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/knowingdoing/notebooklm-codex/notebooklmnpx skills add knowingdoing/notebooklm-codex --skill notebooklmgit clone --depth 1 https://github.com/knowingdoing/notebooklm-codexWhat 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 | $0.00117 | $0.00694 |
| Opus 5 | $0.00059 | $0.00347 |
| Sonnet 5 | $0.00023 | $0.00139 |
| Haiku 4.5 | $0.00012 | $0.00069 |
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 yesterday.
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 — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.
NotebookLM
Use the local notebooklm CLI when available. If it is missing or not authenticated, help the user install and authenticate it before attempting NotebookLM work.
Detailed setup, command reference, and MCP-server instructions live in references/notebooklm-cli-and-mcp.md. Read that reference when installing, troubleshooting auth, generating artifacts, downloading outputs, or exposing NotebookLM through MCP.
Quick Workflow
- Check whether the CLI exists:
command -v notebooklm notebooklm --help - Check authentication and context:
notebooklm auth check notebooklm list notebooklm status - If no notebook is active, list notebooks and use the requested one:
notebooklm list notebooklm use <notebook_id> - Add sources before asking or generating:
notebooklm source add "https://example.com" notebooklm source add ./document.pdf notebooklm source list - Ask questions or generate artifacts:
notebooklm ask "Summarize the key points" notebooklm generate audio "Focus on the practical takeaways" notebooklm artifact list
Autonomy Rules
Run these without extra confirmation when they directly support the user's request: status checks, auth checks, listing notebooks/sources/artifacts/languages, setting the active notebook, creating notebooks, adding sources, waiting for source/artifact/research completion, read-only chat queries, and read-only conversation history.
Ask before destructive, expensive, or filesystem-writing actions: deleting notebooks or sources, generating long-running artifacts, downloading files, saving an answer as a note, or saving chat history as a note.
Installation
If notebooklm is unavailable, read the setup reference and install notebooklm-py[browser] in ~/.notebooklm-venv with Python 3.10+. Prefer the bundled login script pattern in the reference because NotebookLM auth is browser-based and often needs a persistent Playwright profile.
What ships with it
2 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.
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.
- yesterday First seen · 60 lines · 117 tokens per session scan A 4260bdf669dc
notebooklm is a skill published in the GitHub repository knowingdoing/notebooklm-codex (0 stars, last pushed 2mo ago), licensed MIT. It adds 117 tokens to every session and 694 once invoked, about $0.0006 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
trulens-notebook-execution
Execute and display Jupyter notebooks for TruLens demos and quickstarts.
eli5
Explain research, papers, or technical ideas in plain English with minimal jargon, concrete analogies, and clear takeaways. Use when the user says "ELI5 this", asks for a simple explanation of a paper or research result, wants jargon removed, or asks what something technically dense actually means.
deck-course-module
暖纸背景 + Playfair, 左侧学习目标常驻, 含 MCQ 自测页.
master-yinguang
Use when user asks about 印光大师, 净土, 念佛, 持名念佛, 十念法, 摄耳谛听, 老实念佛, 信愿行, 带业往生, 仗佛慈力, 自力他力, 竖出横超, 往生, 极乐, 阿弥陀佛, 净土三经, 敦伦尽分, 闲邪存诚, 因果报应, 文钞, 一函遍复, or wants teaching in 印光大师 Yinguang's voice. Triggers include "印光"、"文钞"、"老实念佛"、"信愿行"、"带业往生"、"仗佛慈力"、"横超竖出"、"都摄六根"、"净念相继"、"敦伦尽分"、"闲邪存诚"、"因果"、"十念法"、"摄耳谛听"、"一函遍复"、"净土三经"、"往生" — invoke…
explore-unknowns
Guide the user through a quadrant walk that maps the unknowns of a task — open by listing the known knowns, then work through known unknowns, unknown knowns, and unknown unknowns one stage at a time, ending with a complete four-quadrant map in the user's hands. Use when a request is ambiguous or underspecified, the…
obsidian-to-clew-import
Convert an Obsidian vault or wiki-linked markdown graph into a validated structured-learning graph package for Clew. Use when the user wants to inspect a vault, preview whether it imports cleanly, preserve explicit relation markers, choose only the few import settings that matter, and produce a fail-closed package…