A command for carrying out research through NotebookLM, a tool for analysing a collection of supplied sources. It can gather sources such as web pages, YouTube videos, Google Drive documents, and pasted text.

Run it with a research topic, add the relevant sources, and use the resulting NotebookLM notebook for analysis. It supports importing web, video, Drive, and direct-text sources.

It organizes source collection and analysis into a repeatable process. Optional automatic source discovery can expand the research set before analysis.

research — Command for Claude Code by CreatmanCEO: A command for carrying out research through NotebookLM, a…

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 commands/creatmanceo/notebooklm-claude-workflows/research

Clone the repo

git clone --depth 1 https://github.com/CreatmanCEO/notebooklm-claude-workflows

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.

README.md

[![agentmods](https://agentmods.dev/badge/commands/creatmanceo/notebooklm-claude-workflows/research.svg)](https://agentmods.dev/commands/creatmanceo/notebooklm-claude-workflows/research)

Your own site

<a href="https://agentmods.dev/commands/creatmanceo/notebooklm-claude-workflows/research"><img src="https://agentmods.dev/badge/commands/creatmanceo/notebooklm-claude-workflows/research.svg" alt="Measured on agentmods" height="20"></a>

Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 868 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.

Model	Per session	Once invoked
Fable 5.1	$0.00000	$0.00868
Opus 5	$0.00000	$0.00434
Sonnet 5	$0.00000	$0.00174
Haiku 4.5	$0.00000	$0.00087

Measured 5d ago against content hash b345cc214836, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

research 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 5d 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.

commands/research.md · 71 lines

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.

/research — Полный цикл исследования через NotebookLM

Параметр

$ARGUMENTS — тема исследования

Фаза 1: Сбор источников

Создай NotebookLM ноутбук "Research: $ARGUMENTS" через notebook_create
Спроси пользователя об источниках. Принимай любые комбинации:
- YouTube ссылки
- Веб-страницы / документация
- Google Drive документы (нужен document_id)
- Текст напрямую
Добавляй каждый источник через source_add:
- YouTube и веб-ссылки: source_type=url
- Google Drive: source_type=drive, document_id=...
- Текст: source_type=text, title=...
- Всегда wait=true
Показывай прогресс: "Загружено 3/7 источников..."

Фаза 1.5: Авто-расширение базы (опционально)

4.1. После загрузки пользовательских источников предложи: "Хочешь автоматически найти дополнительные источники по теме?" 4.2. Если да — используй research_start, передав notebook_id из шага 1 и query = тему исследования 4.3. Проверяй статус через research_status (поддерживает параметр max_wait для автоматического polling) 4.4. Когда готово — покажи найденные источники и спроси какие импортировать 4.5. Импортируй выбранные через research_import, передав task_id из ответа research_status 4.6. Покажи обновлённое количество источников

Фаза 2: Анализ

Выполни серию notebook_query к созданному ноутбуку:
- "Суммаризируй ключевые идеи из всех источников"
- "Какие паттерны и общие темы прослеживаются?"
- "Какие противоречия или расхождения есть между источниками?"
Если пользователь задал конкретный вопрос — задай его тоже
Выведи структурированный отчёт:
- Обзор темы
- Ключевые находки (с цитатами)
- Паттерны и тренды
- Противоречия (если есть)
- Выводы и рекомендации

Фаза 3: Артефакты (по запросу)

Предложи сгенерировать на выбор:
- Audio Overview (подкаст) — studio_create, artifact_type=audio
- Mind Map — studio_create, artifact_type=mind_map
- Flashcards — studio_create, artifact_type=flashcards
- Briefing Doc — studio_create, artifact_type=report
- Quiz — studio_create, artifact_type=quiz
После запуска генерации проверяй статус через studio_status
Скачивай готовые артефакты через download_artifact в ~/Downloads/

Read the full file on GitHub · 71 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.

5d ago First seen · 71 lines · 0 tokens per session scan A b345cc214836

Subscribe to this mod's changes

research is a command published in the GitHub repository CreatmanCEO/notebooklm-claude-workflows (5 stars, last pushed 4mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 868 tokens. 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.

Research ai-research ai-tools anthropic claude-code claude-code-commands claude-md

ars-plan

ARS academic-paper plan mode — Socratic chapter-by-chapter planning.

Imbad0202/academic-research-skills · 19 tokens

superpowers-execute

Execute the current GSD phase plan with Superpowers instead of gsd-execute-phase.

alfredoperez/speckit-companion · 17 tokens

synthesise-reviews

Deduplicate and reconcile multiple completed review reports into one prioritised revision plan with conflicts and dependencies made explicit. Use when parallel reviewers have returned findings that need a single action sequence. Not for running the reviews; use $review-cluster.

flonat/flonat-research · 47 tokens

research