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 Liyux3/scholar-mcp --skill deep-researchgit clone --depth 1 https://github.com/Liyux3/scholar-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/liyux3/scholar-mcp/deep-research)<a href="https://agentmods.dev/skills/liyux3/scholar-mcp/deep-research"><img src="https://agentmods.dev/badge/skills/liyux3/scholar-mcp/deep-research/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/liyux3/scholar-mcp/deep-research"><img src="https://agentmods.dev/badge/skills/liyux3/scholar-mcp/deep-research.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 | $0.00049 | $0.01356 |
| Opus 5 | $0.00024 | $0.00678 |
| Sonnet 5 | $0.00010 | $0.00271 |
| Haiku 4.5 | $0.00005 | $0.00136 |
Grade A, and why
deep-research 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 2d 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 — 136 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Deep Research
The goal is not just to find facts, but to build an evolving, auditable understanding of a field. Use Scholar MCP for academic discovery, identity resolution, citation traversal, primary-text reading, and selected research memory.
Choose the depth
| Mode | Starting scope |
|---|---|
| Focused verification | One bounded claim, one or two searches, a small set of decisive primary sources |
| Technical review | Complementary search views, five to eight inspected candidates, two or three expansion seeds |
| Frontier scan | Recent work, active groups, weak signals, counterevidence, and follow-up activity |
These are starting budgets. Walk one step, see what's there, then decide the next step. Expand when a new branch can change the field map or conclusion; stop a branch when it repeats known structure or drifts from the question.
Scholar MCP routing
| Need | Tool |
|---|---|
| Check live coverage | Read scholar://status |
| Search literature | search_papers; preserve the natural-language question and select an intent only when it changes ranking |
| Recover surveys, foundations, recent work, methods, or datasets | search_papers with intent=survey, foundational, recent, method, or dataset |
| Inspect a paper | paper_info with the needed parts of detail,citations,references |
| Find topical neighbors | recommend_papers with relation=similar |
| Find intellectual peers | recommend_papers with relation=peers |
| Cross vocabulary boundaries | recommend_papers with relation=kin |
| Build a lineage | Resolve stable seed IDs, then use build_paper_graph |
| Read primary evidence | read_paper; one call returns the complete extracted paper |
| Retain a PDF | download_paper |
| Curate durable evidence | paper_library for selected papers, notes, tags, collections, and vault export |
Scholar routes raw, short, and compressed query forms to different source types.
Keep the original question intact. Use source filters when the research question
justifies them. Read _meta.source_coverage, _meta.reranker, and degradation
details before interpreting an empty or thin result. Enable debug=true when
source-level yield, latency, or ranking provenance changes the diagnosis.
What ships with it
1 file beside SKILL.md 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.
- 2d ago First seen · 136 lines · 49 tokens per session scan A 13d195a2cc67
deep-research is a skill published in the GitHub repository Liyux3/scholar-mcp (2 stars, last pushed 4d ago), licensed Apache-2.0. It adds 49 tokens to every session and 1,356 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 2026-09-07.
Other skills, from other repositories
scholarqa-research
Perform evidence-first scholarly research, multi-paper synthesis, and Scideator-style facet-based research ideation with the ScholarQA CLI or Semantic Scholar MCP tools. Use when Codex must answer a research question from academic literature, produce a cited literature review, compare findings, verify scholarly…
noodle-biomedical-literature-discovery
Find, inspect, compare, and traverse public biomedical research literature. Use for PubMed or scholarly paper search, publication details, PMID/DOI/PMCID lookup, related papers, citation paths, semantic literature neighborhoods, corpus coverage, or questions asking what research exists about a gene, variant…
noodle-biomedical-literature-discovery-mcp
Select Noodle Biomedical Literature Discovery MCP from Biorouter for public biomedical paper search, PMID DOI or PMCID lookup, publication inspection, related papers, citation or semantic graph traversal, and corpus metadata even when the user does not know the Noodle name.
paper-search
Search, download, and read academic papers from 20+ sources (arXiv, PubMed, Semantic Scholar, CrossRef, etc). Use when the user asks to find papers, search for research, look up academic literature, download a paper PDF, or extract text from a paper.
ai-research-reproduction
Rigor Reproduce compatible skill slug for README-first deep learning repository reproduction. Use when the user wants an end-to-end, minimal-trustworthy flow that reads the repository first, selects the smallest documented inference or evaluation target, coordinates intake, setup, trusted execution, optional trusted…
ai-research-explore
Rigor Explore compatible skill slug for meaningful and potentially novel deep learning research candidates. Use when the researcher has chosen the task family, dataset, benchmark, evaluation method, provided SOTA references, and wants candidate-only exploration on top of currentresearch with auditable repo…