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/nett0eth/research-stackWrote 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/plugins/nett0eth/research-stack/research-stack)<a href="https://agentmods.dev/plugins/nett0eth/research-stack/research-stack"><img src="https://agentmods.dev/badge/plugins/nett0eth/research-stack/research-stack/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/plugins/nett0eth/research-stack/research-stack"><img src="https://agentmods.dev/badge/plugins/nett0eth/research-stack/research-stack.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
research-stack 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 1mo 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.
What it actually says
{
"name": "research-stack",
"version": "0.1.0",
"description": "Ciclo completo de pesquisa com embasamento pro Claude: fonte primaria, ingestao legivel, protocolo, sintese citada e memoria auditavel.",
"author": { "name": "Netto", "url": "https://x.com/nett0eth" },
"homepage": "https://github.com/nett0eth/research-stack",
"repository": "https://github.com/nett0eth/research-stack",
"license": "MIT",
"keywords": ["research", "science", "citations", "pdf", "zotero", "arxiv", "portugues"]
}
What it installs
The manifest is a name and a version. 3 skills, 2 MCP servers travel with it, and installing the plugin installs all of them — 275 tokens a session between them. Each is measured on its own page, and each can be installed alone.
What ships with it
1 file beside plugin.json in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 1mo ago First seen · 11 lines scan A 4b4ecbdccc2a
research-stack is a plugin published in the GitHub repository nett0eth/research-stack (4 stars, last pushed 2mo ago), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. 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.
Other plugins, from other repositories
claw-hwp marketplace
Single-plugin marketplace shipping claw-hwp — Korean Hangul Word Processor (.hwp / .hwpx) support for Claude.
claw-hwp
Read, create, and edit Korean Hangul Word Processor documents (.hwp / .hwpx) in Claude. Built on the rhwp WebAssembly viewer/editor — no Hancom Office, no LibreOffice, no Windows COM required.
zoteus
Your Zotero library inside Claude: search by keyword or meaning, quote PDF passages with page numbers, format citations in any CSL style, add papers by DOI or arXiv id, and organize with reversible writes.
l3a0
l3a0's Claude Code skills. kindle-highlights extracts a book's Kindle highlights into one verbatim, location-cited Markdown file, recovering everything Amazon's export limit truncates or hides. ask-board convenes a board of ten advisor agents, each with its own objective, and a secretary who drafts the synthesis, on a.
data-analysis-skills
A data-analysis and reporting package for CSV, Excel, JSON, or TSV files. It cleans and analyzes the data, then produces a single interactive HTML report tailored to an industry and audience.
scholar-sidekick
Catch AI-fabricated citations: verifyCitation cross-checks a claimed title against the real record at its identifier, detecting the dominant real-DOI + invented-title pattern (Topaz et al., Lancet 2026) that simple DOI resolution cannot catch. Also checks retraction and open-access status, and resolves eight…