mcp-ebook-read: Instructions file for Codex

AGENTS.md

mcp-ebook-read AGENTS.md is an instructions file for Codex, OpenCode from ArtiPyHeart/mcp-ebook-read. It costs 1,699 tokens per session, scanned A, original, MIT.

An instruction guide for developing and using the mcp-ebook-read document-reading tool. It describes its purpose, common reading tasks, development workflow, and project limits.

In plain words
What is it for?
It is for guiding document navigation, chapter reading, summaries, question answering, formula understanding, and related code work.
Why use it?
It gives agents consistent rules for building the tool and using it to understand books and papers with as much detail as possible.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md. Also seen: mentions AGENTS.md; mentions Codex; $skill-name invocation.

This is ArtiPyHeart/mcp-ebook-read's own configuration. It tells Codex and OpenCode how to work on mcp-ebook-read itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything mcp-ebook-read configures →

Reuse

Borrowing it

Nothing to install: this file belongs to ArtiPyHeart/mcp-ebook-read. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/ArtiPyHeart/mcp-ebook-read/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/ArtiPyHeart/mcp-ebook-read

Made for: Codex, OpenCode.

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.

agentmods badge for mcp-ebook-read AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/artipyheart/mcp-ebook-read/agents-md/github.svg)](https://agentmods.dev/instructions/artipyheart/mcp-ebook-read/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/artipyheart/mcp-ebook-read/agents-md"><img src="https://agentmods.dev/badge/instructions/artipyheart/mcp-ebook-read/agents-md/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.

agentmods 80×15 button for mcp-ebook-read AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/artipyheart/mcp-ebook-read/agents-md"><img src="https://agentmods.dev/badge/instructions/artipyheart/mcp-ebook-read/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,699 This file is loaded in full into every session.
When invoked 1,699 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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.

ModelPer sessionOnce invoked
Fable 5.1 $0.01699 $0.01699
Opus 5 $0.00849 $0.00849
Sonnet 5 $0.00340 $0.00340
Haiku 4.5 $0.00170 $0.00170

Measured 9d ago against content hash f8f88e5f9230, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

mcp-ebook-read AGENTS.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 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.

AGENTS.md · 83 lines

How it starts

The opening of the file, as written. The whole thing — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.

mcp-ebook-read Agent Guide

Scope

  • Build a Codex-usable MCP focused on reading EPUB and PDF books/papers.
  • Keep the implementation minimal first, then iterate.

Product Mission

  • Build toward as-lossless-as-possible parsing of EPUB/PDF books and papers so LLMs can understand source materials with high fidelity.
  • Make the MCP a practical reading companion that collaborates deeply with human users and supports large-scale reading workloads.

Typical Scenarios

  • Use outline-first navigation plus selected chapter reading to summarize content, answer reading questions, and guide users through difficult sections.
  • Help users bring books/papers into real engineering projects, then evaluate incremental value through reading, formula understanding, and code implementation.

Environment

  • Python package/dependency workflow uses uv.
  • Prefer uv run ... for all local commands.
  • Prefer replying to users in Simplified Chinese in chat responses only.
  • Prefer English for project files, documentation, and code comments.

Constraints

  • extern/ is reference-only.
  • Do not modify files under extern/.
  • Do not track extern/ in git.

Decision Policy

  • For any uncertain decision, stop and ask the user before proceeding.
  • Apply fail-fast principle across the project.
  • Use a single implementation path for each feature; avoid redundant fallback/bypass paths unless explicitly approved.
  • During iteration, always optimize for LLM best practices when using this MCP to read books and papers.
  • If compatibility and breaking changes conflict, prefer breaking changes.
  • When shipping breaking changes, remove parameters/fields that are no longer used; do not keep deprecated placeholders.
  • Continuously simplify the codebase: remove redundant branches, stale outputs, and dead compatibility layers.
  • MCP tool names must encode file format and use-case explicitly to minimize LLM confusion; avoid generic multi-mode tool names.
  • Prefer explicit observability over silent degradation: when parsing/extraction falls back, loses fidelity, or cannot explain an output confidently, surface structured diagnostics to the MCP caller so the agent can notice, complain, and route feedback to the human user.

Read the full file on GitHub · 83 lines

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.

  1. 9d ago First seen · 83 lines · 1,699 tokens per session scan A f8f88e5f9230

Subscribe to this mod's changes

mcp-ebook-read AGENTS.md is an instructions file published in the GitHub repository ArtiPyHeart/mcp-ebook-read (2 stars, last pushed 2mo ago), licensed MIT. It adds 1,699 tokens to every session, about $0.0085 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.

Related

Other instructions, from other repositories

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

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.

openai/codex · 5,153 tokens

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).

microsoft/vscode · 6,785 tokens

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).

microsoft/vscode · 5,001 tokens

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.

langchain-ai/langchain · 4,469 tokens

deepseek-harness AGENTS.md

AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.

deepseek-ai/deepseek-harness · 3,735 tokens