paper-agent: Instructions file for Claude Code

CLAUDE.md

paper-agent CLAUDE.md is an instructions file for Claude Code from Guo-Chenxu/paper-agent. It costs 899 tokens per session, scanned A, original, Apache-2.0.

Instructions for an AI agent that supports the full process of writing academic research papers, from collecting papers and running experiments to writing, reviewing, and revising the final document.

In plain words
What is it for?
Use it when working on research ideas, experiment design, LaTeX papers, simulated peer reviews, revisions, and final language improvements.
Why use it?
It sets expectations for clear academic writing and requires each automated stage to receive an adversarial review, meaning a deliberate search for flaws.

Instructions file for Claude Code

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

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

Reuse

Borrowing it

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

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 paper-agent CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/guo-chenxu/paper-agent/claude-md.svg)](https://agentmods.dev/instructions/guo-chenxu/paper-agent/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/guo-chenxu/paper-agent/claude-md"><img src="https://agentmods.dev/badge/instructions/guo-chenxu/paper-agent/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 899 This file is loaded in full into every session.
When invoked 899 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 $0.00899 $0.00899
Opus 5 $0.00449 $0.00449
Sonnet 5 $0.00180 $0.00180
Haiku 4.5 $0.00090 $0.00090

Measured 7d ago against content hash f996dd0c47ee, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

paper-agent 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 7d 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 · 55 lines

How it starts

The opening of the file, as written. The whole thing — 55 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

Role

This repository is operated as a full-process academic paper writing agent. Future Claude Code instances should support paper collection, idea generation, experiment design and execution, LaTeX paper writing, simulated review, revision, and final optimization.

Highest Requirement: Logical Flow, Grammar, and Idiomatic Writing

The single most important requirement for all academic writing is: the paper must have logically coherent and smooth flow, contain no grammatical errors or awkward phrasing, and use idiomatic, native-level English expression. This requirement overrides all other writing constraints.

When there is a conflict between this requirement and any rule under .claude/rules/, prioritize logical flow and natural, idiomatic expression. The rules serve as general guidance but must not compromise readability or naturalness.

Adversarial Review Policy (Zero Tolerance, Zero Compromise)

Every automated stage must undergo adversarial review by independent sub-agents before it can be considered complete. This is not advisory — it is the gate that determines whether a stage is done.

Rules:

  1. No exit until perfect. The review loop ("produce → multi-agent adversarial review → fix → re-review") has no cap on rounds. Exit only when zero issues remain across all review dimensions.
  2. Full-dimension coverage. Each review must check correctness (logic, facts, citations), completeness (no gaps, all edge cases), and consistency (cross-reference alignment, code-description match). Any shortfall in any dimension triggers an automatic rejection.
  3. No compromises allowed. Verdicts like "acceptable," "minor issue," or "not a big deal" are forbidden. Every review round has exactly two possible outcomes: all pass or issues remain. Ambiguous cases default to "issues remain."
  4. Independent sub-agents. Review agents must think independently without cross-influence. Results are aggregated via voting or averaging. When disagreement exceeds the threshold (e.g., score gap ≥ 2), spawn an additional arbitration agent.
  5. Full audit trail. Every finding, fix, and re-verification must be recorded in the stage report.
  6. Holistic re-review. After fixes, re-submit the entire output for adversarial review — do not limit re-review to only the previously flagged issues. New problems introduced by fixes must be caught.

Read the full file on GitHub · 55 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. 7d ago First seen · 55 lines · 899 tokens per session scan A f996dd0c47ee

Subscribe to this mod's changes

paper-agent CLAUDE.md is an instructions file published in the GitHub repository Guo-Chenxu/paper-agent (2 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 899 tokens to every session, about $0.0045 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