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/claude-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/claude-md)<a href="https://agentmods.dev/instructions/drpwchen/textbook-to-note/claude-md"><img src="https://agentmods.dev/badge/instructions/drpwchen/textbook-to-note/claude-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 5.1 | $0.00943 | $0.00943 |
| Opus 5 | $0.00472 | $0.00472 |
| Sonnet 5 | $0.00189 | $0.00189 |
| Haiku 4.5 | $0.00094 | $0.00094 |
Grade A, and why
textbook-to-note 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 6d 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 — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md — which audience are you?
This repo has two kinds of AI reader, and they need different files.
You are setting this tool up for a user (they said "read AGENTS.md and set this up") →
read AGENTS.md. Nothing on this page applies to you.
You are changing this repo (fixing a bug, adding a behaviour, cutting a release) → read
openspec/README.md first, then continue here.
Working on this repo
Spec before code
openspec/specs/ states what this tool does. When a request changes that:
- Write the delta spec first —
openspec/changes/<name>/(copyopenspec/changes/TEMPLATE). - Get the maintainer's line-by-line approval on it.
- Then implement.
When the requirement shifts mid-implementation, go back and change the delta spec before touching code again. A spec that gets updated after the fact is a changelog, and the whole point is to have the argument before the code exists rather than after.
openspec/specs/ itself is edited only by the archive step, never to describe work you are
about to do.
How much ceremony — decide before you start
Not every change earns a full spec cycle. The test: if the agent misread the requirement, does one follow-up prompt fix it?
- Yes → Tier 0. No spec. Commit with
[no-spec]. Tests still have to be green. - No, but the scope is unambiguous → Tier 1. Half a page of delta spec, written as acceptance criteria (Given-When-Then, observable Then, thresholds as literal numbers).
- Anything on the list below → Tier 2. Full cycle (proposal + delta + tasks), line-by-line maintainer approval, and one independent verifier pass after the implementation is done.
Tier 2 in this repo:
- OCR routing — what sends a PDF down the Surya path, the silent-
fitz-failure detection,--force-surya. It only exists in the--batch-dirpath, and getting it wrong costs a user a multi-GB install and hours of runtime. - Table gating — every
T2N_TABLE_*constant,figures/figure_qc_gate.py,figures/pregate.py, and the review-queue flagging. A gate that is too loose ships a misbound dose as clean citable data. - Release discipline — anything that changes what a released tag contains, or the
CHANGELOG+ tag flow itself.
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.
- 6d ago First seen · 81 lines · 943 tokens per session scan A ecc9f5d2f6bb
textbook-to-note CLAUDE.md is an instructions file published in the GitHub repository drpwchen/textbook-to-note (100 stars, last pushed 10d ago), licensed MIT. It adds 943 tokens to every session, about $0.0047 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
obsidian-mcp-server AGENTS.md
AGENTS.md instructions for cyanheads/obsidian-mcp-server, covering agent protocol, what's next?, core rules, patterns and tool — obsidianlisttags.
obsidian-llm-wiki AGENTS.md
AGENTS.md instructions for green-dalii/obsidian-llm-wiki, covering llm wiki plugin project development standards, 🛡️ six-gate quality closure, gate 1: five-gate automated, gate 2: no side effects and gate 3: no breaking changes.
obsidian-llm-wiki CLAUDE.md
Claude Code instructions for green-dalii/obsidian-llm-wiki, a project described as: Karpathy's LLM Wiki implementation plugin for Obsidian - turns notes and PDFs into a linked, LLM-powered knowledge base with entity pages, concept pages, graph-powered Q&A, and local-first privacy.
pdfmux CLAUDE.md
Claude Code instructions for NameetP/pdfmux, covering pdfmux — agent instructions, project, commands, python and site.
obsidian-transcriber AGENTS.md
Instructions for dsebastien/obsidian-transcriber, covering project documentation, documentation surfaces, project overview, agent workflow and session-start checklist.
hippocampus CLAUDE.md
Instructions for sturlese/hippocampus, covering layout, frontmatter schema, conventions, answering questions from the vault (read order) and contradictions.