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.
git clone --depth 1 https://github.com/cookjohn/gs-skillsWrote 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.
[](https://agentmods.dev/agents/cookjohn/gs-skills/gs-researcher)<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.
<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>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 | $0.00048 | $0.01231 |
| Opus 5 | $0.00024 | $0.00616 |
| Sonnet 5 | $0.00010 | $0.00246 |
| Haiku 4.5 | $0.00005 | $0.00123 |
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.
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
- Use
mcp__chrome-devtools__list_pagesto find open Chrome tabs. - Use
mcp__chrome-devtools__select_pageto select a Google Scholar tab (URL containsscholar.google.com). - If no Google Scholar tab exists, use
mcp__chrome-devtools__new_pageto openhttps://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
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.
- 10d ago First seen · 148 lines · 48 tokens per session scan A 60fd15397718
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.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
Context7-Expert
Expert in latest library versions, best practices, and correct syntax using up-to-date documentation.
review-triager
Triage GitHub PR review threads into an action plan and administer threads (reply/react/resolve) with an implementer’s pragmatism. Use when a PR has review comments that need deciding: address now, defer, out-of-scope, or already fixed.