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 agentmods add skills/minihellboy/notebooklm-papers-plugin/paper-researchnpx skills add minihellboy/notebooklm-papers-plugin --skill paper-researchgit clone --depth 1 https://github.com/minihellboy/notebooklm-papers-pluginWrote 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/minihellboy/notebooklm-papers-plugin/paper-research)<a href="https://agentmods.dev/skills/minihellboy/notebooklm-papers-plugin/paper-research"><img src="https://agentmods.dev/badge/skills/minihellboy/notebooklm-papers-plugin/paper-research.svg" alt="Measured on agentmods" 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 | $0.00048 | $0.00666 |
| Opus 5 | $0.00024 | $0.00333 |
| Sonnet 5 | $0.00010 | $0.00133 |
| Haiku 4.5 | $0.00005 | $0.00067 |
Grade A, and why
paper-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 3d 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 — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Paper Research Skill
This skill helps users research and analyze academic papers using NotebookLM.
When to Use This Skill
Activate this skill when the user:
- Wants to understand or summarize a research paper
- Mentions an arXiv paper or ID
- Asks about creating slides or presentations from papers
- Wants to compare multiple research papers
- Requests audio explanations of technical content
- Mentions NotebookLM, NotebookLM notebooks, or paper notebooks
Capabilities
Paper Processing
- Create NotebookLM notebooks from arXiv papers
- Add papers as sources to existing notebooks
- Generate slide decks from paper content
- Create audio overviews (podcast-style discussions)
Paper Discovery
- Search arXiv by topic, author, or category
- Fetch trending papers from Hugging Face Daily Papers
- List papers from specific date ranges
Analysis Support
- Summarize paper contributions and methodology
- Compare multiple papers on the same topic
- Extract key findings and implications
Required Tools
This skill requires the claude-in-chrome MCP server for browser automation:
mcp__claude-in-chrome__tabs_context_mcp- Get browser contextmcp__claude-in-chrome__navigate- Navigate to URLsmcp__claude-in-chrome__read_page- Read page contentmcp__claude-in-chrome__find- Find UI elementsmcp__claude-in-chrome__computer- Click, type, interact
Workflow Patterns
Single Paper to Slides
- Get arXiv ID from user
- Create NotebookLM notebook
- Add arXiv PDF as source
- Generate slide deck
- Provide notebook link
Daily Paper Digest
- Fetch top papers from HuggingFace
- Create notebooks for each
- Generate slides for all
- Provide summary with links
Paper Comparison
- Create single notebook
- Add multiple papers as sources
- Ask NotebookLM to compare
- Generate comparison slides
Best Practices
- Always confirm arXiv IDs are valid before processing
- Use descriptive notebook names for easy identification
- Wait for source processing before generating content
- Track progress with todo list for batch operations
- Provide clear status updates during long operations
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.
- 3d ago First seen · 89 lines · 48 tokens per session scan A 2455b45d45e3
paper-research is a skill published in the GitHub repository minihellboy/notebooklm-papers-plugin (2 stars, last pushed 7mo ago), licensed MIT. It adds 48 tokens to every session and 666 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 2026-08-31.
Other skills, from other repositories
exploratory-data-analysis
Perform bounded, local exploratory analysis of explicitly supported scientific files. Use for redacted CSV/TSV/JSON profiles; optional NumPy, HDF5, FASTA/FASTQ, and basic image metadata inspection; missingness/leakage audits; outlier and transformation sensitivity; and rigorous EDA report scaffolds. Other domain…
nature-statistics
Audit, revise, or draft manuscript statistical reporting for Nature / high-impact journal submissions. Use when the user asks to check statistical analysis sections, p values, confidence intervals, sample size, biological versus technical replicates, randomization, blinding, multiple-comparison correction, model…
evaluating-with-leakage-gates
Evaluate an OpenMed de-identification or clinical NER model against the leakage-first release gates G1a through G8, which gate releases on residual PHI leakage rather than on F1. Use when the user wants to run the OpenMed eval harness on a synthetic golden set, decide whether a de-id model is RELEASABLE or…
mapping-to-snomed
Maps clinical concept spans extracted by OpenMed to SNOMED CT concepts through a USER-SUPPLIED terminology server (the user's own Ontoserver, Snowstorm, or UMLS/UTS), never a bundled vocabulary. Use when the user wants to code findings, disorders, procedures, body structures, or substances to SNOMED CT, run an ECL…
mixed-precision
Use FP16/BF16 mixed precision to accelerate training and reduce memory. Use when optimizing GPU performance.
indication-dossier
Build a source-backed biomedical indication dossier. Use when a research task asks for disease biology, target rationale, patient segmentation, biomarkers, trials, drugs, competitive landscape, or translational evidence.