agentmods.dev

20分钟启动法

20分钟启动法 is a skill for Claude Code, Codex from R2h1/my-book-skills. It costs 113 tokens per session (1,719 once invoked), scanned A, original, MIT.

A Chinese-language method for overcoming procrastination by starting a task with a focused 20-minute timer. The goal is to begin, not necessarily to finish.

In plain words
What is it for?
Use it when someone has postponed a blog, video, business idea, website, or other new project and needs a concrete first step.
Why use it?
Large or uncertain tasks can feel difficult to start. A short, fixed session lowers the initial effort and helps replace waiting for perfect preparation with immediate action.

Skill for Claude CodeCodex

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

not rated 2repo 27d ago A scan 113 tokens original MIT

Good fit Use it when someone has postponed a blog, video, business idea, website, or other new project and needs a concrete first step.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/r2h1/my-book-skills/v10-20
View source ↗ R2h1/my-book-skills
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 R2h1/my-book-skills --skill v10-20
Clone the repo
git clone --depth 1 https://github.com/R2h1/my-book-skills

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 20分钟启动法

README.md
[![agentmods](https://agentmods.dev/badge/skills/r2h1/my-book-skills/v10-20/github.svg)](https://agentmods.dev/skills/r2h1/my-book-skills/v10-20)
Your own site
<a href="https://agentmods.dev/skills/r2h1/my-book-skills/v10-20"><img src="https://agentmods.dev/badge/skills/r2h1/my-book-skills/v10-20/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 20分钟启动法

Your own site · 80×15
<a href="https://agentmods.dev/skills/r2h1/my-book-skills/v10-20"><img src="https://agentmods.dev/badge/skills/r2h1/my-book-skills/v10-20.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 113 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,719 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 $0.00113 $0.01719
Opus 5 $0.00056 $0.00860
Sonnet 5 $0.00023 $0.00344
Haiku 4.5 $0.00011 $0.00172

Measured 12d ago against content hash 9b4323449e81, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

20分钟启动法 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.

30岁人生开挂7步法/v10-20分钟启动法/SKILL.md · 140 lines

How it starts

The opening of the file, as written. The whole thing — 140 lines — stays where its author put it; the contents beside it link to each section on GitHub.

20分钟启动法

R — 原文

"100个人中有99个人是只有在受到金钱的诱惑,或者是受到别人的监视和惩罚的时候才去做事。因为很少有人愿意主动做某事,所以,谁的执行力强,谁就很容易在人生这场游戏中获得财富自由。"

— 金承焕, 第六章

I — 方法论骨架

20分钟启动法是最低门槛的执行力框架,核心思想是'万事开头难,先让车轮转动':

  1. 不要求完成,只要求开始 — 人类本能抗拒'完成一件事'(太累太耗时),但对'做20分钟'的抵触小得多
  2. 20分钟是魔数 — 足够短到让人愿意开始,又足够长到进入状态。一旦开始,惯性和'不想中断'的心理会推动继续
  3. 接受'99%的人不会行动' — 执行力低下不是缺陷而是正常人类状态(Kluge导致)。不为此自责,而是用方法绕过
  4. 计时器是关键道具 — 精确的20分钟倒计时制造紧迫感,防止大脑'我先休息一下'的拖延

核心思维转换: 从'我要完成这件事'转向'我先做20分钟,20分钟后允许停下'

A1 — 书中的应用

案例 1: 作者建议创建博客

  • 问题: 很多人想写博客但从未开始
  • 方法论的使用: '打开计时器,精准倒计时20分钟,随便写一篇文章'
  • 结论: 不是'写一篇好文章',而是'写20分钟'
  • 结果: 作者断言'如果你做到了,你的生活会发生很大的变化'

案例 2: 作者启动YouTube

  • 问题: 犹豫6个月做YouTube
  • 方法论的使用: 不是等'准备好设备''学习了剪辑''有脚本了',而是先上传第一个视频
  • 结论: 先发射再瞄准,而不是先瞄准再发射

案例 3: 无资本创业的第一步

  • 问题: 大多数人想创业但从未开始
  • 方法论的使用: 先建一个网站/服务页面/LOGO设计模板,用20分钟做出第一个版本
  • 结论: 第一版不需要完美,甚至不需要好

A2 — 触发场景

用户会在什么情境下需要这个 skill?

