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/newx/omabook/claude-mdgit clone --depth 1 https://github.com/newx/omabookWrote 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/newx/omabook/claude-md)<a href="https://agentmods.dev/instructions/newx/omabook/claude-md"><img src="https://agentmods.dev/badge/instructions/newx/omabook/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 | $0.06929 | $0.06929 |
| Opus 5 | $0.03465 | $0.03465 |
| Sonnet 5 | $0.01386 | $0.01386 |
| Haiku 4.5 | $0.00693 | $0.00693 |
Grade A, and why
omabook 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 3d 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 — 581 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
Orientation for coding agents working in this repository. Humans want the README; this file covers setup and the conventions that are not obvious from the code.
What this is. omabook is a book library and reader for Omarchy — EPUB, PDF
and MOBI, with reading aloud and local AI. It was written in Rust with
cxx-qt and is being reimplemented here in
plain C++17 and Qt 6, so that it is built the same way as
omawrite, the Omarchy Markdown editor.
The Rust original lives at ~/Projects/omabook-rust and is the reference for
behaviour; SPEC.md is the reference for intent and
TODO.md tracks the port.
omawrite is the style authority. When this document and omawrite disagree, omawrite wins and this document is wrong. There are exactly three deliberate divergences, all because omabook is roughly ten times omawrite's size; each is named and justified where it appears rather than left to be discovered.
Setup
Two things are needed before a clone will run.
1. Qt 6. qt6-base, qt6-declarative, qt6-webengine, qt6-webchannel,
qt6-imageformats, qt6-svg, plus poppler for PDF covers and text. Arch
ships qmake as qmake6; bin/build resolves either name.
qt6-imageformats is not optional and is easy to miss: without it, WebP covers
— which some EPUBs use — decode to nothing and the book gets no cover, with no
error anywhere.
2. foliate-js. The reader engine is not vendored and is gitignored. Without it the app builds and the library works, but opening a book renders nothing:
git clone https://github.com/johnfactotum/foliate-js.git assets/reader/foliate-js
Build, test, run
./bin/build # release, into build/
./bin/build --debug # into build-debug/, faster to compile
./bin/test # QtTest over src/core, and the boundary check
./build/omabook
./bin/install builds the Arch package through makepkg -fsi.
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.
- 3d ago First seen · 581 lines · 6,929 tokens per session scan A 51147433e4b1
omabook CLAUDE.md is an instructions file published in the GitHub repository newx/omabook (12 stars, last pushed 5d ago), licensed MIT. It adds 6,929 tokens to every session, about $0.0346 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 2026-08-31.
Other instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.