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.
npx skills add cookjohn/gs-skills --skill gs-fulltextgit 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/skills/cookjohn/gs-skills/gs-fulltext)<a href="https://agentmods.dev/skills/cookjohn/gs-skills/gs-fulltext"><img src="https://agentmods.dev/badge/skills/cookjohn/gs-skills/gs-fulltext/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/skills/cookjohn/gs-skills/gs-fulltext"><img src="https://agentmods.dev/badge/skills/cookjohn/gs-skills/gs-fulltext.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 | $0.00041 | $0.01133 |
| Opus 5 | $0.00020 | $0.00566 |
| Sonnet 5 | $0.00008 | $0.00227 |
| Haiku 4.5 | $0.00004 | $0.00113 |
Grade A, and why
gs-fulltext 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- gs-fulltext — 97% identical, 1 lines differ
How it starts
The opening of the file, as written. The whole thing — 134 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Google Scholar Full Text Access
Resolve and present all full-text access options for a paper found in Google Scholar search results.
Arguments
$ARGUMENTS can be:
- A
data-cidfrom a previous search result - A result number (e.g.,
3) referring to a previous search result
Prerequisites
This skill works best after a previous gs-search or gs-advanced-search call, which already extracts fullTextUrl and href for each result. If those are available, use them directly.
Steps
Step 1: Collect links from search results
From the previous search result, extract these fields for the target paper:
fullTextUrl: direct PDF/HTML link (from.gs_ggs a)href: link to the paper's publisher page (from.gs_rt a)dataCid: cluster ID
If no previous search context is available, search for the paper first using gs-search.
Step 2: Resolve additional links (evaluate_script)
Navigate to the Google Scholar results page (if not already there), then extract full-text links for the specific paper:
async () => {
const cid = "DATA_CID_HERE";
// Find the result item by data-cid
const item = document.querySelector(`.gs_r.gs_or.gs_scl[data-cid="${cid}"]`);
if (!item) return { error: 'not_found', message: 'Paper not found on current page. Try searching again.' };
const titleEl = item.querySelector('.gs_rt a');
const title = titleEl?.textContent?.trim() || item.querySelector('.gs_rt')?.textContent?.trim() || '';
const paperUrl = titleEl?.href || '';
// Full-text PDF/HTML link (shown on the right side of results)
const fullTextEl = item.querySelector('.gs_ggs a') || item.querySelector('.gs_or_ggsm a');
const fullTextUrl = fullTextEl?.href || '';
const fullTextType = fullTextEl?.querySelector('span.gs_ctg2')?.textContent?.trim() || '';
// Meta info for context
const meta = item.querySelector('.gs_a')?.textContent || '';
const parts = meta.split(' - ');
const authors = parts[0]?.trim() || '';
const journalYear = parts[1]?.trim() || '';
// Try to extract DOI from paper URL
let doi = '';
if (paperUrl.includes('doi.org/')) {
doi = paperUrl.replace(/^https?:\/\/(dx\.)?doi\.org\//, '');
}
// Build access links
const links = {};
if (fullTextUrl) {
links.fullText = fullTextUrl;
links.fullTextType = fullTextType || (fullTextUrl.endsWith('.pdf') ? '[PDF]' : '[HTML]');
}
if (paperUrl) {
links.publisher = paperUrl;
}
if (doi) {
links.doi = `https://doi.org/${doi}`;
links.scihub = `https://sci-hub.ru/${doi}`;
} else if (paperUrl) {
// Sci-Hub also works with direct URLs
links.scihub = `https://sci-hub.ru/${paperUrl}`;
}
return {
dataCid: cid,
title,
authors,
journalYear,
doi,
fullTextUrl,
fullTextType,
paperUrl,
links
};
}
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 · 134 lines · 41 tokens per session scan A 43ff7d4d17fa
gs-fulltext is a skill published in the GitHub repository cookjohn/gs-skills (505 stars, last pushed 6mo ago), licensed MIT. It adds 41 tokens to every session and 1,133 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 skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…