query

query is a skill for Claude Code from platdrag/notebookLM-claude-skill. It costs 26 tokens per session (1,307 once invoked), scanned A, original, MIT.

A way to ask questions of Google NotebookLM notebooks using the documents uploaded there. It returns answers grounded in those sources and supports follow-up conversations.

In plain words
What is it for?
Use it to ask domain-specific questions, explore uploaded documents, and continue a source-grounded conversation about their contents.
Why use it?
It lets you investigate a specific document collection without relying only on general knowledge. It checks that the NotebookLM command-line tool is installed and authenticated before querying.

Skill for Claude Code

Written for Claude Code: disable-model-invocation in frontmatter.

Part of the notebooklm plugin — 2 skills shipped together

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/platdrag/notebooklm-claude-skill/query
Any agent
npx skills add platdrag/notebookLM-claude-skill --skill query
Clone the repo
git clone --depth 1 https://github.com/platdrag/notebookLM-claude-skill

Made for: Claude Code.

Or install notebooklm, the plugin that ships this one along with the rest of its 2 skills.

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 query

README.md
[![agentmods](https://agentmods.dev/badge/skills/platdrag/notebooklm-claude-skill/query.svg)](https://agentmods.dev/skills/platdrag/notebooklm-claude-skill/query)
Your own site
<a href="https://agentmods.dev/skills/platdrag/notebooklm-claude-skill/query"><img src="https://agentmods.dev/badge/skills/platdrag/notebooklm-claude-skill/query.svg" alt="Measured on agentmods" height="20"></a>
Per session 26 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,307 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 $0.00026 $0.01307
Opus 5 $0.00013 $0.00654
Sonnet 5 $0.00005 $0.00261
Haiku 4.5 $0.00003 $0.00131

Measured 6d ago against content hash 8360a1db58e8, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

query 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 6d 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.

skills/query/SKILL.md · 145 lines

How it starts

The opening of the file, as written. The whole thing — 145 lines — stays where its author put it; the contents beside it link to each section on GitHub.

NotebookLM Query

You are using NotebookLM as a knowledge base. Your job is to query the user's NotebookLM notebook for domain-specific knowledge and return grounded, cited answers.

Prerequisites

The notebooklm-py CLI must be installed and authenticated. If any step below fails with a missing command or auth error, tell the user to run /notebooklm:setup first.

Execution Steps

Step 1: Parse the Request

The user's input is: $ARGUMENTS

Extract:

  • query: The domain question to ask (everything before --notebook flag, or the entire input if no flag)
  • notebook_name: Optional. Value after --notebook flag. Defaults to null.

If $ARGUMENTS is empty or missing, ask the user what they want to know.

Step 2: Verify Authentication

Run this command to check auth status before doing anything else:

notebooklm auth check --json
  • If exit code is 0 and output shows valid auth, proceed to Step 3.

  • If the notebooklm command is not found, tell the user to run /notebooklm:setup.

  • If auth check fails, tell the user:

    NotebookLM authentication has expired. Run notebooklm login in your terminal to re-authenticate (requires a browser).

    Then stop — do not proceed until auth is resolved.

Step 3: Determine Target Notebook

If --notebook <name> was provided:

Read {project-root}/.claude/notebooklm-config.json and look up the notebook name in the notebooks map to get its ID. If found and the ID is valid (not "PASTE_NOTEBOOK_ID_HERE" or null), use that ID and skip to Step 4.

If not found in config, fall through to the interactive selection below.

Otherwise (no --notebook flag, or name not in config):

Read {project-root}/.claude/notebooklm-config.json to check if a defaultNotebook is configured. If a valid default exists, use that notebook's ID and skip to Step 4.

If no default is configured, list available notebooks and let the user choose:

notebooklm list --json

Read the full file on GitHub · 145 lines

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. 6d ago First seen · 145 lines · 26 tokens per session scan A 8360a1db58e8

Subscribe to this mod's changes

query is a skill published in the GitHub repository platdrag/notebookLM-claude-skill (5 stars, last pushed 6mo ago), licensed MIT. It adds 26 tokens to every session and 1,307 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.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

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…

microsoft/ai-agents-for-beginners · 200 tokens

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…

microsoft/vscode · 72 tokens

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.

microsoft/vscode · 53 tokens

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…

microsoft/vscode · 71 tokens

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…

vercel/next.js · 95 tokens