read-paper: Instructions file for Claude Code

CLAUDE.md

read-paper CLAUDE.md is an instructions file for Claude Code from Lucaswangzcx/read-paper. It costs 699 tokens per session, scanned A, original, MIT.

A set of instructions for reading and explaining academic papers. It covers collecting the paper, checking its sections and evidence, explaining necessary background, and writing a readable report; the default report language is Chinese.

In plain words
What is it for?
For explaining, critiquing, reproducing, or turning an academic paper into a report, including a visual PDF and Markdown copy when an output folder is provided.
Why use it?
It gives the agent a repeatable way to cover the whole accessible paper and separate the authors' claims from the evidence supporting them.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions Claude Code.

This is Lucaswangzcx/read-paper's own configuration. It tells Claude Code how to work on read-paper 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 read-paper configures →

Reuse

Borrowing it

Nothing to install: this file belongs to Lucaswangzcx/read-paper. 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/Lucaswangzcx/read-paper/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/Lucaswangzcx/read-paper

Made for: Claude Code.

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 read-paper CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/lucaswangzcx/read-paper/claude-md.svg)](https://agentmods.dev/instructions/lucaswangzcx/read-paper/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/lucaswangzcx/read-paper/claude-md"><img src="https://agentmods.dev/badge/instructions/lucaswangzcx/read-paper/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 699 This file is loaded in full into every session.
When invoked 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 $0.00699 $0.00699
Opus 5 $0.00349 $0.00349
Sonnet 5 $0.00140 $0.00140
Haiku 4.5 $0.00070 $0.00070

Measured 8d ago against content hash 97b46e9cfd09, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

read-paper 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 8d 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.

CLAUDE.md · 87 lines

How it starts

The opening of the file, as written. The whole thing — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.

read-paper rules for Claude Code

Use these rules when the user asks Claude Code to read, explain, critique, reproduce, or turn an academic paper into a report.

Goal

Read the whole accessible paper and produce a complete but readable learning report. The report should help the user understand the paper first, then inspect the evidence, then critique limitations and reproducibility.

Default output language: Chinese, unless the user asks otherwise.

Default deliverable: a visual PDF report with a Markdown source copy when an output directory is supplied.

Workflow

  1. Collect the paper source: PDF, URL, DOI, title, citation, or pasted text.
  2. Extract or inspect the full accessible main paper before writing the report.
  3. Build a coverage map:
    • sections and subsections
    • visible figures and tables
    • key equations, metrics, datasets, or materials
    • major experiments and controls
    • author claims and supporting evidence
    • inaccessible or missing supplementary materials
  4. Write a readable main report:
    • one-page explanation
    • reading map
    • necessary background and terminology
    • core method or mechanism
    • key visual explanations
    • evidence strength
    • critical takeaways
    • three-pass reading route
  5. Add a completeness appendix:
    • section coverage
    • figure/table coverage
    • equation/metric coverage
    • experiment coverage
    • claim-to-evidence map
    • missing or unverified items
  6. If creating a PDF, render from Markdown and verify that the PDF exists, is non-empty, and contains readable text.

Reading Principles

  • Start with plain language. Do not begin with dense jargon.
  • Explain every central acronym or technical term before using it heavily.
  • For each important figure or table, explain:
    • what question it answers
    • where to look first
    • what result matters
    • what claim it supports
    • what it cannot prove
  • Separate "author claim", "evidence supports", and "not yet confirmed".
  • Do not pretend to cover inaccessible supporting information. Mark it clearly.
  • Keep the main report readable. Put dense coverage details in the appendix.
  • Do not reproduce full papers, long copyrighted passages, or all figures. Include only small relevant excerpts or summaries needed for private learning.

Read the full file on GitHub · 87 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. 8d ago First seen · 87 lines · 699 tokens per session scan A 97b46e9cfd09

Subscribe to this mod's changes

read-paper CLAUDE.md is an instructions file published in the GitHub repository Lucaswangzcx/read-paper (5 stars, last pushed 4mo ago), licensed MIT. It adds 699 tokens to every session, about $0.0035 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

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.

github/spec-kit · 7,104 tokens