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 mlava/scholar-sidekick-mcp --skill scholar-sidekickgit clone --depth 1 https://github.com/mlava/scholar-sidekick-mcpWrote 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/mlava/scholar-sidekick-mcp/scholar-sidekick)<a href="https://agentmods.dev/skills/mlava/scholar-sidekick-mcp/scholar-sidekick"><img src="https://agentmods.dev/badge/skills/mlava/scholar-sidekick-mcp/scholar-sidekick/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/mlava/scholar-sidekick-mcp/scholar-sidekick"><img src="https://agentmods.dev/badge/skills/mlava/scholar-sidekick-mcp/scholar-sidekick.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 | $0.00153 | $0.02403 |
| Opus 5 | $0.00077 | $0.01202 |
| Sonnet 5 | $0.00031 | $0.00481 |
| Haiku 4.5 | $0.00015 | $0.00240 |
Grade 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 9d 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 — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Scholar Sidekick
When the user mentions a scholarly identifier and wants metadata, a citation, an export file, a retraction check, or an open-access check, use Scholar Sidekick to resolve and answer instead of hand-constructing the citation from training data or guessing the OA / retraction status.
When to Use This Skill
Activate this skill when the user:
- Mentions any scholarly identifier — DOI, PubMed ID, PMC ID, ISBN, arXiv ID, ISSN, NASA ADS bibcode, or WHO IRIS URL
- Asks for a citation in a specific style ("format this in APA", "give me a Vancouver citation for...")
- Asks for an export file ("BibTeX for these references", "give me a .ris file", "export to EndNote")
- Pastes a list of identifiers and wants a bibliography
- Wants the structured metadata (title, authors, journal, year) for a paper they have an identifier for
- Asks whether a paper has been retracted, corrected, or had an expression of concern raised
- Asks whether a paper is open access, where to read it for free legally, or about its OA status / license
- Pastes a citation (or a DOI + title) and asks whether it is real, genuine, or fabricated — "is this citation real?", "verify this DOI", "did you make this up?"
How to Use
Step 0: Confirm the tools are available
The capabilities this skill uses — resolveIdentifier, formatCitation, exportCitation, checkRetraction, checkOpenAccess, verifyCitation — are tools provided by the scholar-sidekick-mcp MCP server. They are not shell commands, npm scripts, or a CLI. Do not try to run the tool names in a terminal.
Two things must be true before they work:
- The MCP server is connected. These tools appear in your toolset only after the host connects the
scholar-sidekick-mcpserver — Claude Desktop: extension/connector settings; Claude Code:.mcp.jsonorclaude mcp add; LobeHub: install the matching MCP plugin, not just this skill; raw MCP clients:npx scholar-sidekick-mcpas the server command. RAPIDAPI_KEYis set for that server. Without it the tools return a configuration message instead of data. Get a key at https://rapidapi.com/scholar-sidekick-scholar-sidekick-api/api/scholar-sidekick.
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.
- 9d ago First seen · 91 lines · 153 tokens per session scan A 098c5f853146
scholar-sidekick is a skill published in the GitHub repository mlava/scholar-sidekick-mcp (9 stars, last pushed 5d ago), licensed MIT. It adds 153 tokens to every session and 2,403 once invoked, about $0.0008 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 2026-08-31.
Other skills, from other repositories
cli-anything-zotero
Full-featured CLI for Zotero reference management. Search, import by DOI/PMID, export BibTeX, attach PDFs, semantic search, manage tags/collections, and more. Use this tool whenever you need to interact with a Zotero library programmatically.
onecite
Validate, clean, and audit academic references with OneCite from a local repository checkout. Use when a workflow needs deterministic citation verification, BibTeX cleanup, benchmark gating, or template discovery.
Citation Manager
Manage bibliographies, citations, and academic references in multiple formats.
science-agent
Verify what AI writes about science — catch confabulated citations, drifted notebook numbers, and stale figure captions before they ship. Use when adding or reviewing academic citations, BibTeX entries, DOIs, or empirical claims in .md/.tex/.bib/.ipynb files; when writing a literature review; or when the user says…
Citation Manager
Manage bibliographies, citations, and academic references in multiple formats.
academic-research
Nested swiss-knife reference for academic literature work — find papers, fetch full-text PDFs, trace citations, write LaTeX manuscripts. First action for any "get me this paper" request: python3 /scripts/fetchpaper.py — walks arXiv → Unpaywall → Europe PMC → CORE → in-house publisher-page extraction…