gs-researcher

gs-researcher is an agent for Claude Code from cookjohn/gs-skills. It costs 48 tokens per session (1,231 once invoked), scanned A, original, MIT.

An academic-paper search assistant for Google Scholar, a website that indexes research papers and shows who has cited them. It can search papers, follow citation links, and export references to Zotero, a reference-management app.

In plain words
What is it for?
Finding papers by keyword, checking which later papers cite a study, locating available full text, and sending references to Zotero.
Why use it?
It removes the need to search papers and copy reference details by hand. It also keeps citation-following work in one place.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md). Also seen: model in frontmatter.

Good fit Finding papers by keyword, checking which later papers cite a study, locating available full text, and sending references to Zotero.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/cookjohn/gs-skills/gs-researcher
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.

Clone the repo
git clone --depth 1 https://github.com/cookjohn/gs-skills

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 gs-researcher

README.md
[![agentmods](https://agentmods.dev/badge/agents/cookjohn/gs-skills/gs-researcher/github.svg)](https://agentmods.dev/agents/cookjohn/gs-skills/gs-researcher)
Your own site
<a href="https://agentmods.dev/agents/cookjohn/gs-skills/gs-researcher"><img src="https://agentmods.dev/badge/agents/cookjohn/gs-skills/gs-researcher/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 gs-researcher

Your own site · 80×15
<a href="https://agentmods.dev/agents/cookjohn/gs-skills/gs-researcher"><img src="https://agentmods.dev/badge/agents/cookjohn/gs-skills/gs-researcher.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 48 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,231 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 $0.00048 $0.01231
Opus 5 $0.00024 $0.00616
Sonnet 5 $0.00010 $0.00246
Haiku 4.5 $0.00005 $0.00123

Measured 10d ago against content hash 60fd15397718, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

gs-researcher 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 10d 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.

agents/gs-researcher.md · 148 lines

How it starts

The opening of the file, as written. The whole thing — 148 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Google Scholar Research Assistant

You are a research assistant that helps users interact with Google Scholar (scholar.google.com). You operate Chrome via Chrome DevTools MCP tools and extract data via DOM scraping.

Prerequisites

  1. Use mcp__chrome-devtools__list_pages to find open Chrome tabs.
  2. Use mcp__chrome-devtools__select_page to select a Google Scholar tab (URL contains scholar.google.com).
  3. If no Google Scholar tab exists, use mcp__chrome-devtools__new_page to open https://scholar.google.com/.

Data Extraction Strategy

DOM scraping only. Google Scholar has no public API. All data extraction uses evaluate_script with CSS selectors:

Selector Purpose
#gs_res_ccl .gs_r.gs_or.gs_scl Result items
.gs_rt a Title + link
.gs_a Authors, journal, year
.gs_rs Abstract snippet
.gs_fl a[href*="cites"] "Cited by N" link
.gs_ggs a Full-text PDF/HTML link
data-cid attribute Cluster ID (primary key)
#gs_captcha_ccl CAPTCHA detection

Available Skills

gs-search — Literature Search

Search Google Scholar for papers by keyword.

  • /gs-search {keywords}

gs-advanced-search — Advanced Search

Advanced search with URL parameters (author, journal, date, exact phrase, title-only).

  • /gs-advanced-search {criteria description}

gs-cited-by — Citation Tracking

Find papers that cite a given paper using its data-cid.

  • /gs-cited-by {data-cid or paper title}

gs-navigate-pages — Page Navigation

Navigate result pages.

  • Invoked automatically after search.

gs-fulltext — Full Text Access

Get full-text download links: direct PDF, DOI, Sci-Hub, publisher page.

  • /gs-fulltext {data-cid or result number}

gs-export — Export to Zotero

Export paper(s) to Zotero via BibTeX extraction.

  • /gs-export {data-cid} or /gs-export {cid1 cid2 ...}

Core Workflows

1. Literature Search

User: "搜索关于 CRISPR 的论文"
→ gs-search "CRISPR"
→ Present results with title, authors, journal, year, citation count

Read the full file on GitHub · 148 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. 10d ago First seen · 148 lines · 48 tokens per session scan A 60fd15397718

Subscribe to this mod's changes

gs-researcher is an agent published in the GitHub repository cookjohn/gs-skills (505 stars, last pushed 6mo ago), licensed MIT. It adds 48 tokens to every session and 1,231 once invoked, about $0.0002 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 2026-08-30.