  1. 用户说'想做XX已经好几个月了但一直没开始'
  2. 用户说自己'没有时间'做新尝试
  3. 用户对新想法犹豫不决,找各种准备理由

语言信号

  • '我还没准备好'
  • '等我有时间了再……'
  • '我想先学习一下……'
  • '这个需要XX设备/条件'

与相邻 skill 的区分

  • 与Kluge识别与对抗法的关系: 20分钟启动法是Kluge对抗的具体执行手段——当Kluge说'别多事了'时,打开计时器做20分钟
  • 与周日2小时战略的区别: 20分钟启动法用于突破'开始'的心理门槛,周日2小时用于每周固定时间做新尝试

E — 可执行步骤

当 skill 被激活后,agent 应按以下步骤执行:

  1. 选择一件事

    • 让用户从一直拖延的事情中选一件最小的
    • 标准:这件事20分钟内一定可以开始(不是完成)
    • 完成标准: 用户确定了一件具体的事

  2. 打开计时器

    • 要求用户现在(或约定一个具体时间)打开计时器设置20分钟
    • 建议使用手机计时器而非心理计时
    • 完成标准: 计时器正在倒计时
    • 判停条件: 如果用户说'等一会儿',追问具体时间并约定提醒

  3. 开始并允许停下

    • 明确告知:'20分钟后允许你停下来,不强求继续'
    • 完成后询问感受——大多数人会发现自己做了不止20分钟
    • 完成标准: 用户完成了20分钟,并反馈结果

B — 边界

不要在以下情况使用此 skill

  • 用户需要的是专业指导而非启动动力(如'如何做心脏手术'——20分钟启动法不适用)
  • 任务确实需要大量准备时间时(如出差前需要规划路线)
  • 用户已经行动过度(工作狂)——需要的是停下而非启动

作者在书中警告的失败模式

  • 作者反复强调'100人中有99人不行动'——你不需要做得比99人好,只需要比他们先做
  • ce08: Kluge回避新挑战——'别多事了'——20分钟启动法是直接对抗

作者的盲点 / 时代局限

  • 对部分患有ADHD或严重拖延症的人,'开始20分钟'可能仍然过高(可能需要'开始30秒')
  • 20分钟法对'创意性工作'(写作/设计)有效,对'准备工作复杂'的任务(如装修)效果有限
  • 作者假设'开始了就会继续',实际上有些人确实会在20分钟整停下来

容易混淆的邻近方法论

  • 番茄工作法(Pomodoro 25分钟)——形式上类似,但番茄法的目的是'保持专注'',20分钟启动法的目的是'突破开始门槛'
  • '先发射再瞄准'(Ready, Fire, Aim)——20分钟启动法是这个想法的具体实施工具

Read the full file on GitHub · 140 lines

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. 12d ago First seen · 140 lines · 113 tokens per session scan A 9b4323449e81

Subscribe to this mod's changes

20分钟启动法 is a skill published in the GitHub repository R2h1/my-book-skills (2 stars, last pushed 27d ago), licensed MIT. It adds 113 tokens to every session and 1,719 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 2026-08-31.

Claude CodeProductivityai-agentbookschineseclaude-skillsknowledge-distillation公众号
Related

Other skills, from other repositories

accint-commitments

Triage acc's open promises and close them with honest real-world verdicts via accact(runtime="outcome").

lingxling/awesome-skills-cn · 29 tokens

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 …

f-tiger/zaoqi-blueprints · 207 tokens

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.

f-tiger/zaoqi-blueprints · 166 tokens

screen-detox

A habit-change framework for reducing non-work screen use such as social media, short videos, games, and endless scrolling.

kangarooking/cangjie-skill · 148 tokens

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.

kangarooking/cangjie-skill · 158 tokens

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…

coreyhaines31/makerskills · 322 tokens