agentmods.dev

eatbook: Instructions file for Claude Code

CLAUDE.md

eatbook CLAUDE.md is an instructions file for Claude Code from SuperJJ007/eatbook. It costs 814 tokens per session, scanned A, original, MIT.

Repository instructions for Eatbook, a Chinese-language AI reading companion for studying books and research materials. They describe its shared-reading approach, project folders, and five reading-related skills.

In plain words
What is it for?
Use them to select, import, study, discuss, and research books or branch into related literature through Eatbook's reading workflow.
Why use it?
They keep reading sessions focused on thorough understanding, with visible progress, navigation, recovery of context, and fewer interruptions for the learner.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions .claude-plugin; mentions Claude Code; mentions Codex.

This is SuperJJ007/eatbook's own configuration. It tells Claude Code how to work on eatbook itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything eatbook configures →

not rated 6repo 5mo ago A scan 814 tokens original MIT
View source ↗ SuperJJ007/eatbook
Reuse

Borrowing it

Nothing to install: this file belongs to SuperJJ007/eatbook. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/SuperJJ007/eatbook/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/SuperJJ007/eatbook

Made for: Claude Code.

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 eatbook CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/superjj007/eatbook/claude-md/github.svg)](https://agentmods.dev/instructions/superjj007/eatbook/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/superjj007/eatbook/claude-md"><img src="https://agentmods.dev/badge/instructions/superjj007/eatbook/claude-md/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 eatbook CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/superjj007/eatbook/claude-md"><img src="https://agentmods.dev/badge/instructions/superjj007/eatbook/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 814 This file is loaded in full into every session.
When invoked 814 The same file — it is already loaded in full.
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 $0.00814 $0.00814
Opus 5.5 $0.00326 $0.00326
Sonnet 5.5 $0.00163 $0.00163
Haiku 4.5 $0.00081 $0.00081

Measured 2mo ago against content hash ca731040f9a1, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

eatbook CLAUDE.md 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.

CLAUDE.md · 44 lines

What it actually says

Eatbook — AI 辅助深度阅读

定位

和用户共读，以最小摩擦的彻底理解为目标。不是摘要工具，是共读伙伴。用中文沟通。 鼓励用户提问和讨论，不单方面灌输。

摩擦是人放弃学习的头号原因。"彻底理解"定义读多深，"最小摩擦"定义怎么读得下去： 每次会话进入成本趋近零（用户说"继续"就够），卡点当场拆解，进度永远可见， 记忆/导航/恢复现场全是 AI 的工程，人只负责理解本身。 摩擦观察与减摩决策记录在 docs/friction-log.md。

共创模式

Eatbook 是和用户共同建造的，AI 不只是 skill 的执行者，也是 skill 的共同设计者：

  • 观察摩擦信号：用户重复提问、中途放弃、绕过 skill 手工操作、对流程表现出不耐烦——都是信号
  • 主动提建议：在会话自然收尾处提出互动/skill 改进建议，每次 ≤2 条，不打断心流
  • 落盘闭环：建议与决策记入 docs/friction-log.md；采纳的改动回流到 skill 源和规则文件

目录导航

  • eatbook-plugin/ — 五技能插件源，经仓库自带 marketplace（.claude-plugin/marketplace.json） 以插件方式安装：claude plugin install eatbook@eatbook（user scope，全局可用）
  • books/ — 单本阅读工作区；domains/ — 领域系统学习（plugin 驱动）
  • docs/ — MinerU 手册、翻译工程经验
  • 内容层布局与防幻觉细则见 .claude/rules/

五技能索引

/eatbook:university 选书 → /eatbook:ingest 入库 → /eatbook:read 深读打底 → /eatbook:coread 共读 → /eatbook:branch 分支文献深研

独立发布 · university-skill

/eatbook:university（原 domain，已改名）抽出独立发布为单技能仓库 junjieashan/university-skill：产出升级为 notion 风格可交互档案（横向节点路线图 + 竖向主选/备选时间轴，点击跳转/阶段高亮/中轴随滚动）， 跨平台一键装 npx skills add junjieashan/university-skill（Claude Code / Codex / Cursor / 70+ agent）。 eatbook 内 eatbook-plugin/skills/university/ 与该仓库同源同模板（改动两边同步）。

本机工具链

  • PDF→MD：/pdf-ocr（MinerU，conda env mineru）；备选 docling CLI（须 CPU 模式）
  • MD 中译：/md-translate（Qwen 分块管线，断点续传）
  • 细节：docs/MinerU使用手册.md、docs/translation-lessons.md

Git 纪律

公开仓库。书籍内容（原文/译文/PDF/图片）一律不入库——.gitignore 已设红线， 提交前若 git status 出现 source/、translation.md、*.pdf 类文件，停下来检查而不是 add。

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. 2mo ago First seen · 44 lines · 814 tokens per session scan A ca731040f9a1

Subscribe to this mod's changes

eatbook CLAUDE.md is an instructions file published in the GitHub repository SuperJJ007/eatbook (6 stars, last pushed 5mo ago), licensed MIT. It adds 814 tokens to every session, about $0.0033 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 2026-08-31.

Learning and teachingResearch
Related

eatbook CLAUDE.md compared with instructions from other repositories

eatbook CLAUDE.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
eatbook CLAUDE.mdSuperJJ007/eatbookInstructions file65mo agoMITA814Claude Code
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143kyesterdayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149kyesterdayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file274k2d agoMITA4,313Codex, OpenCode