What is paper-research-skill CLAUDE.md?

Contribution instructions for maintaining a paper-research skill repository. They define versioning rules, required pre-commit checks, and documentation updates.

Use them when editing the paper-research skill project, especially before committing changes to skills, templates, plugin metadata, or README files.

They help contributors keep releases and repository documentation consistent when changing skills or templates.

How Geek96/paper-research-skill configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to Geek96/paper-research-skill. 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/Geek96/paper-research-skill/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/Geek96/paper-research-skill

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/geek96/paper-research-skill/claude-md/github.svg)](https://agentmods.dev/instructions/geek96/paper-research-skill/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/geek96/paper-research-skill/claude-md"><img src="https://agentmods.dev/badge/instructions/geek96/paper-research-skill/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/geek96/paper-research-skill/claude-md"><img src="https://agentmods.dev/badge/instructions/geek96/paper-research-skill/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 1,183 This file is loaded in full into every session.

When invoked 1,183 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.

Model	Per session	Once invoked
Fable 5.1	$0.01183	$0.01183
Opus 5.5	$0.00473	$0.00473
Sonnet 5.5	$0.00237	$0.00237
Haiku 4.5	$0.00118	$0.00118

Measured 2mo ago against content hash e2ef5b83a5aa, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

paper-research-skill 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 · 109 lines

How it starts

The opening of the file, as written. The whole thing — 109 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md — Contribution Rules for paper-research-skill

This file tells Claude (and human contributors) how to maintain this repository consistently.

⚠️ Versioning — EVERY COMMIT MUST FOLLOW

MANDATORY: Agent 每次 commit 前必须执行版本检查。不执行 = 违规。 禁止跳版本号：Agent 只能递增 PATCH（最后一位），绝对不能跳版本（如 1.0.5 → 1.4.0 ❌）。

Version format: MAJOR.MINOR.PATCH — stored in .claude-plugin/plugin.json as the version field. This is the single source of truth.

Component	Rule	Who controls
PATCH	+1 on every commit that changes skill/template/user-facing content	Claude (automatic)
MINOR	Auto-increment when PATCH reaches 10, reset PATCH to 0	Claude (automatic carry)
MAJOR	Only when user explicitly says "bump major" or "breaking change"	Human only

🔴 Pre-Commit Checklist（每次 commit 前必做）

□ 1. cat .claude-plugin/plugin.json → 读取当前版本号
□ 2. 本次 commit 改了 SKILL.md / templates/ / plugin.json / README.md / CHANGELOG.md？
     → YES: PATCH +1（只 +1，不跳）
     → NO:  不 bump
□ 3. PATCH = 10？→ PATCH 归零，MINOR +1
□ 4. 在同一个 commit 中更新 plugin.json 的 version
□ 5. 同步更新 README.md 顶部 badge 中的版本号
□ 6. commit message 中包含版本号

跳过 bump: .gitignore, LICENSE, 纯注释（无行为变化）

Examples

Before	Action	After	OK?
`1.0.3`	patch	`1.0.4`	✅
`1.0.9`	patch (carry)	`1.1.0`	✅
`1.1.9`	patch (carry)	`1.2.0`	✅
`1.2.4`	user says "bump major"	`2.0.0`	✅
`1.0.5`	agent jumps	`1.4.0`	❌ 禁止
`1.3.0`	agent bumps major	`2.0.0`	❌ 需用户授权

Changelog & Release

三层记录体系

层级	文件	粒度	何时写
Git log	git commit messages	每次 commit	自动
CHANGELOG.md	`CHANGELOG.md`	每次 MINOR 进位	进位时汇总该轮所有 patch
GitHub Release	GitHub Releases	每次 MINOR 进位	与 CHANGELOG 同步，`gh release create`

CHANGELOG 规则

不逐 PATCH 写 CHANGELOG。在 MINOR 进位时（如 1.3.9 → 1.4.0），回顾该 MINOR 周期内所有 commit，汇总为一个 release entry。

Read the full file on GitHub · 109 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.

2mo ago First seen · 109 lines · 1,183 tokens per session scan A e2ef5b83a5aa

Subscribe to this mod's changes

paper-research-skill CLAUDE.md is an instructions file published in the GitHub repository Geek96/paper-research-skill (23 stars, last pushed 4mo ago), licensed MIT. It adds 1,183 tokens to every session, about $0.0047 per session on Opus 5.5. 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 2026-08-30.

paper-research-skill CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
paper-research-skill CLAUDE.mdGeek96/paper-research-skill	Instructions file	23	4mo ago	MIT	A	1,183	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

paper-research-skill: Instructions file for Claude Code