paper-toolkit-mcp: Instructions file for Claude Code

CLAUDE.md

paper-toolkit-mcp CLAUDE.md is an instructions file for Claude Code from czwziy/paper-toolkit-mcp. It costs 1,162 tokens per session, scanned A, original, from a forked repository, MIT.

Project instructions for `paper-toolkit-mcp`, an MCP toolkit for searching academic papers, processing manuscripts, and generating citations. Academic papers are research publications, and citations are references that identify the sources used.

In plain words
What is it for?
They are for building and verifying the toolkit with linting, type checks, architecture checks, tests, coverage, and security scans.
Why use it?
They tell developers where to find the project's architecture, feature specifications, checks, and test commands.

Instructions file for Claude Code

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

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

Reuse

Borrowing it

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

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-toolkit-mcp CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/czwziy/paper-toolkit-mcp/claude-md/github.svg)](https://agentmods.dev/instructions/czwziy/paper-toolkit-mcp/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/czwziy/paper-toolkit-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/czwziy/paper-toolkit-mcp/claude-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 paper-toolkit-mcp CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/czwziy/paper-toolkit-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/czwziy/paper-toolkit-mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,162 This file is loaded in full into every session.
When invoked 1,162 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 fork From a forked repository.
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 $0.01162 $0.01162
Opus 5.5 $0.00465 $0.00465
Sonnet 5.5 $0.00232 $0.00232
Haiku 4.5 $0.00116 $0.00116

Measured 2mo ago against content hash 6944cd3947e1, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

paper-toolkit-mcp 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 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.

CLAUDE.md · 78 lines

How it starts

The opening of the file, as written. The whole thing — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md — paper-toolkit-mcp

本文件是知识地图(指向"去哪找"),不是百科全书。

项目概述

paper-toolkit-mcp 是一个 MCP 工具包,用于学术论文搜索、手稿处理与引用生成。技术栈:Python 3.10+ / FastMCP / requests / pypdf / Pandoc。PyPI 包名 paper-toolkit-mcp,提供 paper-toolkit-mcp(MCP server)入口。

知识导航

你需要… 去这里
理解分层架构与依赖方向 .harness/specs/architecture/boundaries.md
系统概览(模块/技术栈/数据流) .harness/specs/architecture/overview.md
查找"约定 → 机械化规则"对照表 .harness/constraints/contracts.md
安全扫描配置 .harness/constraints/security/bandit.yaml
架构约束(import-linter)配置 pyproject.toml 的 [tool.importlinter]
Lint / 类型 / 测试 / 覆盖率配置 pyproject.toml 的对应 [tool.*] 段
了解功能设计与范围 .trae/specs/<feature>/spec.md
Harness 工程化方法论 harness.md

构建与验证

# 一次性安装开发依赖(lint / 类型 / 测试 / 架构 / 安全)
pip install -e ".[dev]"

# 风格检查(ruff)
ruff check paper_toolkit_mcp tests

# 类型检查(mypy)
mypy paper_toolkit_mcp

# 架构检查(import-linter,分层依赖方向)
lint-imports

# 单元测试(CI 默认,hermetic 离线)
pytest

# 覆盖率报告
pytest --cov --cov-report=term-missing

# 集成测试(需网络,手动触发,CI 不跑)
pytest tests/integration/

# 安全扫描(bandit)
bandit -r paper_toolkit_mcp -c .harness/constraints/security/bandit.yaml -q

# 完整验证门(CI 等价命令)
ruff check paper_toolkit_mcp tests \
  && mypy paper_toolkit_mcp \
  && lint-imports \
  && pytest \
  && bandit -r paper_toolkit_mcp -c .harness/constraints/security/bandit.yaml -q

硬性规则

以下规则由约束层代码机械化执行,违反即 CI 红。

  • 禁止硬编码 API key。所有密钥通过 config.get_env(name) 读取,配置走 .env 文件(gitignored)。参见 .env.example。
  • 禁止 academic_platforms/* 反向 import server 或 tools。分层依赖方向单向,由 lint-imports 强制。
  • 禁止新增不继承 PaperSource 的搜索器。所有学术源必须实现 academic_platforms/base.py 的 PaperSource 抽象基类。
  • 禁止在 paper.py(数据类)中 import 任何上层模块。Paper 是最底层依赖。
  • 禁止提交真实 API key / .env / paper_cache/ / downloads/。.gitignore 已覆盖。
  • 测试拆分:tests/unit/ 必须离线 hermetic(mock 所有外部 IO);任何在 import 或 setUp 阶段触网、或断言真实 API 响应的测试放 tests/integration/。CI 只跑 tests/unit/。
  • 不可逆操作:不允许 git push --force 到 main/master;不允许删除 csl/ 内置引用样式文件。
  • 入库操作:存入到数据库中的元数据,必须要有摘要
  • 代码中严禁使用emoji进行输出提示

Read the full file on GitHub · 78 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. 2mo ago First seen · 78 lines · 1,162 tokens per session scan A 6944cd3947e1

Subscribe to this mod's changes

paper-toolkit-mcp CLAUDE.md is an instructions file published in the GitHub repository czwziy/paper-toolkit-mcp (0 stars, last pushed 3mo ago), licensed MIT. It adds 1,162 tokens to every session, about $0.0046 per session on Opus 5.5. A static security scan graded it A with 0 findings. It comes from a forked repository.

Related

paper-toolkit-mcp CLAUDE.md compared with instructions from other repositories

paper-toolkit-mcp CLAUDE.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
paper-toolkit-mcp CLAUDE.mdczwziy/paper-toolkit-mcpInstructions file03mo agoMITA1,162Claude Code
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143kyesterdayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149kyesterdayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file274k2d agoMITA4,313Codex, OpenCode