agentmods.dev

compare-papers

compare-papers is a skill for Claude Code, Codex from shuishousong/zotero-ima-mcp. It costs 27 tokens per session (262 once invoked), scanned A, original, MIT.

A tool for comparing several research papers in a comparison table. It examines their questions, methods, data, results, conclusions, and limitations.

In plain words
What is it for?
Use it to compare research methods and findings, judge whether conclusions agree, and record the source for each table entry.
Why use it?
It makes differences and agreements between papers easier to see without relying on unsupported claims about which study is better.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

not rated 1repo 3mo ago A scan 27 tokens original MIT

Good fit Use it to compare research methods and findings, judge whether conclusions agree, and record the source for each table entry.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/shuishousong/zotero-ima-mcp/compare-papers
View source ↗ shuishousong/zotero-ima-mcp
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add shuishousong/zotero-ima-mcp --skill compare-papers
Clone the repo
git clone --depth 1 https://github.com/shuishousong/zotero-ima-mcp

Made for: Claude Code, Codex.

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 compare-papers

README.md
[![agentmods](https://agentmods.dev/badge/skills/shuishousong/zotero-ima-mcp/compare-papers/github.svg)](https://agentmods.dev/skills/shuishousong/zotero-ima-mcp/compare-papers)
Your own site
<a href="https://agentmods.dev/skills/shuishousong/zotero-ima-mcp/compare-papers"><img src="https://agentmods.dev/badge/skills/shuishousong/zotero-ima-mcp/compare-papers/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 compare-papers

Your own site · 80×15
<a href="https://agentmods.dev/skills/shuishousong/zotero-ima-mcp/compare-papers"><img src="https://agentmods.dev/badge/skills/shuishousong/zotero-ima-mcp/compare-papers.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 27 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 262 The whole file, excluding the scripts and references it only reads on demand.
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 $0.00027 $0.00262
Opus 5.5 $0.00011 $0.00105
Sonnet 5.5 $0.00005 $0.00052
Haiku 4.5 $0.00003 $0.00026

Measured 2mo ago against content hash db2c77ead618, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

compare-papers 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.

skills/compare-papers/SKILL.md · 26 lines

What it actually says

compare-papers

对用户选定的多篇论文建立可比性矩阵，输出对比结论。

触发条件

用户要求：对比这几篇论文、A 和 B 有什么区别、哪个方法更好、几篇论文结论是否一致等。

流程

  1. 逐篇 zotero_search_items 定位，收集 zoteroKey 列表。
  2. 逐篇 literature_paper_read 读取核心信息（问题/方法/数据/结果/结论）。
  3. 建立对比矩阵（维度：研究问题、方法、数据集、主要结果、结论、局限）。
  4. 输出矩阵 + 差异分析 + 一致性判断。

输出要求

  • 矩阵必须逐格标注文献来源。
  • 不输出未经文献支持的"更好/更差"判断；只陈述事实差异。
  • 不要求用户人工干预：自动判断哪些文献可用、自动读取全文。
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 · 26 lines · 27 tokens per session scan A db2c77ead618

Subscribe to this mod's changes

compare-papers is a skill published in the GitHub repository shuishousong/zotero-ima-mcp (1 stars, last pushed 3mo ago), licensed MIT. It adds 27 tokens to every session and 262 once invoked, about $0.0001 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 2026-08-31.

LiteratureResearchZoteroai-agentmcp
Related

compare-papers compared with skills from other repositories

compare-papers next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
compare-papersshuishousong/zotero-ima-mcpSkill13mo agoMITA27Claude Code, Codex
literature-mentorbahayonghang/my-ai-cli-toolkitSkill1710d agoMITA121Claude Code, Codex
zotero-cli54yyyu/zotero-mcpSkill5.8k2d agoMITA93Claude Code, Codex
annotate-paper54yyyu/zotero-mcpSkill5.8k2d agoMITA82Claude Code, Codex
deeppapernote917Dhj/DeepPaperNoteSkill1.3ktodayMITA71Claude Code, Codex
paper-glossary917Dhj/DeepPaperNoteSkill1.3ktodayMITA46Claude Code, Codex
fin-ref-papercsmar432/finai-researchSkill1095d agoMITA47Claude Code, Codex