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 coreyhaines31/makerskills --skill read-bookgit clone --depth 1 https://github.com/coreyhaines31/makerskillsWrote 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/coreyhaines31/makerskills/read-book)<a href="https://agentmods.dev/skills/coreyhaines31/makerskills/read-book"><img src="https://agentmods.dev/badge/skills/coreyhaines31/makerskills/read-book/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/coreyhaines31/makerskills/read-book"><img src="https://agentmods.dev/badge/skills/coreyhaines31/makerskills/read-book.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00192 | $0.02297 |
| Opus 5 | $0.00096 | $0.01149 |
| Sonnet 5 | $0.00038 | $0.00459 |
| Haiku 4.5 | $0.00019 | $0.00230 |
Grade A, and why
read-book 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 — 174 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/read-book — Extract structured notes from books and long PDFs
Sibling to watch-video. Same content-consumption pattern: ingest → chunk → extract → optionally capture to second-brain.
Step 1 — Parse input
Accept:
- PDF: file path (Claude reads PDFs natively in chunks via
Read pages:"X-Y") - EPUB / MOBI: file path (needs
pandocorebook-convertto extract — seereferences/sources.md) - Markdown / .txt: file path (read directly)
- Pasted text: just use what was pasted
- URL to public-domain text:
WebFetch(Project Gutenberg, archive.org, etc.)
Detect type from file extension. If ambiguous, ask.
Step 2 — Parse mode
| Invocation | Mode | What you get |
|---|---|---|
/read-book <input> |
notes (default) | Chapter-by-chapter: TL;DR + key concepts + quotes + action items + frameworks |
/read-book <input> summary |
summary | Whole-book TL;DR (1 paragraph) + 3–5 key takeaways + who-it's-for |
/read-book <input> quotes |
quotes | Pull-quote highlights only, with chapter context and page refs |
/read-book <input> study |
study | Notes mode + 10–20 spaced-repetition Q&A cards |
If the book is long (>200 pages) and mode is unspecified, default to notes but warn it'll take many tool calls.
Step 3 — Get the text + chunk
See references/sources.md for per-source ingestion. Output of this step: text content + a chunking plan.
Chunking strategy (hybrid, in priority order):
-
By chapter if a TOC exists (PDF with bookmarks, EPUB/MOBI converted via pandoc preserves chapter headers)
- Use
pdfinfo <pdf> | grep "Pages"for PDFs - Use
pdftotext -layout <pdf> | grep -i "^chapter\|^part"for chapter detection, or read TOC from page 1–5 - EPUB: after
pandoc <epub> -o tmp.md, chunks are between# Chapter Xheaders
- Use
-
By page count for PDFs without TOC: 50 pages per chunk
-
By character count for text/markdown: 30,000 chars per chunk (~7,500 words)
Save the chunking plan as ~/Documents/books/<author>-<title-slug>-<YYYY-MM-DD>/chunks.json:
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 · 174 lines · 192 tokens per session scan A 08f64c723264
read-book is a skill published in the GitHub repository coreyhaines31/makerskills (795 stars, last pushed 4d ago), licensed MIT. It adds 192 tokens to every session and 2,297 once invoked, about $0.0010 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 skills, from other repositories
document-classification-nlp
Automatically classify and extract information from construction documents using NLP. Categorize RFIs, submittals, change orders, specifications, and contracts.
google-apps-script
Build Google Apps Script automation for Sheets and Workspace. Custom menus, triggers (onEdit / time-driven / form submit), dialogs, sidebars, email batches, PDF export, external API. Use whenever the user wants to automate a Google Sheet, build a Sheets menu / sidebar / dialog, hit a Sheets row from email or a…
compression
Cuts a draft to a target word count without losing substance. Two modes behind one skill. target-count hits a specific number (200 for a cold email, 500 for an op-ed, 6 for a product summary). redundancy catches the specific failure where a phrase says what the verb or context already implied — "going forward" after a…
signature-request
Pre-signature gate and routing plan for a finalized document — verifies exact legal entity names, signatory authority, attached exhibits, filled blanks, consistent dates, and counterparty details, then sets the signing order (sequential vs. parallel, with reasons), writes envelope instructions for any e-sign tool, and…
tax-prep
Organizes tax season — an organizer, not tax advice: a document checklist by category (income, expenses, assets, payroll, prior filings), an expense-category sweep that flags plausibly missed deductions in generic jurisdiction-agnostic categories, a quarterly-estimate calendar template, a clean handoff pack for the…
voice-builder
Ingests 5–20 of the user's writing samples and distils a reusable voice-profile.md — signature phrases, sentence-length distribution, opener/closer habits, punctuation quirks, vocabulary do/don't lists, tone sliders, and three calibration paragraphs with self-checks. Other skills load this file so every post sounds…