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.
git clone --depth 1 https://github.com/Muraty6242/notebooklm-claude-integrationWrote 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/commands/muraty6242/notebooklm-claude-integration/nlm)<a href="https://agentmods.dev/commands/muraty6242/notebooklm-claude-integration/nlm"><img src="https://agentmods.dev/badge/commands/muraty6242/notebooklm-claude-integration/nlm/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/commands/muraty6242/notebooklm-claude-integration/nlm"><img src="https://agentmods.dev/badge/commands/muraty6242/notebooklm-claude-integration/nlm.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00014 | $0.02791 |
| Opus 5 | $0.00007 | $0.01396 |
| Sonnet 5 | $0.00003 | $0.00558 |
| Haiku 4.5 | $0.00001 | $0.00279 |
Grade A, and why
nlm 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.
This is a copy
100% identical to nlm — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 337 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/nlm - NotebookLM Integration
Query your Google NotebookLM notebooks for source-grounded, citation-backed answers from Gemini.
Subcommands
| Subcommand | Usage | Description |
|---|---|---|
ask |
/nlm ask <question> |
Ask a question to a notebook by ID |
ask-all |
/nlm ask-all <question> |
Ask all notebooks in parallel, compare answers |
create |
/nlm create <name> |
Create a new notebook (RPC only) |
rename |
/nlm rename <id> <name> |
Rename a notebook (RPC only) |
delete |
/nlm delete <id> |
Delete a notebook (RPC only, confirm) |
list |
/nlm list |
List all notebooks |
source |
`/nlm source <add-url | add-text |
research |
`/nlm research <start | status |
studio |
`/nlm studio <audio | video |
describe |
`/nlm describe <notebook | source> ` |
configure |
`/nlm configure <goal | length |
auth |
/nlm auth [rpc] |
Manage authentication |
Arguments
$ARGUMENTS
Instructions
Parse the subcommand from arguments and execute the appropriate action:
Server Selection (Default Behavior)
- Use the
notebooklm-rpctools only (expanded toolset + feature parity).
ask - Ask a Question
When user runs /nlm ask <question>:
- Ensure RPC auth is configured (cookies saved via
save_auth_tokens) - Use
notebook_querywithnotebook_id - Display the answer with citations formatted clearly:
## Answer
[Answer text from NotebookLM]
### Sources
- [Citation 1]
- [Citation 2]
Example:
/nlm ask How do I implement OAuth in FastAPI?
ask-all - Ask All Notebooks (Parallel)
When user runs /nlm ask-all <question>:
This command queries all notebooks in your library simultaneously using parallel subagents, then aggregates the responses with clear notebook identification.
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 · 337 lines · 14 tokens per session scan A c9e238f1aafc
nlm is a command published in the GitHub repository Muraty6242/notebooklm-claude-integration (0 stars, last pushed 2mo ago), licensed MIT. It adds 14 tokens to every session and 2,791 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to nlm, differing in 0 lines, and is treated as a copy.
Other commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.