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 muyuhill/100books-to-skills --skill deep-workgit clone --depth 1 https://github.com/muyuhill/100books-to-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/muyuhill/100books-to-skills/deep-work)<a href="https://agentmods.dev/skills/muyuhill/100books-to-skills/deep-work"><img src="https://agentmods.dev/badge/skills/muyuhill/100books-to-skills/deep-work/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/muyuhill/100books-to-skills/deep-work"><img src="https://agentmods.dev/badge/skills/muyuhill/100books-to-skills/deep-work.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 | $0.00055 | $0.01111 |
| Opus 5.5 | $0.00022 | $0.00444 |
| Sonnet 5.5 | $0.00011 | $0.00222 |
| Haiku 4.5 | $0.00006 | $0.00111 |
Grade A, and why
deep-work 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 2mo 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.
What it actually says
Deep Work — 在分心时代夺回专注力
深度工作：在无干扰的状态下进行专注的职业活动，将认知能力推向极限。这种努力创造新价值，提升技能，且难以复制。
Cal Newport 的核心主张：在一个越来越碎片化的世界里，能够长时间深度专注的人，是稀缺的——稀缺 = 值钱。
深度工作 vs 浮浅工作
| 深度工作 | 浮浅工作 | |
|---|---|---|
| 特征 | 无干扰、认知极限、创造新价值 | 有干扰、低认知、可替代 |
| 例子 | 写代码、写作、设计、研究 | 回邮件、开会、刷消息 |
| 价值 | 高，难以复制 | 低，容易被替代或自动化 |
| 感觉 | 难，但做完有成就感 | 轻松，但一天下来什么都没做成 |
核心洞察：你感觉自己「很忙」的那一天，通常做的全是浮浅工作。
四种深度工作哲学
| 模式 | 怎么操作 | 适合谁 |
|---|---|---|
| 禁欲模式 | 完全隔离，长时间不接触外界 | 作家、研究员 |
| 双峰模式 | 把一年/一周分成两块：深度期和浮浅期 | 有固定假期的人 |
| 节奏模式 | 每天固定时段深度工作（如 6-9 AM） | 大多数人，最实用 |
| 记者模式 | 随时随地抓住空隙进入深度 | 日程不可预测的人 |
建议从节奏模式开始：每天早上 2-3 小时，手机关机，不做任何浮浅任务。
深度工作的四条准则
准则一：深度工作（Work Deeply）
- 设定固定的深度工作时间段：不商量，不可被占用
- 创造仪式：固定地点、固定时间、固定时长
- 关门：物理上隔绝干扰
准则二：拥抱无聊（Embrace Boredom）
如果你在等红灯的 30 秒里都必须刷手机，你的大脑已经失去了「什么都不做」的能力。而这种能力是深度工作的前提。
- 排队时不刷手机——训练大脑忍受无聊
- 散步不带耳机——让大脑自由联想
- 不要「多任务」——那不是效率，那是切换成本
准则三：戒掉社交媒体（Quit Social Media）
不是「少刷」，是「为什么要刷」。
对每个社交平台问：它是我职业成功的核心工具，还是娱乐？如果是后者，删掉。你可以在 30 天实验后再决定要不要装回来。
准则四：减少浮浅工作（Drain the Shallows）
- 每天安排浮浅工作的时间上限（如 2 小时）
- 拒绝不必要的会议
- 回复邮件只在一两个时间段做——不要让邮件定义你的日程
深度工作的反直觉真相
高质量产出 = 投入时间 × 专注强度。不是时间长就产出多——是被打断的时间完全不算。
被打断一次，重新进入深度需要 15-25 分钟。一天被打断 5 次 = 损失 2 小时。
快速上手：今天就能开始
- 选一个模式：推荐节奏模式——每天早上 8-11 点为深度工作时间
- 关掉手机：物理上放在另一个房间
- 设定产出目标：不是「写代码」，是「完成功能 X」
- 记录深度工作时长：追踪数字，每天目标 2-3 小时
- 安排休息：深度工作后必须恢复——散步、小睡、运动
一句话总结
在一个分心的世界里，专注力不是天赋——是选择。每天 3 小时深度工作，远超 8 小时浮浅忙碌。
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.
- 2mo ago First seen · 96 lines · 55 tokens per session scan A 36923f0ce56b
deep-work is a skill published in the GitHub repository muyuhill/100books-to-skills (14 stars, last pushed 4mo ago), licensed MIT. It adds 55 tokens to every session and 1,111 once invoked, about $0.0002 per session on Opus 5.5. 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.
deep-work compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| deep-workmuyuhill/100books-to-skills | Skill | 14 | 4mo ago | MIT | A | 55 | Claude Code, Codex |
| orbit-notionnexu-io/open-design | Skill | 106k | yesterday | Apache-2.0 | A | 117 | Claude Code, Codex |
| agentmailpaperclipai/paperclip | Skill | 111k | yesterday | MIT | A | 30 | Claude Code, Codex |
| Cortexdanielmiessler/LifeOS | Skill | 20k | yesterday | MIT | A | 184 | Claude Code |
| rowboat-spacesrowboatlabs/rowboat | Skill | 18k | yesterday | Apache-2.0 | A | 60 | Claude Code, Codex |
| feishuHmbown/CodeWhale | Skill | 41k | 6d ago | MIT | A | 33 | Claude Code, Codex |
| pinchtab-mcppinchtab/pinchtab | Skill | 11k | 10d ago | MIT | A | 52 | Claude Code, Codex |