notebooklm

notebooklm is a skill for Claude Code, Codex from rulords/notebooklm-mcp-multiprofile. It costs 91 tokens per session (1,746 once invoked), scanned A, original, MIT.

An orchestration skill for Google NotebookLM, a service for working with source-based notebooks. It supports notebooks, sources, research, generated study materials, notes, and Workspace export across multiple Google profiles.

In plain words
What is it for?
Use it to manage notebooks and sources, run research, create audio, video, slides, reports, flashcards, quizzes, or mind maps, edit notes, and export work to Google Workspace.
Why use it?
It handles the coordination details that make these operations reliable, including account selection, waiting for background jobs, authentication renewal, and Drive synchronization.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

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 skills/rulords/notebooklm-mcp-multiprofile/docs
Any agent
npx skills add rulords/notebooklm-mcp-multiprofile --skill docs
Clone the repo
git clone --depth 1 https://github.com/rulords/notebooklm-mcp-multiprofile

Made for: Claude Code, Codex.

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 notebooklm

README.md
[![agentmods](https://agentmods.dev/badge/skills/rulords/notebooklm-mcp-multiprofile/docs.svg)](https://agentmods.dev/skills/rulords/notebooklm-mcp-multiprofile/docs)
Your own site
<a href="https://agentmods.dev/skills/rulords/notebooklm-mcp-multiprofile/docs"><img src="https://agentmods.dev/badge/skills/rulords/notebooklm-mcp-multiprofile/docs.svg" alt="Measured on agentmods" height="20"></a>
Per session 91 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,746 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 5.1 $0.00091 $0.01746
Opus 5 $0.00046 $0.00873
Sonnet 5 $0.00018 $0.00349
Haiku 4.5 $0.00009 $0.00175

Measured 5d ago against content hash 119cde29c1fa, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

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 5d 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.

docs/SKILL.md · 143 lines

How it starts

The opening of the file, as written. The whole thing — 143 lines — stays where its author put it; the contents beside it link to each section on GitHub.

NotebookLM MCP — Skill de Orquestación

Reglas de Operación (leer siempre primero)

  1. Multi-perfil: Las herramientas se llaman mcp_notebooklm_[PERFIL]_[herramienta]. Elegir el perfil correcto según el contexto del usuario. Si es ambiguo, preguntar.
  2. Async obligatorio: research_start y studio_create son asíncronos. SIEMPRE hacer poll con research_status / studio_status hasta status="completed". Nunca asumir completado inmediato.
  3. Confirmación: Todas las herramientas _create destructivas y _delete requieren confirm=True. Si el usuario dio instrucción clara, proceder sin preguntar de nuevo.
  4. Auth expirada: Si cualquier herramienta retorna RPC Error 16 o Authentication expired, ejecutar refresh_auth() del perfil afectado. Si sigue fallando, informar al usuario que debe renovar cookies con inject_profile.py.
  5. Drive sync: Antes de consultar notebooks con fuentes de Drive, ejecutar source_list_drive y si hay needs_sync=True, ejecutar source_sync_drive(confirm=True).

Referencia de Herramientas

Notebooks

Herramienta Descripción
notebook_list Lista todos los notebooks. Usar max_results para limitar.
notebook_create Crea notebook vacío. Parámetro: title.
notebook_get Detalles y lista de fuentes de un notebook.
notebook_describe Resumen IA del contenido + temas sugeridos.
notebook_rename Renombrar. Usar proactivamente si el título es genérico.
notebook_delete Eliminar permanentemente. Requiere confirm=True.
notebook_query Pregunta a la IA basada SOLO en las fuentes del notebook. Usar conversation_id para follow-up.
chat_configure Configurar estilo de respuesta (goal, response_length).

Fuentes

Herramienta Descripción
source_add Agregar fuente. source_type: url, text, drive, file. Usar wait=True para esperar procesamiento.
source_describe Resumen IA de una fuente específica.
source_get_content Texto crudo de la fuente (sin IA, más rápido).
source_delete Eliminar fuente. Requiere confirm=True.
source_list_drive Listar fuentes de Drive con estado de frescura.
source_sync_drive Sincronizar fuentes desactualizadas. Requiere confirm=True.

Read the full file on GitHub · 143 lines

Files

What ships with it

4 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.

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. 5d ago First seen · 143 lines · 91 tokens per session scan A 119cde29c1fa

Subscribe to this mod's changes

notebooklm is a skill published in the GitHub repository rulords/notebooklm-mcp-multiprofile (0 stars, last pushed 4mo ago), licensed MIT. It adds 91 tokens to every session and 1,746 once invoked, about $0.0005 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.

Related

Other skills, from other repositories