A controlled workflow for importing, reading, and combining information from an entire supported book in its original order.

Use it when you need to absorb a complete supported book, read it in order, or continue an existing book-reading session.

It is designed for whole-book reading and keeps track of the source and reading progress instead of treating the book as an ordinary document excerpt.

using-book — Skill for Claude Code and Codex by JanYork/llm-wiki-cli

Install

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.

Any agent

npx skills add JanYork/llm-wiki-cli --skill using-book

Clone the repo

git clone --depth 1 https://github.com/JanYork/llm-wiki-cli

Made for: Claude Code, Codex.

Or install claude-lwc, the plugin that ships this one along with the rest of its 8 skills, 7 hooks, 1 MCP server.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/janyork/llm-wiki-cli/using-book/github.svg)](https://agentmods.dev/skills/janyork/llm-wiki-cli/using-book)

Your own site

<a href="https://agentmods.dev/skills/janyork/llm-wiki-cli/using-book"><img src="https://agentmods.dev/badge/skills/janyork/llm-wiki-cli/using-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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/janyork/llm-wiki-cli/using-book"><img src="https://agentmods.dev/badge/skills/janyork/llm-wiki-cli/using-book.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 28 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 652 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits

NVIDIA SkillSpector pass 7 Sept 2026

How audits are shown

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.

Model	Per session	Once invoked
Fable 5.1	$0.00028	$0.00652
Opus 5.5	$0.00011	$0.00261
Sonnet 5.5	$0.00006	$0.00130
Haiku 4.5	$0.00003	$0.00065

Measured 2mo ago against content hash 09778ef73b0d, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

using-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 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.

integrations/claude-lwc/skills/using-book/SKILL.md · 54 lines

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.

Using Book

Use Book when the user wants whole-book absorption, ordered reading, or recovery of an active Book lease. Skip ordinary lookup, summarization of supplied excerpts, and unsupported HTML, scanned/OCR PDF, MOBI, or AZW3 input.

Book is a silent control plane. Do not narrate status checks, leases, locators, coverage commits, source lookup, or other routine tool calls. Never inspect its SQLite, plugin files, or runtime binaries and never probe CLI help for routine arguments. Give the user only the requested reading result, progress that materially affects them, or a concise actionable failure.

Enter or recover

Inspect LWC_READINESS.book. It is read-only capability metadata, not consent to enable, install, import, or expose book text.
If disabled, explain the durable local-data boundary and ask once before running lwc --scope global config set --book enabled. An explicit enable request already supplies consent. Enabling does not download; the first lwc book status may lazily install the fixed hash-verified runtime.
Run lwc book status. Recover the current book and outstanding lease before import or new reading. Retry with the same request_id, owner, and if_revision.
After cross-machine recovery, require the latest successful Sync receipt and run an explicit exact-revision takeover. The old owner must stop writing after takeover.

Ordered reading

Import only EPUB, TXT, Markdown, or text PDF. Preserve returned book_id, source hash, anomalies, and preparation state. Never guess identity from title or tags.
Do not read until preparation reports validated ordered blocks and ready state.
Call read next with an explicit token or UTF-8-byte budget. Read the complete returned contiguous text and retain lease ID, revision, locators, and range hash.
Submit the required structured report with read commit, owner, request ID, and if_revision. Coverage advances only after that commit succeeds.
Repeat until exact ordered coverage reaches 100%. Search, show, and peek never advance coverage. Synthesis still requires every hierarchy summary, mainline, relation, and anomaly disposition.

Read the full file on GitHub · 54 lines

Files

What ships with it

1 file 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.

agents/openai.yaml 207 B

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.

2mo ago First seen · 54 lines · 28 tokens per session scan A 09778ef73b0d

Subscribe to this mod's changes

using-book is a skill published in the GitHub repository JanYork/llm-wiki-cli (72 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 28 tokens to every session and 652 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 2026-08-30.

Documents Learning and teaching agent-memory-system ai-agents ai-agents-cli context-engineering knowledge-bases local-first-ai

using-book next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
using-bookJanYork/llm-wiki-cli	Skill	72	1mo ago	Apache-2.0	A	28	Claude Code, Codex
cheat-sheetssmurfgg04-gif/context-m	Skill	2	yesterday	Apache-2.0	A	127	Claude Code, Codex
gaokao-generate-reportssmurfgg04-gif/context-m	Skill	2	yesterday	Apache-2.0	A	67	Claude Code, Codex
stage-dslTHU-MAIC/OpenMAIC	Skill	43k	yesterday	MIT	A	104	Claude Code, Codex
pptx-importTHU-MAIC/OpenMAIC	Skill	43k	yesterday	MIT	A	125	Claude Code, Codex
annotate-paper54yyyu/zotero-mcp	Skill	5.8k	6d ago	MIT	A	82	Claude Code, Codex
gsd-helpopen-gsd/gsd-core	Skill	11k	yesterday	MIT	A	12	Claude Code