What is deep-research?

A deep-research command conducts a multi-step investigation through NotebookLM, a tool for asking questions about collected sources. It builds a topic tree, gathers sources, and combines their contents into a detailed report.

It is for researching a subject from URLs, YouTube videos, Drive files, text, or other sources, with optional automatic source discovery.

It helps with broad topics that need several rounds of source collection, questions, and synthesis instead of a short search.

deep-research — Command for Claude Code by CreatmanCEO

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/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/deep-research/github.svg)](https://agentmods.dev/commands/creatmanceo/notebooklm-claude-workflows/deep-research)

Your own site

<a href="https://agentmods.dev/commands/creatmanceo/notebooklm-claude-workflows/deep-research"><img src="https://agentmods.dev/badge/commands/creatmanceo/notebooklm-claude-workflows/deep-research/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.

Your own site · 80×15

<a href="https://agentmods.dev/commands/creatmanceo/notebooklm-claude-workflows/deep-research"><img src="https://agentmods.dev/badge/commands/creatmanceo/notebooklm-claude-workflows/deep-research.svg" alt="Reviewed on agentmods" width="80" 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 689 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 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	$0.00689
Opus 5.5	$0.00000	$0.00276
Sonnet 5.5	$0.00000	$0.00138
Haiku 4.5	$0.00000	$0.00069

Measured 1mo ago against content hash 4a603006f51d, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

deep-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 1mo 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/deep-research.md · 49 lines

How it starts

The opening of the file, as written. The whole thing — 49 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/deep-research — Глубокое многоитерационное исследование через NotebookLM

В отличие от /research (3 вопроса), здесь Claude проводит глубокое погружение: строит дерево тем, задаёт серию уточняющих вопросов по каждой, синтезирует комплексный отчёт.

Параметр

$ARGUMENTS — тема исследования

Фаза 1: Подготовка

Проверь существующие ноутбуки через notebook_list — возможно, подходящий уже есть
Если нет — создай ноутбук "Deep Research: $ARGUMENTS" через notebook_create
Спроси пользователя об источниках (URL, YouTube, Drive, текст, файлы)
Добавляй каждый через source_add с wait=true, показывай прогресс

Фаза 2: Авто-расширение базы (опционально)

Предложи: "Хочешь, чтобы я автоматически нашёл дополнительные источники по теме?"
Если да — используй research_start, передав notebook_id из шага 2 и query = $ARGUMENTS
Проверяй статус через research_status
Импортируй найденные через research_import, передав task_id из ответа research_status

Фаза 3: Глубокий анализ

Первый запрос через notebook_query: "Составь подробное оглавление/структуру всей информации в источниках — основные темы, подтемы, ключевые понятия"
На основе полученной структуры — по КАЖДОЙ основной теме задай 3-5 уточняющих вопросов через notebook_query:
- Что конкретно говорят источники по этой теме?
- Какие цифры, факты, примеры приводятся?
- Есть ли противоречия между источниками?
- Какие практические рекомендации можно извлечь?
Используй conversation_id для сохранения контекста между вопросами

Фаза 4: Синтез

Собери все ответы и создай комплексный отчёт:
- Executive Summary (3-5 предложений)
- Дерево знаний (иерархия тем → подтем → фактов)
- Детальный разбор каждой темы с цитатами
- Противоречия и расхождения между источниками
- Практические выводы и рекомендации
- Список открытых вопросов (что не покрыто источниками)

Фаза 5: Сохранение (опционально)

Предложи варианты сохранения результатов:
- MD-файлы — отдельный файл на каждую тему (для Obsidian)
- PDF — сгенерировать через studio_create с artifact_type=report, confirm=true
- Mind Map — через studio_create с artifact_type=mind_map, confirm=true
При сохранении в MD — создавай файлы с frontmatter (tags, date, source) и [[wiki-links]] между связанными темами для графа знаний в Obsidian

Read the full file on GitHub · 49 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.

1mo ago First seen · 49 lines · 0 tokens per session scan A 4a603006f51d

Subscribe to this mod's changes

deep-research is a command published in the GitHub repository CreatmanCEO/notebooklm-claude-workflows (5 stars, last pushed 5mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 689 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.

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

deep-research

Getting it into your agent

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

/deep-research — Глубокое многоитерационное исследование через NotebookLM

Параметр

Фаза 1: Подготовка

Фаза 2: Авто-расширение базы (опционально)

Фаза 3: Глубокий анализ

Фаза 4: Синтез

Фаза 5: Сохранение (опционально)

What this file has done since we first saw it

Other commands, from other repositories

update-counts

watch

render

golden-path

firebase-publish

gws-people