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.
/plugin marketplace add mlava/scholar-sidekick-mcpnpx agentmods add plugins/mlava/scholar-sidekick-mcp/plugingit clone --depth 1 https://github.com/mlava/scholar-sidekick-mcpGrade A, and why
scholar-sidekick 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 yesterday.
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
{
"$schema": "https://json.schemastore.org/claude-code-plugin.json",
"name": "scholar-sidekick",
"displayName": "Scholar Sidekick",
"version": "0.8.8",
"description": "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 identifier types (DOI, PMID, PMCID, ISBN, arXiv, ISSN, ADS, WHO IRIS) into 10,000+ CSL styles or nine export formats, single or batch.",
"author": {
"name": "Scholar Sidekick",
"url": "https://scholar-sidekick.com"
},
"homepage": "https://scholar-sidekick.com/mcp",
"repository": "https://github.com/mlava/scholar-sidekick-mcp",
"license": "MIT",
"keywords": [
"citations",
"citation-verification",
"fabrication-detection",
"bibliography",
"academic",
"doi",
"pmid",
"arxiv",
"bibtex",
"ris",
"retraction",
"open-access"
],
"mcpServers": {
"scholar-sidekick": {
"command": "npx",
"args": [
"-y",
"scholar-sidekick-mcp@latest"
]
}
}
}
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.
- yesterday First seen · 38 lines scan A 103e692bfa98
scholar-sidekick is a plugin published in the GitHub repository mlava/scholar-sidekick-mcp (8 stars, last pushed 9d 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
science-agent
Citation, prose, figure, and rigor auditing for AI-assisted research drafts.
science-agent
Citation, prose, figure, and rigor auditing for AI-assisted research drafts.
reviewer-2
Rigorous, fair peer review in two modes. (A) Red-team your OWN draft before you submit — a simulated panel (a generous champion, the brutal Reviewer 2, a novelty-hawk Area Chair) predicts the reviews and hands you a prioritized fix list. (B) Review SOMEONE ELSE'S paper when you're an assigned reviewer or helping your…
doiget
Plugin marketplace listing 1 plugin: doiget.
doiget
Turn DOIs and arXiv IDs into local PDFs and structured metadata via official Open-Access APIs. Never bypasses paywalls.
research-stack
Plugin marketplace listing 1 plugin: research-stack.