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 roomi-fields/notebooklm-mcp --skill notebooklmgit clone --depth 1 https://github.com/roomi-fields/notebooklm-mcpWrote 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/roomi-fields/notebooklm-mcp/notebooklm)<a href="https://agentmods.dev/skills/roomi-fields/notebooklm-mcp/notebooklm"><img src="https://agentmods.dev/badge/skills/roomi-fields/notebooklm-mcp/notebooklm.svg" alt="Measured on agentmods" 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 | $0.00118 | $0.01067 |
| Opus 5 | $0.00059 | $0.00534 |
| Sonnet 5 | $0.00024 | $0.00213 |
| Haiku 4.5 | $0.00012 | $0.00107 |
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 8d 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 — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.
NotebookLM
Overview
NotebookLM answers questions only from the sources uploaded to a notebook,
with inline citations to the exact passages used — no open-web knowledge, so
answers are hallucination-resistant and fully traceable. This skill drives the
@roomi-fields/notebooklm-mcp engine to query notebooks, manage sources, and
generate Studio content, and encodes the patterns that make NotebookLM usable at
research scale (citation formats, the ~50-queries/day quota, batch-to-cache).
Choosing the transport
Two ways reach the same engine — pick per what the session already has:
- notebooklm MCP tools — if tools such as
notebook_ask/source_add/server_health(ormcp__notebooklm__*) are available in the session, call them directly. This is the preferred path and needs no server. - HTTP REST API — otherwise, use the bundled
scripts/nblm.sh, which talks to a running NotebookLM MCP server (defaulthttp://localhost:3000, override withNOTEBOOKLM_SERVER_URL). If no server is reachable, ask the user to start one (npm run start:httpfrom a clone) or to install the MCP.
Both are backed by the same account and session, so the choice is purely about which is already wired up.
Prerequisite: one Google login
NotebookLM needs a signed-in Google session (saved once, reused across runs).
Verify with nblm.sh health (or the server_health tool) — look for
authenticated: true. If not authenticated, run the interactive login in a
terminal (a visible Chrome window opens):
notebooklm-mcp-setup-auth # global install
# or: scripts/nblm.sh auth
Run the login in a terminal rather than through an in-client tool: interactive Google login can take minutes and a stdio client's tool-call timeout may cut it off.
Core tasks
Use scripts/nblm.sh for the REST path (or the equivalent MCP tool):
scripts/nblm.sh health # reachability + auth status
scripts/nblm.sh notebooks # list notebooks (id + name)
scripts/nblm.sh ask "<question>" <notebook_id> # citation-backed answer (JSON citations)
scripts/nblm.sh generate <notebook_id> report # audio|report|video|infographic|presentation|data_table|flashcards|quiz|mind_map
What ships with it
3 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.
- 8d ago First seen · 91 lines · 118 tokens per session scan A 8921fc61ca50
notebooklm is a skill published in the GitHub repository roomi-fields/notebooklm-mcp (174 stars, last pushed 3d ago), licensed MIT. It adds 118 tokens to every session and 1,067 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 2026-08-30.
Other skills, from other repositories
blog-post
Writes and structures long-form blog posts, creates tutorial outlines, and optimizes content for SEO with cover image generation. Use when the user asks to write a blog post, article, how-to guide, tutorial, technical writeup, thought leadership piece, or long-form content.
post-build-flow
Handles workflow verification and setup after build-workflow succeeds, or when the message contains workflow-verification-follow-up or workflow-setup-required. Load after direct builds, when verificationReadiness requires action, or on orchestrator verify/setup follow-up turns.
intent-recognition
Classifies automation requests using two decisions: anchor (which primitive owns the top-level control flow — workflow-anchored, agent-anchored, needs-clarification, or out-of-scope) and embedsother (whether the other primitive appears embedded inside — an agent step inside a workflow, or a workflow invoked as an…
data-table-manager
Load before calling data-tables or parse-file. Use for natural standalone requests like "what data tables do I have?", "show/list my tables", or "what columns are in this table?", and whenever the user asks to list, show, create, inspect, import, seed, query, update, clean up, rename columns in, or delete data tables…
planned-task-runtime
Handles system follow-up turns: planned-task-follow-up (synthesize, replan, build-workflow, checkpoint), background-task-completed, running-tasks context, and create-tasks silence rules. Load whenever any of these tags appear or after calling create-tasks.
planning
ONLY for coordinated multi-artifact work: multiple workflows with dependencies, shared data-table schema/migration across tasks, or the user explicitly asked to review a plan first. Load create-tasks via loadtool before calling it (search "create tasks" if not visible). Do NOT use for new one-off workflows…