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.
git clone --depth 1 https://github.com/gfsaaser24/notebooklm-coworkWrote 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/commands/gfsaaser24/notebooklm-cowork/notebook-studio)<a href="https://agentmods.dev/commands/gfsaaser24/notebooklm-cowork/notebook-studio"><img src="https://agentmods.dev/badge/commands/gfsaaser24/notebooklm-cowork/notebook-studio/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/commands/gfsaaser24/notebooklm-cowork/notebook-studio"><img src="https://agentmods.dev/badge/commands/gfsaaser24/notebooklm-cowork/notebook-studio.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 | $0.00015 | $0.00330 |
| Opus 5 | $0.00008 | $0.00165 |
| Sonnet 5 | $0.00003 | $0.00066 |
| Haiku 4.5 | $0.00002 | $0.00033 |
Grade A, and why
notebook-studio 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.
What it actually says
The user wants to create a NotebookLM studio artifact. Request: $ARGUMENTS
Available artifact types:
- audio — AI podcast/discussion (formats: deep_dive, brief, critique, debate)
- video — AI-generated video (formats: explainer, brief, cinematic)
- infographic — visual summary
- slide_deck — presentation (formats: detailed, presenter)
- report — written document (briefing, study guide, blog post)
- flashcards — study cards (difficulty: easy, medium, difficult)
- quiz — assessment questions (configurable count)
- data_table — structured data extraction
- mind_map — visual topic organization
Steps:
- If the user didn't specify a notebook, call
notebook_list()and ask which one. - Determine the artifact type from the user's request.
- Ask about type-specific options (format, length, difficulty, etc.) if not specified.
- Optionally ask if they want to focus on specific sources within the notebook.
- Create with
studio_create(notebook_id, artifact_type, confirm=True, ...). - Poll
studio_status(notebook_id)until the artifact is ready. - Ask if the user wants to download the artifact. If yes, use
download_artifact(). - For slide decks, mention they can revise individual slides with
studio_revise().
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 · 29 lines · 0 tokens per session scan A b1fe7adb2823
notebook-studio is a command published in the GitHub repository gfsaaser24/notebooklm-cowork (10 stars, last pushed 2mo ago), licensed MIT. It adds 15 tokens to every session and 330 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.
Other commands, from other repositories
products-creation
Product Creation - digital products, courses, templates across all FrankX domains.
start-3-1-2
Module 3.1.2: Understanding the Basics - Parameters, aspect ratios, resolution, and iteration.
start-1-2
A Japanese-language lesson about advanced banner creation for Instagram and Facebook.
start-1-3
A beginner lesson on creating and editing images with Nano Banana, an image-generation and editing tool.
start-1-2.en
Welcome to Lesson 1-2: Advanced Banners (Instagram, Facebook)!
explain-video
Bridge workflow — analyze content with Gemini research tools, then synthesize an explainer video.