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 agentmods add skills/platdrag/notebooklm-claude-skill/setupnpx skills add platdrag/notebookLM-claude-skill --skill setupgit clone --depth 1 https://github.com/platdrag/notebookLM-claude-skillWrote 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/platdrag/notebooklm-claude-skill/setup)<a href="https://agentmods.dev/skills/platdrag/notebooklm-claude-skill/setup"><img src="https://agentmods.dev/badge/skills/platdrag/notebooklm-claude-skill/setup.svg" alt="Measured on agentmods" 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 | $0.00029 | $0.01398 |
| Opus 5 | $0.00015 | $0.00699 |
| Sonnet 5 | $0.00006 | $0.00280 |
| Haiku 4.5 | $0.00003 | $0.00140 |
Grade A, and why
setup 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.
How it starts
The opening of the file, as written. The whole thing — 173 lines — stays where its author put it; the contents beside it link to each section on GitHub.
NotebookLM Setup
This skill guides the user through installing and configuring the notebooklm-py CLI tool so that /notebooklm:query can query their NotebookLM notebooks.
Step 1: Check if notebooklm-py is Already Installed
notebooklm --version
- If the command succeeds, report the version and skip to Step 3.
- If the command is not found, proceed to Step 2.
Step 2: Install notebooklm-py
Ask the user which installation method they prefer:
Option A — Lightweight (recommended if you can export browser cookies manually):
pip install notebooklm-py
This installs the CLI and all query functionality. Authentication must be handled by manually exporting cookies from an existing browser session (see Step 4, Option B).
Option B — With browser-based login:
pip install "notebooklm-py[browser]"
playwright install chromium
This adds Playwright, which enables the notebooklm login command. It opens a dedicated Chromium instance to capture Google session cookies — regular browsers don't expose cookies to external programs, so Playwright's own browser is needed for automated cookie extraction.
If pip fails, try pip3 or suggest the user activate the appropriate Python virtual environment. pipx install notebooklm-py is also an option for global CLI tools.
Verify installation:
notebooklm --version
Step 3: Check Authentication Status
notebooklm auth check --json
- If auth is valid, report the status and skip to Step 5.
- If auth is invalid or missing, proceed to Step 4.
Step 4: Authenticate
Offer two authentication methods:
Option A — Browser login (requires [browser] extra and Playwright):
Tell the user:
Please run this command in your terminal (not here — it opens a browser window):
notebooklm login
- A Chromium window will open to the NotebookLM page
- Log in with your Google account
- Once the page loads, switch back to your terminal and press ENTER
Come back here when you're done.
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.
- 5d ago First seen · 173 lines · 29 tokens per session scan A 6faa936b7a25
setup is a skill published in the GitHub repository platdrag/notebookLM-claude-skill (5 stars, last pushed 6mo ago), licensed MIT. It adds 29 tokens to every session and 1,398 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 2026-08-31.
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…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…