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 DorianSchlede/nexus-template --skill notebooklmgit clone --depth 1 https://github.com/DorianSchlede/nexus-templateWrote 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/dorianschlede/nexus-template/notebooklm)<a href="https://agentmods.dev/skills/dorianschlede/nexus-template/notebooklm"><img src="https://agentmods.dev/badge/skills/dorianschlede/nexus-template/notebooklm/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/dorianschlede/nexus-template/notebooklm"><img src="https://agentmods.dev/badge/skills/dorianschlede/nexus-template/notebooklm.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 | $0.00016 | $0.00458 |
| Opus 5 | $0.00008 | $0.00229 |
| Sonnet 5 | $0.00003 | $0.00092 |
| Haiku 4.5 | $0.00002 | $0.00046 |
Grade A, and why
notebooklm 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 8d 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
NotebookLM Integration
Complete integration for Google NotebookLM Enterprise API.
Quick Start
Say any of these:
- "create notebook [title]"
- "list my notebooks"
- "add [url] to notebook"
- "upload [file] to notebook"
- "create audio overview"
- "generate podcast"
Available Operations
Notebooks
- Create notebook - Create a new notebook
- List notebooks - List recently viewed notebooks
- Get notebook - Get notebook details
- Delete notebooks - Delete one or more notebooks
- Share notebook - Share with other users
Sources
- Add sources - Add from web URL, YouTube, Google Drive, or text
- Upload file - Upload PDF, TXT, MD, DOCX, audio, images
- Get source - Get source details
- Delete sources - Remove sources from notebook
Audio Overview
- Create audio - Generate podcast-style audio overview
- Delete audio - Remove audio overview
Setup Required
NotebookLM Enterprise requires:
- Google Cloud project with NotebookLM Enterprise enabled
- gcloud CLI installed and authenticated
- Project number in
.env
Run setup:
uv run python 00-system/skills/notebooklm/notebooklm-master/scripts/setup_notebooklm.py
Architecture
notebooklm/
├── notebooklm-master/ # Shared resources (DO NOT load directly)
├── notebooklm-connect/ # Meta-skill (entry point)
├── notebooklm-create-notebook/
├── notebooklm-list-notebooks/
├── notebooklm-get-notebook/
├── notebooklm-delete-notebooks/
├── notebooklm-share-notebook/
├── notebooklm-add-sources/
├── notebooklm-upload-file/
├── notebooklm-get-source/
├── notebooklm-delete-sources/
├── notebooklm-create-audio/
└── notebooklm-delete-audio/
Version: 1.0 Created: 2025-12-27
What ships with it
22 files 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.
- notebooklm-add-sources/scripts/add_sources.py 4.3 KB runs code
- notebooklm-connect/SKILL.md 5.5 KB
- notebooklm-create-audio/scripts/create_audio.py 3.1 KB runs code
- notebooklm-create-notebook/scripts/create_notebook.py 1.6 KB runs code
- notebooklm-delete-audio/scripts/delete_audio.py 1.9 KB runs code
- notebooklm-delete-notebooks/scripts/delete_notebooks.py 2.2 KB runs code
- notebooklm-delete-sources/scripts/delete_sources.py 2.5 KB runs code
- notebooklm-get-notebook/scripts/get_notebook.py 1.9 KB runs code
- notebooklm-get-source/scripts/get_source.py 2.0 KB runs code
- notebooklm-list-notebooks/scripts/list_notebooks.py 1.8 KB runs code
- notebooklm-master/references/api-reference.md 4.8 KB
- notebooklm-master/references/authentication.md 4.3 KB
- notebooklm-master/references/error-handling.md 3.8 KB
- notebooklm-master/references/setup-guide.md 3.0 KB
- notebooklm-master/scripts/check_notebooklm_config.py 9.3 KB runs code
- notebooklm-master/scripts/notebooklm_client.py 5.8 KB runs code
- notebooklm-master/scripts/setup_notebooklm.py 6.7 KB runs code
- notebooklm-master/SKILL.md 4.4 KB
- notebooklm-share-notebook/scripts/share_notebook.py 2.1 KB runs code
- notebooklm-upload-file/scripts/upload_file.py 3.6 KB runs code
- pyproject.toml 207 B
- uv.lock 30 KB
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.
- 8d ago First seen · 74 lines · 16 tokens per session scan A 3093daa426ce
notebooklm is a skill published in the GitHub repository DorianSchlede/nexus-template (8 stars, last pushed 7mo ago), licensed MIT. It adds 16 tokens to every session and 458 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 2026-09-03.
Other skills, from other repositories
pydicom
Use pydicom to read, inspect, write, transform, and safely preflight local DICOM datasets and pixel data. Applies to DICOM metadata, transfer syntaxes, compression plugins, frames, private elements, JSON, and bounded de-identification review.
foundry-hosted-agent-validation
Step-by-step process for validating a Python Foundry hosted agent sample (under python/samples/04-hosting/foundry-hosted-agents/) end to end — running it locally (native runtime and azd ai agent run) and after deploying it to an Azure AI Foundry project with azd. Use this when asked to validate a hosted agent sample.
skill-doc-delivery
Convert markdown to DOCX, PPTX, XLSX, PDF office documents — use when you need exportable deliverables.
pdf-extract-create-workflow
Complete PDF lifecycle: download, extract, and generate structured documents with reportlab.
document-direct-python
Use direct Python execution for reliable document creation including spreadsheets, PDFs, and structured reports.
parse-document
Convert a PDF, scan, image of a page, or office file to clean markdown through the connected Superlinked MCP edge, so the source document is not read into model context directly. Use when the user asks to read, parse, OCR, extract from, summarize, or answer questions about a document.