notebook-research

notebook-research is a command for Claude Code from gfsaaser24/notebooklm-cowork. It costs 10 tokens per session (238 once invoked), scanned A, original, MIT.

A command for researching a topic through NotebookLM using web search or Google Drive, then importing selected results into a notebook.

In plain words
What is it for?
It is for running fast or deep research tasks, reviewing discovered sources, and adding chosen sources to a NotebookLM notebook.
Why use it?
It organizes the research process, including source selection, progress checks, and importing results, instead of requiring these steps manually.

Command for Claude Code

Written for Claude Code: argument-hint in frontmatter.

Part of the notebooklm-cowork plugin — 1 skill, 5 commands, 1 MCP server shipped together

Good fit It is for running fast or deep research tasks, reviewing discovered sources, and adding chosen sources to a NotebookLM notebook.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/gfsaaser24/notebooklm-cowork/notebook-research
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.

Clone the repo
git clone --depth 1 https://github.com/gfsaaser24/notebooklm-cowork

Made for: Claude Code.

Or install notebooklm-cowork, the plugin that ships this one along with the rest of its 1 skill, 5 commands, 1 MCP server.

Wrote 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.

agentmods badge for notebook-research

README.md
[![agentmods](https://agentmods.dev/badge/commands/gfsaaser24/notebooklm-cowork/notebook-research/github.svg)](https://agentmods.dev/commands/gfsaaser24/notebooklm-cowork/notebook-research)
Your own site
<a href="https://agentmods.dev/commands/gfsaaser24/notebooklm-cowork/notebook-research"><img src="https://agentmods.dev/badge/commands/gfsaaser24/notebooklm-cowork/notebook-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.

agentmods 80×15 button for notebook-research

Your own site · 80×15
<a href="https://agentmods.dev/commands/gfsaaser24/notebooklm-cowork/notebook-research"><img src="https://agentmods.dev/badge/commands/gfsaaser24/notebooklm-cowork/notebook-research.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 10 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 238 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00010 $0.00238
Opus 5 $0.00005 $0.00119
Sonnet 5 $0.00002 $0.00048
Haiku 4.5 $0.00001 $0.00024

Measured 10d ago against content hash 8946b96efc38, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

notebook-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 10d 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.

commands/notebook-research.md · 21 lines

What it actually says

The user wants to research a topic using NotebookLM's research feature. Topic: $ARGUMENTS

Steps:

  1. Ask the user (if not specified):
    • Source: web search or Google Drive?
    • Mode: fast (~30 seconds) or deep (~5 minutes)?
    • Which notebook to import results into? (list notebooks if needed)
  2. Start research with research_start(query="$ARGUMENTS", source=..., mode=...).
  3. Poll with research_status(notebook_id, task_id=...) until complete. Deep runs may take up to ~15 minutes (default poll window is now 900s).
    • Shortcut: pass auto_import=True to import all discovered sources automatically on completion, then skip steps 4-6.
  4. Present the discovered sources to the user with titles and descriptions.
  5. Ask which sources to import (all or specific indices).
  6. Import with research_import(notebook_id, task_id, source_indices=...).
  7. Confirm the sources were added to the notebook.
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. 10d ago First seen · 21 lines · 10 tokens per session scan A 8946b96efc38

Subscribe to this mod's changes

notebook-research is a command published in the GitHub repository gfsaaser24/notebooklm-cowork (10 stars, last pushed 2mo ago), licensed MIT. It adds 10 tokens to every session and 238 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 2026-08-30.