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 instructions/drpwchen/textbook-to-note/agents-mdgit clone --depth 1 https://github.com/drpwchen/textbook-to-noteWrote 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/instructions/drpwchen/textbook-to-note/agents-md)<a href="https://agentmods.dev/instructions/drpwchen/textbook-to-note/agents-md"><img src="https://agentmods.dev/badge/instructions/drpwchen/textbook-to-note/agents-md.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 | $0.04177 | $0.04177 |
| Opus 5 | $0.02089 | $0.02089 |
| Sonnet 5 | $0.00835 | $0.00835 |
| Haiku 4.5 | $0.00418 | $0.00418 |
Grade A, and why
textbook-to-note AGENTS.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 4d 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 — 342 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — Instructions for your AI coding agent
You are helping your user set up textbook-to-note: a local-first pipeline
that converts their own PDF/EPUB textbooks into searchable markdown, then
into structured, fully-cited notes in their personal knowledge vault
(Obsidian, Logseq, or a plain markdown folder). This repository is designed
to be deployed by you, an AI coding agent, working directly with the
user rather than requiring them to hand-run every script themselves.
Read this file fully before doing anything. Then work through the steps below in order, checking in with the user at the marked decision points.
What you're setting up
converter/ — PDF/EPUB → markdown conversion (0 LLM tokens)
figures/ — on-demand figure extraction with QC gating
skills/ — two Claude Code skill definitions (drop-in to ~/.claude/skills/)
workflows/ — the note-writing workflow specification
templates/ — real production note templates (zh-TW + English) for the topic-type
table in workflows/note-writing.md Step 1.1 (profiles B/C)
docs/ — architecture + OCR-ladder reference docs
examples/ — one example output note showing the target format
shared/ — shared config (paths, env var names)
requirements.txt
Read docs/architecture.md first for the full picture. Leave
docs/ocr-ladder.md alone until Step 4.5 tells you to open it — it is a
reference for a failure case most users never hit, not part of setup.
Step 1: Which profile is the user setting up?
Ask this before anything else, and do not start installing until you have an answer. The profiles stack — each is the one above it plus one more thing — and the wrong assumption here costs the user an install they never needed.
| Profile | The user wants | Steps you run |
|---|---|---|
| A · Converter only | Their books as clean, greppable markdown. grep is their whole search story. |
1.1 → 2 → 3 → 4 (→ 4.5 only if output is broken). Then stop. |
| B · A + note workflow | An AI writing structured, cited notes from that corpus, with figures. | A's steps, then 6 → 7 → 8. |
| C · B + semantic search | Cross-book retrieval by meaning, not keyword. | B's steps, plus 5. |
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.
- 4d ago First seen · 342 lines · 4,177 tokens per session scan A db4e7cd18133
textbook-to-note AGENTS.md is an instructions file published in the GitHub repository drpwchen/textbook-to-note (100 stars, last pushed 8d ago), licensed MIT. It adds 4,177 tokens to every session, about $0.0209 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 2026-08-30.
Other instructions, from other repositories
pdfmux CLAUDE.md
Instructions for NameetP/pdfmux, covering pdfmux — agent instructions, project, commands, python and site.
book-to-skill CLAUDE.md
Claude Code instructions for virgiliojr94/book-to-skill, a project described as: Turn any technical book PDF into a Claude Code skill — ready to study, reference, and use while you work.
phd-deepread-workflow CLAUDE.md
Instructions for heleninsights-dot/phd-deepread-workflow, covering claude.md, commands, install, test and code quality.
notebooklm-wiki-pipeline CLAUDE.md
Instructions for capitalparser/notebooklm-wiki-pipeline, covering 05notebooklmwikipipeline — 프로젝트 컨텍스트, 핵심 문제, 아키텍처, 도구 구성 and 슬래시 커맨드.
tablepack AGENTS.md
Instructions for kujiangmudao/tablepack, covering two user paths, multimodal requirement, environment, hard requirements (never skip) and qc checklist (every pdf).
agent-edu-reviewkit AGENTS.md
Instructions for lijiawei255/agent-edu-reviewkit, covering agent 指令, 项目概述, 主要技能, agent 平台兼容性 and opencode 适配（p1）.