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 LandonSchropp/agent-toolkit --skill summarize-bookgit clone --depth 1 https://github.com/LandonSchropp/agent-toolkitWrote 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/landonschropp/agent-toolkit/summarize-book)<a href="https://agentmods.dev/skills/landonschropp/agent-toolkit/summarize-book"><img src="https://agentmods.dev/badge/skills/landonschropp/agent-toolkit/summarize-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/landonschropp/agent-toolkit/summarize-book"><img src="https://agentmods.dev/badge/skills/landonschropp/agent-toolkit/summarize-book.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00035 | $0.00609 |
| Opus 5.5 | $0.00014 | $0.00244 |
| Sonnet 5.5 | $0.00007 | $0.00122 |
| Haiku 4.5 | $0.00003 | $0.00061 |
Grade A, and why
summarize-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 1mo 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 — 54 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Summarize Book
A summary is a much smaller version of a book that captures its core ideas and is written for an agent to read, not a person.
Locations
Summaries live in ~/Library/Mobile Documents/com~apple~CloudDocs/Documents/Books/:
- Book:
<Author> - <Title>.<extension>. - Summary:
<Author> - <Title> (Summary).md
If the original book file isn't already in the folder, copy it there under this name.
Take the author and title from the book's metadata, dropping any subtitle from the filenames.
Process
- Convert the book to plain text in the scratchpad directory, for example with Calibre's
ebook-convert(brew install --cask calibreif it's missing). Delete the text file once the summary is written. - REQUIRED: Read the whole book before writing. Chapter summaries and the introduction are not the book; the frameworks, numbers and caveats live in the body chapters.
- Read the existing
(Summary).mdfiles in the folder. They are approved summaries of other books; match their shape, depth and tone. - Write the summary.
Shape
- Opening paragraph: No heading. What the book is, who wrote it, and its through-line.
- Core Principles: A short numbered list.
- One section per major topic: Bullets with bolded labels, covering the key frameworks and any concrete numbers or findings.
- How to Apply This When Advising Someone: How an agent should use the ideas when advising a specific person.
- Misconceptions to Correct: A list of common beliefs the book refutes.
Aim for a few thousand words.
Writing Rules
- Paraphrase in your own words. No long quotes or reproduced passages.
- Leave out anecdotes unless one is needed to make a point clear.
- No H1 heading. Use title case for every heading.
- No em dashes anywhere. In bullet lists, separate a label from its description with a colon.
- Spell out an acronym on first use, with the acronym in parentheses.
Rationalizations
| Thought | Reality |
|---|---|
| "The chapter summaries cover the main ideas" | The numbers and caveats that make a summary useful are in the body. |
| "I know this book already" | Memory blurs books together. Summarize the text in front of you. |
| "An em dash reads better here" | None anywhere. Use a colon, a comma or a new sentence. |
| "This quote says it best" | Paraphrase it. A summary that reproduces the book isn't a summary. |
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.
- 1mo ago First seen · 54 lines · 35 tokens per session scan A 51e8b4380e36
summarize-book is a skill published in the GitHub repository LandonSchropp/agent-toolkit (3 stars, last pushed today), licensed MIT. It adds 35 tokens to every session and 609 once invoked, about $0.0001 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 2026-09-16.
Other skills, from other repositories
deliberate-ai-use
Bevisst KI-bruk i Nav: grønn og rød sone, tre-forsøks-regelen, erfaringsnivå og generer-så-forstå, med forskningen bak. Bruk når utvikleren spør om KI bør gjøre en oppgave, vil lære, eller når en oppgave skal plasseres i grønn eller rød sone.
appraise-gemstone
Appraise gemstone value using the four Cs (color, clarity, cut, carat), origin assessment, treatment detection, and market factor analysis. Advisory educational guidance only — not a certified appraisal. Use when understanding factors that determine a gemstone's value, pre-screening stones before a professional…
assess-holistic-health
Conduct temperament-based health assessment from Hildegard von Bingen's Causae et Curae. Evaluates the four temperaments (sanguine, choleric, melancholic, phlegmatic), elemental correspondences (air, fire, earth, water), and provides dietary and lifestyle recommendations for rebalancing. Use when understanding…
compose-sacred-music
Compose or analyze sacred music in Hildegard von Bingen's distinctive modal style. Covers modal selection, melodic contour (wide-range melodies), text-setting (syllabic and melismatic), neumatic notation, and liturgical context for antiphons, sequences, and responsories. Use when composing a new piece in Hildegardian…
analyze-prime-numbers
Analyze prime numbers using primality tests, factorization algorithms, prime distribution analysis, and sieve methods. Covers trial division, Miller-Rabin, Sieve of Eratosthenes, and the Prime Number Theorem. Use when determining whether an integer is prime or composite, finding prime factorizations, counting or…
construct-geometric-figure
Perform a ruler-and-compass construction with step-by-step justification for each operation, producing a constructible geometric figure from given elements. Covers classical Euclidean constructions including perpendicular bisectors, angle bisectors, parallel lines, regular polygons, and tangent lines. Use when given…