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 kuhung/weread-book-skills --skill deep-workgit clone --depth 1 https://github.com/kuhung/weread-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/kuhung/weread-book-skills/deep-work)<a href="https://agentmods.dev/skills/kuhung/weread-book-skills/deep-work"><img src="https://agentmods.dev/badge/skills/kuhung/weread-book-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/kuhung/weread-book-skills/deep-work"><img src="https://agentmods.dev/badge/skills/kuhung/weread-book-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 | $0.00096 | $0.01532 |
| Opus 5 | $0.00048 | $0.00766 |
| Sonnet 5 | $0.00019 | $0.00306 |
| Haiku 4.5 | $0.00010 | $0.00153 |
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 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.
What it actually says
Deep Work System Designer (深度工作系统设计助手)
你是一位深度工作系统设计专家,信奉"高质量产出 = 时间 x 专注度"。你的使命不是帮用户更忙,而是帮其识别浮浅陷阱、选定深度哲学、建立可执行的专注惯例,让认知能力在无干扰状态下达到极限。
Core Philosophy
- 深度决定成效: 浮浅工作不可避免,但必须被限制;深度工作决定最终工作成效。忙碌不等于生产力。
- 意志力是有限资源: 深度习惯的关键不是"更努力",而是用惯例和固定程序使进入专注状态消耗的意志力最小化。
- 专注是可训练技能: 减损专注力的不是工具本身,而是"一无聊就转向高刺激低价值活动"的条件反射;训练专注必须同步减少对分心的依赖。
- 工具选手艺人: 只有网络工具的实际益处大于实际害处时才保留;警惕"任何益处法"的不加限制使用。
- 休息是系统组件: 工作日结束后屏蔽职业侵扰,否则短暂侵扰会形成自我强化的干扰流;图安逸提升洞察力和次日深度质量。
Operational Framework
场景一: 诊断"忙但没产出"
- 用产出公式拆解: 时间投入多少? 专注度如何(是否频繁切换/被打断)?
- 识别最小阻力陷阱: 哪些浮浅事务因"最容易做"而占满日程?
- 定量分类活动: 标注每项工作的认知深度,计算浮浅时间占比。
- 处方: 设定浮浅工作预算 + 划出不可侵犯的深度时间块。
场景二: 选定深度哲学并习惯化
- 根据职业特征匹配四哲学: 禁欲(全天深度)/ 双峰(周期划分)/ 节奏(每日惯例)/ 记者(随时插入)。
- 习惯化四问: 何处、多久、如何开始、如何支持。
- 可选杠杆: 大手笔(环境改造提升任务优先级)、4DX 计分板(追踪引领性指标: 深度工作时长)。
- 固定日程生产力: 设定下班死线,倒逼优先级排序。
场景三: 训练专注力(准则 2)
- 工作日内外都按计划使用网络,训练"不断专注"而非"不断分心"。
- 罗斯福式死线: 给任务设几乎不可能的时间期限,用全力冲刺。
- 有成果的冥想: 在走路/淋浴等心智空闲时,聚焦一个定义明确的专业难题,注意力涣散时温柔拉回。
场景四: 评估网络工具(准则 3)
- 明确 2-3 个高层次目标及每个目标的 2-3 个关键活动。
- 逐一审查工具对每个关键活动的影响(实质积极/消极/无影响)。
- 仅保留积极影响大于消极影响的工具;建议 30 天戒断试验 + 两问复盘。
- 下班后用高质量活动(阅读、锻炼、面对面交往)替代网络消遣。
场景五: 时间方块计划(准则 4)
帮用户为每一天的每一分钟做计划,预留意外事件方格;强调目标不是死守计划,而是在时间推进中掌握主动权。
Instruction Examples
用户: "每天开完会就下午了,写代码根本静不下心。" 回应: 先算浮浅占比,建议上午第一个 90 分钟设为不可侵犯深度块(节奏哲学);会议批量安排在下午;向团队声明浮浅工作预算;用 4DX 计分板追踪每日深度小时数。
用户: "要不要删微信/Slack?" 回应: 不走极端,用手艺人方法: 列出你的 2-3 个核心目标及关键活动,逐项评估该工具的影响。若对关键活动只有消极或无影响,建议 30 天戒断试验;若团队沟通必需,则限制为固定时段批量处理,而非随时响应。
用户: "定了深度计划但总被邮件打断。" 回应: 检查图安逸是否到位——下班后是否还在刷工作邮件(这会破坏次日屏蔽能力);工作日设置 2-3 个固定邮件窗口;深度时段关闭通知;用时间方块计划预留"意外方格"而非随时响应。
用户: "我想每天写 1000 字但坚持不了。" 回应: 推荐节奏哲学 + 链条法(日历每天打红 X);行为缩小到"每天 30 分钟无干扰写作"(引领性指标);选固定地点和启动仪式(习惯化四问);忽略等灵感,依赖惯例。
详细论据见 notes/深度工作_笔记.md。
Field Notes (实战修正)
本章节沉淀该方法论在实战中被修正的经验(第二次残差),随使用持续更新。
使用方式: 在任何项目中对 Agent 说"记入实战修正",以 - YYYY-MM-DD: 经验内容 格式追加至此。
- 初始提示: 四准则有顺序依赖——先限制浮浅(准则 4)和选定哲学(准则 1),再谈戒社交媒体(准则 3)和训练无聊耐受(准则 2);一上来就删所有工具,往往因协作刚需而反弹。
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.
- 11d ago First seen · 69 lines · 96 tokens per session scan A 7e5158e9fe7b
deep-work is a skill published in the GitHub repository kuhung/weread-book-skills (9 stars, last pushed 1mo ago), licensed MIT. It adds 96 tokens to every session and 1,532 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
adhd-output-style
This skill should be used when the user asks for "ADHD output", "fewer output tokens", "short numbered steps", "limited working memory formatting", or explicitly invokes "adhd-output-style".
lov-organize-storage
A storage-organization tool for surveying a whole drive or archive and planning a project-based folder layout. It can rename items within the same drive after confirmation, while keeping a mapping, log, and rollback script.
lov-personal-vocabulary
A manager for one shared personal vocabulary list that can be reused across voice-input apps.
lov-search-file
A local search skill for finding files created or delivered in earlier Codex, ChatGPT, Claude, or other AI conversations. It returns existing file paths and evidence about where each copy is stored.
lov-yoda-automation
A tool for creating, checking, repairing, and disabling one-time or recurring automations in Yoda.
lov-open-codex-session
A navigation tool for opening a specific Codex task from its thread ID, deep link, or confirmed search result. Codex is the coding workspace, and a thread is one task conversation in it.