.dev/badge/skills/ace3000chao/book2startup/fan-xing-fu-pan/github.svg)](https://agentmods.dev/skills/ace3000chao/book2startup/fan-xing-fu-pan)
Your own site
<a href="https://agentmods.dev/skills/ace3000chao/book2startup/fan-xing-fu-pan"><img src="https://agentmods.dev/badge/skills/ace3000chao/book2startup/fan-xing-fu-pan/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.

agentmods 80×15 button for fan-xing-fu-pan

Your own site · 80×15
<a href="https://agentmods.dev/skills/ace3000chao/book2startup/fan-xing-fu-pan"><img src="https://agentmods.dev/badge/skills/ace3000chao/book2startup/fan-xing-fu-pan.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 164 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,427 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00164 $0.02427
Opus 5 $0.00082 $0.01213
Sonnet 5 $0.00033 $0.00485
Haiku 4.5 $0.00016 $0.00243

Measured 11d ago against content hash 355ee50926bd, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

fan-xing-fu-pan 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 11d 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.

易经skills/fan-xing-fu-pan/SKILL.md · 132 lines

How it starts

The opening of the file, as written. The whole thing — 132 lines — stays where its author put it; the contents beside it link to each section on GitHub.

反省复盘法

R — 原文 (Reading)

"复,亨。出入无疾,朋来无咎。反复其道,七日来复,利有攸往。" "不远复,无祗悔,元吉。"

— 《易经》复卦


I — 方法论骨架 (Interpretation)

复卦的核心是"一阳复始"——剥尽纯阴之后,一阳重新生起,象征事物在衰落后重新恢复生机的过程。

"七日来复"不是机械的7天周期,而是强调:在合理的时间窗口内完成纠偏。时间太短则来不及沉淀教训,太长则问题累积成势。7天是一个经验值,核心是"不远复"——在偏离轨道不远时就能觉察并纠正,而非等到大错已铸才来后悔。

应用于创业决策:项目遇到挫折时,不应拖延复盘,也不应仓促下结论。关键是区分"假失败"(方向对但执行有偏差)与"真迷失"(方向根本错误需重新定位)。复盘的价值不在于追究责任,而在于提炼可操作的改进路径,让下一次决策质量更高。


A1 — 书中的应用 (Past Application)

案例1: 周公摄政后的反思

  • 问题: 周公辅政七年,平定管蔡之乱、营建东都,政治成就斐然。然而作为臣子摄政,始终面临"功高震主"的道德质疑与政治风险。
  • 方法论的使用: 周公以复卦"不远复"自省——趁自己尚在权力巅峰、尚未引发君主猜忌之前,主动提出归政成王。他没有等危机爆发才撤退,而是在风险尚远时就主动收敛。
  • 结论: 功成身退、以退为进,是"不远复"的最高体现——在问题尚无端倪时主动纠偏,而非等到灾难临头。
  • 结果: 周公得以善终,其治国理念延续,成王康王之治奠定周朝八百年基业。

案例2: 文王被囚羑里的七年

  • 问题: 周文王被殷纣王囚禁于羑里,长达七年之久,事业发展遭受毁灭性打击。
  • 方法论的使用: 文王在狱中并没有做无谓的正面冲突,而是借此时机推演伏羲八卦为六十四卦,完成《易经》的核心构建——将危机转化为深化的契机。
  • 结论: 逆境中的复盘不是否定自己,而是重新校准方向、深化认知。"复"之"亨"在于:真正通达的复盘能让你比被困前更强大。
  • 结果: 文王出狱后,方向更清晰、人心更凝聚,最终完成灭商大业。

A2 — 触发场景 (Future Trigger) ★

用户会在什么情境下需要这个 skill?

  1. 项目阶段性受挫后:融资失败、产品上线反响不如预期、核心成员离职、关键合作破裂——需要系统复盘而非简单归因。
  2. 每周例行反思:希望建立稳定复盘习惯,在"无问题"时也定期检视方向是否偏移,而非等到出了大事才来救火。
  3. 决策失误后的思路重梳:发现自己某次决策明显有问题,需要冷静分析"哪里出了错、以后怎么改",而不是陷入自我否定或推卸责任。
  4. 习惯性拖延/回避问题者:总是推迟面对问题,积小成大,需要用结构化复盘强迫自己直面现实。

语言信号

  • "复盘一下"
  • "这事哪里出了问题"
  • "我需要反思一下"
  • "总结一下经验教训"
  • "这个决策是不是错了"
  • "现在回过头看……"

与相邻 skill 的区分

  • 与**积不善之余殃(ce04)**的区别: ce04强调持续作恶的累积后果,属预防性警示;本skill是事后的系统复盘与纠偏,ce04是"不要开始",本skill是"开始了就要检视"。
  • 与**守成戒贪法(f10)**的区别: f10强调守成期的节制;本skill强调复盘后的行动修正,不限于守成或进取阶段。

E — 可执行步骤 (Execution)

  1. 设立复盘锚点

    • 完成标准: 确定复盘的时间窗口(事件发生后24-72小时内启动,不超过7天);明确复盘是"为下次更好"而非"追究责任"
    • 判停条件: 若处于极度情绪化状态(愤怒、沮丧),先做5分钟深呼吸,必要时推迟到次日
  2. 还原事实层(剥去叙事)

    • 完成标准: 用3-5句话客观描述发生了什么,不含形容词和判断词;列出涉及的关键决策点、时间线和结果
    • 判停条件: 若事实还原过程中持续自我辩护("但是……"),记录情绪后强制切换到下一步
  3. 区分"假失败"与"真迷失"

    • 完成标准: 写下"如果重来一次,我会做哪1-2件事不同"(执行层面的改进);再写下"这件事暴露了我对什么判断有误"(认知层面的修正)
    • 判停条件: 若是"真迷失"(方向性错误),将问题升级,触发更大范围的方向重检
  4. 提炼可执行的动作

    • 完成标准: 产出一份"下次遇到同类情况,我这么做"的简短清单(3条以内),记录到可检索的位置
    • 判停条件: 若提炼不出可执行动作,说明复盘深度不足,返回第2步重新还原

Read the full file on GitHub · 132 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

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.

  1. 11d ago First seen · 132 lines · 164 tokens per session scan A 355ee50926bd

Subscribe to this mod's changes

fan-xing-fu-pan is a skill published in the GitHub repository ace3000chao/book2startup (80 stars, last pushed 4mo ago), licensed MIT. It adds 164 tokens to every session and 2,427 once invoked, about $0.0008 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.