process-paper

A command that takes one arXiv research paper and creates a NotebookLM notebook from it, then generates a slide deck. arXiv is an online repository where researchers share academic papers.

In plain words
What is it for?
Use it with an arXiv ID or URL to create a notebook and slides, optionally adding an audio overview or choosing a detailed or presenter-style deck.
Why use it?
It turns a paper into a NotebookLM workspace and presentation without requiring you to set up the source and slide generation yourself.

Command

Install

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.

agentmods
npx agentmods add commands/minihellboy/notebooklm-papers-plugin/process-paper
Clone the repo
git clone --depth 1 https://github.com/minihellboy/notebooklm-papers-plugin
Per session 16 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 400 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00016 $0.00400
Opus 5 $0.00008 $0.00200
Sonnet 5 $0.00003 $0.00080
Haiku 4.5 $0.00002 $0.00040

Measured yesterday against content hash 437a081a566b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

process-paper 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.

commands/process-paper.md · 46 lines

What it actually says

Process Single Paper

Creates a NotebookLM notebook for a single arXiv paper and generates a slide deck.

Arguments

Parse from: $ARGUMENTS

Expected formats:

  • arXiv ID: 2601.02151
  • arXiv URL: https://arxiv.org/abs/2601.02151
  • arXiv PDF URL: https://arxiv.org/pdf/2601.02151.pdf

Options:

  • --audio: Also generate audio overview
  • --name "Custom Name": Custom notebook name (otherwise uses paper title)
  • --detailed or --presenter: Slide format

Workflow

  1. Parse Input: Extract arXiv ID from the provided argument
  2. Get Browser Context: Use mcp__claude-in-chrome__tabs_context_mcp
  3. Create Notebook: Navigate to NotebookLM and create new notebook
  4. Add Source: Add the arXiv PDF as a website source
  5. Wait for Processing: Wait for NotebookLM to process the PDF
  6. Generate Slides: Click Slide Deck and wait for generation
  7. Generate Audio (if --audio): Click Audio Overview and generate
  8. Report: Provide links to notebook and generated assets

Example Usage

/notebooklm-papers:process-paper 2601.02151
/notebooklm-papers:process-paper https://arxiv.org/abs/2601.02151 --audio
/notebooklm-papers:process-paper 2601.02151 --name "My Research Paper"

Output

Report the NotebookLM notebook URL and status of generated assets.

Changes

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.

  1. yesterday First seen · 46 lines · 16 tokens per session scan A 437a081a566b

Subscribe to this mod's changes

process-paper is a command published in the GitHub repository minihellboy/notebooklm-papers-plugin (2 stars, last pushed 7mo ago), licensed MIT. It adds 16 tokens to every session and 400 once invoked, about $0.0001 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.