Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/julianobarbosa/claude-code-skillsnpx agentmods add skills/julianobarbosa/claude-code-skills/notebooklmWrote 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/julianobarbosa/claude-code-skills/notebooklm)<a href="https://agentmods.dev/skills/julianobarbosa/claude-code-skills/notebooklm"><img src="https://agentmods.dev/badge/skills/julianobarbosa/claude-code-skills/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/julianobarbosa/claude-code-skills/notebooklm"><img src="https://agentmods.dev/badge/skills/julianobarbosa/claude-code-skills/notebooklm.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Rogue Agent · line 4 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
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 | $0.00150 | $0.02380 |
| Opus 5 | $0.00075 | $0.01190 |
| Sonnet 5 | $0.00030 | $0.00476 |
| Haiku 4.5 | $0.00015 | $0.00238 |
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 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.
How it starts
The opening of the file, as written. The whole thing — 291 lines — stays where its author put it; the contents beside it link to each section on GitHub.
NotebookLM Automation
Unofficial Python CLI and API for Google NotebookLM (notebooklm-py). Provides full programmatic access including capabilities the web UI doesn't expose.
Prerequisites
- Python 3.10+
- Google account with NotebookLM access
- One-time browser login via Playwright
Installation
# Install with browser login support
pip install "notebooklm-py[browser]"
playwright install chromium
# Linux only: also run
playwright install-deps chromium
Authentication
First-time setup requires browser login:
notebooklm login
# Opens Chromium → sign into Google → press Enter when done
# Session saved to ~/.notebooklm/storage_state.json
Check auth status: notebooklm auth check --test
For headless/CI environments, copy storage_state.json from a local machine or set NOTEBOOKLM_AUTH_JSON env var.
Environment Variables
| Variable | Description | Default |
|---|---|---|
NOTEBOOKLM_HOME |
Config directory | ~/.notebooklm |
NOTEBOOKLM_AUTH_JSON |
Inline auth JSON (CI/CD) | — |
NOTEBOOKLM_LOG_LEVEL |
DEBUG/INFO/WARNING/ERROR |
WARNING |
NOTEBOOKLM_DEBUG_RPC |
Enable RPC debug (1) |
false |
Core Workflow
The typical workflow is: create notebook → add sources → generate content → download.
1. Notebook Management
notebooklm create "My Research" # Create notebook
notebooklm list # List all notebooks
notebooklm use <id> # Set active notebook (supports partial ID)
notebooklm summary # AI summary of current notebook
notebooklm rename "New Title" # Rename
notebooklm delete <id> # Delete
2. Adding Sources
Sources are auto-detected by type:
notebooklm source add "https://example.com/article" # URL
notebooklm source add "https://youtube.com/watch?v=..." # YouTube
notebooklm source add ./document.pdf # File (PDF, MD, DOCX, TXT, audio, video, images)
notebooklm source add-drive <drive-file-id> "Title" # Google Drive
notebooklm source add-research "climate policy" --mode deep --import-all # Research agent
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 · 291 lines · 150 tokens per session scan A 5bd3ceb04c9c
notebooklm is a skill published in the GitHub repository julianobarbosa/claude-code-skills (10 stars, last pushed 14d ago), licensed MIT. It adds 150 tokens to every session and 2,380 once invoked, about $0.0007 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.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…