nlm

nlm is a skill for Claude Code from aksika/abtars. It costs 16 tokens per session (262 once invoked), scanned A, original, Apache-2.0.

A command-line way to ask questions about documents stored in NotebookLM, Google's tool for working with a curated set of reference sources.

In plain words
What is it for?
Use it to query uploaded research papers, technical documentation, and other reference material, with the sources used returned alongside the answer.
Why use it?
It provides answers grounded in selected papers, guides, or technical documents instead of relying only on general model knowledge. It is not intended for personal memories or live information.

Skill for Claude Code

Written for Claude Code: user-invocable in frontmatter.

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/aksika/abtars/nlm
Any agent
npx skills add aksika/abtars --skill nlm
Clone the repo
git clone --depth 1 https://github.com/aksika/abtars

Made for: Claude Code.

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 nlm

README.md
[![agentmods](https://agentmods.dev/badge/skills/aksika/abtars/nlm.svg)](https://agentmods.dev/skills/aksika/abtars/nlm)
Your own site
<a href="https://agentmods.dev/skills/aksika/abtars/nlm"><img src="https://agentmods.dev/badge/skills/aksika/abtars/nlm.svg" alt="Measured on agentmods" height="20"></a>
Per session 16 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 262 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 $0.00016 $0.00262
Opus 5 $0.00008 $0.00131
Sonnet 5 $0.00003 $0.00052
Haiku 4.5 $0.00002 $0.00026

Measured 6d ago against content hash 7c41c75df064, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

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 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.

templates/skills/nlm/SKILL.md · 41 lines

What it actually says

Knowledge Base Query (NotebookLM)

Query curated reference documents — research papers, technical docs, guides.

nlm notebook query <NOTEBOOK_ID> "your question here" --json

Other commands:

nlm notebook list --json                    # list notebooks
nlm notebook create <name> --json           # create notebook
nlm source list <NOTEBOOK_ID> --json        # list sources

Troubleshooting

If nlm returns 400 Bad Request or auth errors, the session has expired. Fix:

nlm login

This opens a browser for Google re-authentication. Happens periodically when Google rotates session tokens.

Returns JSON: answer, sources_used.

When to use

  • Questions about uploaded reference material (docs, research, guides)
  • Technical documentation lookups local memory wouldn't have
  • Local memory search returned nothing and question is about curated knowledge

When NOT to use

  • Answer already in conversation context
  • Personal memories / past conversations (use memory-search)
  • Real-time / live information (knowledge base is static)
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 · 41 lines · 16 tokens per session scan A 7c41c75df064

Subscribe to this mod's changes

nlm is a skill published in the GitHub repository aksika/abtars (9 stars, last pushed yesterday), licensed Apache-2.0. It adds 16 tokens to every session and 262 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.