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 agentmods add skills/superjj007/eatbook/readnpx skills add SuperJJ007/eatbook --skill readgit clone --depth 1 https://github.com/SuperJJ007/eatbookWrote 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/superjj007/eatbook/read)<a href="https://agentmods.dev/skills/superjj007/eatbook/read"><img src="https://agentmods.dev/badge/skills/superjj007/eatbook/read.svg" alt="Measured on agentmods" 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 | $0.00114 | $0.01238 |
| Opus 5 | $0.00057 | $0.00619 |
| Sonnet 5 | $0.00023 | $0.00248 |
| Haiku 4.5 | $0.00011 | $0.00124 |
Grade A, and why
read 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 5d 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 — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/eatbook:read — 深读打底
铁律先行：本 skill 的一切产出必须服从 references/grounding.md 防幻觉协议。 开始前先读它；给子 agent 派活时必须把该文件路径写进 prompt。
前置检查
- 定位书目录
domains/<领域>/books/<书slug>/，确认存在source/full.md和notes/_toc.json - 读
_toc.json播报章节规模（章数、各章行数） - 若部分章节笔记已存在：播报进度，从缺口继续（断点续读）
阶段 1：逐章精读
对 _toc.json 的每一章：
- 全文必读：按
start_line/end_line用 Read 读取全章。超过 1500 行的章分多次连续 Read，不允许跳读、不允许只读开头 - 写章节笔记
notes/chNN.md：复制 templates/chapter-note.md 结构填写；每条事实/概念/理论带锚点【chN L起-止】"≤25字原文引文" - 抽取图谱
graph/staging/<书slug>-chNN.json：按 references/kg-schema.md 抽取实体/关系（只抽本章核心，跳过路过式提及）
并行加速：章节相互独立，可每章派一个子 agent（Agent 工具）。子 agent prompt 必须包含：
- 书目录绝对路径 + 该章行号范围
- grounding.md、kg-schema.md、chapter-note.md 三个文件的绝对路径，并要求先读
- 要求返回：笔记文件路径 + staging JSON 路径 + 自检声明（"全章 N 行已完整读取"）
章数多时建议分批（每批 4-6 章），每批完成后抽查再继续。
阶段 2：验证 pass（不可省略）
派独立子 agent（不能是写笔记的那个）执行：
- 从每章笔记抽样 ≥15% 条目 + 全部
[争议]条目 - 对每条：用 Grep 在
source/full.md对应行号附近搜索引文（允许 OCR 噪声的近似匹配，见 grounding.md §验证） - 产出
notes/_verify-chNN.md：每条 PASS/FAIL + FAIL 原因 - 任何 FAIL → 对应章节打回重读修正，再验证，直到通过
阶段 3：综合
只允许从章节笔记综合，禁止回模型记忆取材（发现笔记覆盖不足就回阶段 1 补读）。
- 单书导读
guide.md：按 templates/book-guide.md。蓝本质量标杆是books/playing-with-reality/guide.md（逐章核心论点+论证路径+部级弧线） - 图谱合并：
对 dupes 输出逐对判断（依据 description，参考 kg-schema.md §去重），把确认的合并写入python3 ${CLAUDE_SKILL_DIR}/scripts/graph_tools.py merge <领域目录> # staging → entities/relations.json python3 ${CLAUDE_SKILL_DIR}/scripts/graph_tools.py dupes <领域目录> # 输出疑似重复实体graph/aliases.json，重跑 merge。最后：python3 ${CLAUDE_SKILL_DIR}/scripts/graph_tools.py validate <领域目录> # 悬空边/枚举校验，必须零报错 python3 ${CLAUDE_SKILL_DIR}/scripts/graph_tools.py mermaid <领域目录> # 重建 roadmap.md - 领域级文档增量更新：
overview.md（分层式：1 页全域地图 + 每分支 1-2 页——核心问题/基本事实/主要理论/未解之谜）facts.md（新事实并入；多书一致的升级为[共识]，书间矛盾的标[争议]并列双方+各自锚点）
- 更新
00-domain.md进度表："深读打底 ☑"
What ships with it
5 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.
- 5d ago First seen · 68 lines · 114 tokens per session scan A 6348a625c8d1
read is a skill published in the GitHub repository SuperJJ007/eatbook (4 stars, last pushed 3mo ago), licensed MIT. It adds 114 tokens to every session and 1,238 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.
Other skills, from other repositories
hr-onboarding
A new-hire onboarding plan as a single page — first week schedule, buddy + manager intro, learning track, equipment checklist, and "you're set when…" outcomes. Use when the brief mentions "onboarding", "new hire", "first week plan", or "入职".
book-mirror
Take any book (EPUB/PDF), produce a personalized chapter-by-chapter analysis. Each chapter is preserved in detail (The Chapter) and mirrored back to the reader's actual life (The Mirror) using brain context. The mirror observes and resonates — a friend pointing out parallels, NOT a consultant rearranging the reader's…
miniapp
Build a tiny interactive HTML playground only when someone asks to see, play with, or step through a mechanism.
eli5
Explain research, papers, or technical ideas in plain English with minimal jargon, concrete analogies, and clear takeaways. Use when the user says "ELI5 this", asks for a simple explanation of a paper or research result, wants jargon removed, or asks what something technically dense actually means.
deck-course-module
暖纸背景 + Playfair, 左侧学习目标常驻, 含 MCQ 自测页.
best-practices
Searchable knowledge base of 152+ programming best practices across 30+ languages and frameworks. BM25-powered search over curated resources from industry leaders (Google, Airbnb, Uber, Mozilla, Shopify, OWASP).