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 skills add ItamarZand88/CLI-Anything-WEB --skill notebooklm-cligit clone --depth 1 https://github.com/ItamarZand88/CLI-Anything-WEBWrote 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/itamarzand88/cli-anything-web/notebooklm-cli)<a href="https://agentmods.dev/skills/itamarzand88/cli-anything-web/notebooklm-cli"><img src="https://agentmods.dev/badge/skills/itamarzand88/cli-anything-web/notebooklm-cli/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/itamarzand88/cli-anything-web/notebooklm-cli"><img src="https://agentmods.dev/badge/skills/itamarzand88/cli-anything-web/notebooklm-cli.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00109 | $0.01000 |
| Opus 5.5 | $0.00044 | $0.00400 |
| Sonnet 5.5 | $0.00022 | $0.00200 |
| Haiku 4.5 | $0.00011 | $0.00100 |
Grade A, and why
notebooklm-cli 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 1mo 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 — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.
cli-web-notebooklm
Manage NotebookLM notebooks, sources, chat, and artifact generation. Requires Google auth (auth login).
Install: pip install "cli-web-notebooklm[auth]", then playwright install chromium.
Commands
| Command | Purpose | Key options |
|---|---|---|
notebooks list|create|get|rename|delete |
Manage notebooks | --title, --emoji; delete needs --confirm; IDs may be partial |
use NOTEBOOK_ID / status |
Set/show persistent notebook context | once set, --notebook is optional everywhere |
sources list|get|delete |
Manage sources | --notebook ID, delete needs --confirm |
sources add-url --url URL |
Add a web page as source | |
sources add-text --title T --text "..." |
Add pasted text as source | |
chat ask --query "..." |
Ask the notebook a question | --notebook ID |
artifacts generate --type TYPE |
Generate an artifact | types: audio, video, mindmap, study-guide, briefing, faq, quiz, infographic, slide-deck, data-table; --wait (poll until done), --retry N, -o FILE |
artifacts list |
All artifacts with status | |
artifacts download ARTIFACT_ID -o FILE |
Download a completed artifact | briefing/study-guide → .md, audio/video → .mp4, slide-deck → .pdf/.pptx, data-table → .csv, quiz/faq → .json; mindmap content is inline |
artifacts generate-notes / artifacts list-audio-types |
Study notes; audio overview formats | |
whoami |
Current Google account |
Examples
# Build a research notebook end to end
cli-web-notebooklm notebooks create --title "Research" --json
cli-web-notebooklm use <id-from-above>
cli-web-notebooklm sources add-url --url https://example.com/paper --json
sleep 10 # sources need a few seconds of processing
# Ask a grounded question
cli-web-notebooklm chat ask --query "What methodology was used?" --json
# Generate a briefing doc and save it
cli-web-notebooklm artifacts generate --type briefing --wait -o briefing.md --json
# Generate a podcast-style audio overview (5-10 min), then download
cli-web-notebooklm artifacts generate --type audio --wait --json
cli-web-notebooklm artifacts download <artifact-id> -o podcast.mp4 --json
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.
- 1mo ago First seen · 71 lines · 109 tokens per session scan A 9251f224b804
notebooklm-cli is a skill published in the GitHub repository ItamarZand88/CLI-Anything-WEB (233 stars, last pushed yesterday), licensed MIT. It adds 109 tokens to every session and 1,000 once invoked, about $0.0004 per session on Opus 5.5. 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 2026-08-30.
Other skills, from other repositories
modelcontextprotocol-python-sdk-context
Answers questions about the official Model Context Protocol (MCP) Python SDK (mcp package on PyPI, modelcontextprotocol/python-sdk on GitHub). Tracks the main branch (v2 pre-alpha — MCPServer/snakecase/constructor-on handlers). Use when working with MCP servers or clients in Python, debugging v1→v2 migrations, or…
string-algorithms
Reference for string algorithm patterns — KMP, Z-function, Rabin-Karp, Manacher's, string hashing, suffix arrays, and Aho-Corasick. Covers recognition signals, core ideas, Python templates, edge cases, and common mistakes for each technique.
python-syntax-tutor
A Python syntax tutor that explains unfamiliar language features in the code where they appear. Python is a programming language; examples include decorators, async code, generators, and type hints.
teach
Pedagogical companion to /no-surrender. Builds engagement on identified gaps via Socratic prompts. Does NOT write engagement — only /no-surrender does. Gated by surrender.enabled in vault.yaml.
no-surrender
Probe the user's grip on a vault claim across mechanism / implications / falsifiability / bounds axes. Updates the claim's engagement vector. The only verb that writes engagement. Gated by surrender.enabled in vault.yaml.
aget-create-rubric
Create scoring rubrics with domain-adaptive structure, extreme anchoring, and governed storage. ADR-008 Generator level for rubric creation.