research-agent

research-agent is an agent for Claude Code from Muraty6242/notebooklm-claude-integration. It costs 46 tokens per session (1,233 once invoked), scanned A, a copy of research-agent, MIT.

A research agent that investigates topics using NotebookLM notebooks, which are workspaces built from the user's reference documents. It asks follow-up questions and combines findings into answers with citations.

In plain words
What is it for?
Use it to research, investigate, compare, or learn comprehensively from documentation, including implementation guidance and documented approaches.
Why use it?
It helps avoid shallow answers when the relevant information is spread across documentation. It also makes gaps in the available sources explicit.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter.

Part of the notebooklm plugin — 1 command, 1 agent shipped together

Good fit Use it to research, investigate, compare, or learn comprehensively from documentation, including implementation guidance and documented approaches.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/muraty6242/notebooklm-claude-integration/research-agent
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.

Clone the repo
git clone --depth 1 https://github.com/Muraty6242/notebooklm-claude-integration

Made for: Claude Code.

Or install notebooklm, the plugin that ships this one along with the rest of its 1 command, 1 agent.

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 research-agent

README.md
[![agentmods](https://agentmods.dev/badge/agents/muraty6242/notebooklm-claude-integration/research-agent/github.svg)](https://agentmods.dev/agents/muraty6242/notebooklm-claude-integration/research-agent)
Your own site
<a href="https://agentmods.dev/agents/muraty6242/notebooklm-claude-integration/research-agent"><img src="https://agentmods.dev/badge/agents/muraty6242/notebooklm-claude-integration/research-agent/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.

agentmods 80×15 button for research-agent

Your own site · 80×15
<a href="https://agentmods.dev/agents/muraty6242/notebooklm-claude-integration/research-agent"><img src="https://agentmods.dev/badge/agents/muraty6242/notebooklm-claude-integration/research-agent.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 46 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,233 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin 100% copy Near-identical to another mod 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 $0.00046 $0.01233
Opus 5 $0.00023 $0.00616
Sonnet 5 $0.00009 $0.00247
Haiku 4.5 $0.00005 $0.00123

Measured 8d ago against content hash 23f6e0e81451, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

research-agent 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.

Origin

This is a copy

100% identical to research-agent — 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.

plugins/notebooklm/agents/research-agent.md · 188 lines

How it starts

The opening of the file, as written. The whole thing — 188 lines — stays where its author put it; the contents beside it link to each section on GitHub.

NotebookLM Research Agent

A specialized research agent that conducts thorough investigations using NotebookLM notebooks, generating intelligent follow-up questions and synthesizing findings into comprehensive, citation-backed answers.

Core Identity

You are a research specialist focused on extracting maximum value from the user's NotebookLM notebooks. You combine initial queries with strategic follow-up questions to build complete understanding of any topic, always citing sources and acknowledging gaps in documentation.

When to Activate (PROACTIVE)

Trigger automatically when user:

  • Uses keywords: "research", "investigate", "explore", "deep dive", "learn about"
  • Asks complex questions requiring comprehensive understanding
  • Says "tell me everything about...", "what do my docs say about..."
  • Needs implementation guidance from their documentation
  • Requests comparison or analysis of documented approaches

Example triggers:

"Research how to implement authentication"
"Investigate the error handling patterns in my docs"
"Deep dive into the API architecture"
"What do my docs say about caching strategies?"
"Explore all the testing approaches documented"

Technical Domains

Primary Focus

  • Documentation Research: Extracting information from user's NotebookLM notebooks
  • Citation Management: Tracking and presenting source references
  • Gap Analysis: Identifying what documentation covers vs. what's missing
  • Synthesis: Combining multiple answers into coherent findings

MCP Tools Used

  • mcp__notebooklm-rpc__notebook_list - Find available notebooks
  • mcp__notebooklm-rpc__notebook_query - Query notebooks with questions

Research Methodology

Phase 1: Context Discovery

1. Check available notebooks with notebook_list
2. Identify the most relevant notebook(s) for the topic

Phase 2: Initial Query

1. Formulate clear, specific primary question
2. Query with notebook_query
3. Analyze response for:
   - Key information found
   - Gaps or unclear areas
   - Follow-up opportunities

Read the full file on GitHub · 188 lines

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. 8d ago First seen · 188 lines · 46 tokens per session scan A 23f6e0e81451

Subscribe to this mod's changes

research-agent is an agent published in the GitHub repository Muraty6242/notebooklm-claude-integration (0 stars, last pushed 2mo ago), licensed MIT. It adds 46 tokens to every session and 1,233 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to research-agent, differing in 0 lines, and is treated as a copy.