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 unix2dos/skills --skill book-dissectgit clone --depth 1 https://github.com/unix2dos/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/unix2dos/skills/book-dissect)<a href="https://agentmods.dev/skills/unix2dos/skills/book-dissect"><img src="https://agentmods.dev/badge/skills/unix2dos/skills/book-dissect/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/unix2dos/skills/book-dissect"><img src="https://agentmods.dev/badge/skills/unix2dos/skills/book-dissect.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 | $0.00043 | $0.02068 |
| Opus 5 | $0.00022 | $0.01034 |
| Sonnet 5 | $0.00009 | $0.00414 |
| Haiku 4.5 | $0.00004 | $0.00207 |
Grade A, and why
book-dissect 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 9d 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 — 135 lines — stays where its author put it; the contents beside it link to each section on GitHub.
book-dissect
一句话定位
给一个书名，先联网核实，再产出一份 80% 深度讲解 + 20% 价值鉴定 的拆书报告：把书"讲了什么、每段在表达什么"逐段拆透，最后给出读不读、收获什么、思想是什么。
核心反面：绝不能只给一段笼统概述。讲解部分必须逐幕/逐论点深走，每个单元都有自己的篇幅下限（见"深度下限"）。
工作流程
按顺序执行，每步都有完成判据，判据不达成不进下一步。
- 接收书名（含作者更好，歧义书名要先确认是哪一本/哪个版本）。
- 联网搜索核实：每本书都先搜，不靠记忆裸写。至少核实：作者与成书年代、真实情节/论证主线、关键人物或案例、主流评价。
- 完成判据：拿到足以支撑逐段拆解的事实；冷门书若搜不到可靠信息，明确声明信息有限，不编造情节。
- 判断书的类型（见"类型判断"），选定骨架 A（叙事）或骨架 B（论说）。
- 按骨架写报告：先写满 80% 讲解，再写 20% 鉴定。写完逐条过"红旗自检"+"量化自检"，不过就改。
- 保存并告知路径（见"输出保存"）。
类型判断
| 信号 | 归类 | 用骨架 |
|---|---|---|
| 小说、传记、剧本、神话、叙事性历史——有人物和情节线 | 叙事类 | A |
| 社科、科普、哲学、商业、自助、思想随笔——有论点和论证 | 论说类 | B |
混合书（如叙事体裁但重在传达思想）按主导成分归类，并在报告头一句话说明为何这么归。
骨架 A：叙事/小说类
报告头（必写）：一句话故事 + 体裁/作者/年代 + 信息来源与置信度（搜到了什么、是否可靠）。
讲解 80%：
- 一、整体故事线：完整故事弧，含结局（默认全剧透，报告头提示一句"含剧透"即可）。
- 二、逐幕剧情深走 ← 主体，最吃篇幅。按书的真实结构分段（开端 / 发展 / 转折 / 高潮 / 结局，或书自带的卷/部）。每一段都必须含三个 REQUIRED 槽位：
发生了什么：这一段的剧情。为何重要：它在整体结构里的作用（铺垫/反转/命运齿轮）。想表达什么：作者借此传达的主题、隐喻或意图。
- 三、关键人物解读：每个核心人物给
角色定位+人物弧光/转变+象征意义。 - 四、核心主题与母题：全书反复叩问的母题，想表达的思想是什么。
骨架 B：论说/非虚构类
报告头（必写）：一句话核心思想 + 本书要解决的核心问题 + 信息来源与置信度。
讲解 80%：
- 一、核心论点清单：3–6 条，每条一句话概括一个关键思想。
- 二、思想蓝图：逐论点深走 ← 主体，最吃篇幅。按核心章节/论点模块拆，每个模块必须含三个 REQUIRED 槽位：
思想解码：这个论点/理论/模型本身。关键例证：书中支撑它的最关键例子、数据或论证。它解决什么：这个论点的含义与适用边界。
- 三、关键人物/案例解读：理论提出者、关键案例主角等，给
角色定位+核心贡献/故事。 - 四、思想脉络小结：上述论点如何串成一个体系。
20% 鉴定（两类骨架共用，接在讲解之后）
- 五、阅读决策评级：必读 🌟🌟🌟🌟🌟 / 建议读 👍👍👍👍 / 快速翻阅 🏃 / 无需阅读 ❌；分别说明对哪类读者有价值、谁可以跳过。
- 六、作品评价：大师/专家眼中的赞誉与批评 + 普通读者的共鸣与吐槽 + 1–2 个经典"名场面" + 1 个被低估的"宝藏"观点 + 常见误读澄清 + 1–2 个最有力的反方观点。
- 七、思想坐标：作者速写与时代问题意识 + 扩展书单（源头之作 / 同侪参照 / 进阶批判，各 1 本，写清与本书的关系）。
- 八、收获与知行合一：一句话核心思想 + 1–2 个可立即执行的行动/思维练习 + 一句最终反思（"如果当时你已懂本书的 X，会有何不同"）。
- 可复用工具箱（并入八或单列）：关键术语词典（2–4 条）+ 高光金句（1–2 句，附解读与使用场景）。
深度下限（防"太简略"的硬约束）
| 约束 | 下限 |
|---|---|
| 讲解部分占全报告 | ≥ 70%（目标 80%） |
| 叙事类：逐幕段落 | ≥ 4 段，每段 ≥ 150 字，三槽位齐全 |
| 论说类：核心模块 | ≥ 3 个，每个 ≥ 200 字，三槽位齐全 |
| 全报告总量 | 2500–4500 字（书极简单可放宽下限，但不能只剩概述） |
What ships with it
2 files 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.
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.
- 9d ago First seen · 135 lines · 43 tokens per session scan A cf64097f29c9
book-dissect is a skill published in the GitHub repository unix2dos/skills (5 stars, last pushed yesterday), licensed MIT. It adds 43 tokens to every session and 2,068 once invoked, about $0.0002 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
81-pipecat
Create your Pipecat skill from official documentation, then learn to improve it throughout the chapter.
34-openai-agents-sdk-panaversity-agentfactory-8f59f147
Create your OpenAI Agents SDK skill in one prompt, then learn to improve it throughout the chapter.
35-google-adk-reliable-agents
Create your Google Agent Development Kit skill in one prompt, then learn to improve it throughout the chapter.
36-anthropic-agents-kit-development
Create your Claude Agent SDK skill in one prompt, then learn to improve it throughout the chapter.
academy-guide
Stop and check this skill before finishing any reply to a question about how to use Claude or a Claude product — it recommends matching courses, tutorials, and use cases from Claude Academy (academy.claude.com), Anthropic's learning hub. Trigger on: "how do I", "how can I", "getting started with", "what can Claude…
quiz-me
Verify understanding after implementation with targeted quizzes.