agentmods.dev

notebooklm-wiki-pipeline: Instructions file for Claude Code

CLAUDE.md

notebooklm-wiki-pipeline CLAUDE.md is an instructions file for Claude Code from capitalparser/notebooklm-wiki-pipeline. It costs 571 tokens per session, scanned A, original, MIT.

A project instruction file describing a pipeline that sends large Google Drive PDFs to NotebookLM and turns its analysis into Obsidian wiki notes. Obsidian is a markdown-based note-taking application.

In plain words
What is it for?
Use it as project guidance when configuring authentication, choosing output locations, reusing NotebookLM notebooks, or running the PDF-to-wiki command.
Why use it?
It documents how the project avoids loading whole PDFs into the assistant and which tools handle file lookup, analysis, and note creation.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: reads .claude/ paths; mentions Claude Code.

This is capitalparser/notebooklm-wiki-pipeline's own configuration. It tells Claude Code how to work on notebooklm-wiki-pipeline itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything notebooklm-wiki-pipeline configures →

not rated 93repo +2 3mo ago A scan 571 tokens original MIT
View source ↗ capitalparser/notebooklm-wiki-pipeline
Reuse

Borrowing it

Nothing to install: this file belongs to capitalparser/notebooklm-wiki-pipeline. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/capitalparser/notebooklm-wiki-pipeline/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/capitalparser/notebooklm-wiki-pipeline

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 notebooklm-wiki-pipeline CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/capitalparser/notebooklm-wiki-pipeline/claude-md.svg)](https://agentmods.dev/instructions/capitalparser/notebooklm-wiki-pipeline/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/capitalparser/notebooklm-wiki-pipeline/claude-md"><img src="https://agentmods.dev/badge/instructions/capitalparser/notebooklm-wiki-pipeline/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 571 This file is loaded in full into every session.
When invoked 571 The same file — it is already loaded in full.
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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00571 $0.00571
Opus 5 $0.00285 $0.00285
Sonnet 5 $0.00114 $0.00114
Haiku 4.5 $0.00057 $0.00057

Measured 8d ago against content hash 34ed853423ee, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

notebooklm-wiki-pipeline CLAUDE.md 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.

CLAUDE.md · 55 lines

What it actually says

05_notebooklm_wiki_pipeline — 프로젝트 컨텍스트

Drive 대용량 PDF를 NotebookLM에 외주화하고, 분석 결과만 Claude Code가 수령하여 00_Wiki/ Obsidian 노트로 자동 변환하는 토큰-효율 파이프라인.

핵심 문제

Drive MCP로 PDF를 직접 읽으면 PDF 전체 텍스트가 Claude 컨텍스트를 지나가 토큰 소모가 과다. NotebookLM이 내부에서 PDF를 처리하고 Claude는 분석 결과(텍스트)만 수령하는 구조로 해결.

아키텍처

Drive PDF (대용량)
  ↓ source_add(drive_url)  — URL만 전달, 파일 내용은 Claude 컨텍스트 비통과
NotebookLM 내부 처리
  ↓ notebook_query("분석 요청")
분석 결과 텍스트  — 수백~수천 토큰만
  ↓ Claude Code 구조화
00_Wiki/{category}/{title}.md  — [[wikilink]] 포함 Obsidian 노트

도구 구성

  • notebooklm-mcp-cli (PyPI): notebooklm-mcp MCP 서버
    • 설치: uv tool install notebooklm-mcp-cli
    • 인증: nlm login (브라우저 기반 쿠키, 2-4주 유효)
    • MCP 등록: nlm setup add claude-code
  • Drive MCP (mcp__claude_ai_Google_Drive__*): 파일 메타데이터/ID 조회용만 사용
    • download_file_content 사용 금지 — 토큰 낭비의 원인

슬래시 커맨드

  • /pdf-to-wiki — 단일 PDF → Obsidian 노트 변환
    • 플러그인 위치: ~/.claude/commands/pdf-to-wiki.md
    • Claude Code 세션 시작 시 자동 로드됨

인증 관리

NotebookLM 쿠키는 2-4주마다 만료. 만료 시:

nlm login

자동 갱신 시도하지만 실패 시 수동 재인증 필요. Free tier: ~50 queries/day 한도.

산출물 위치

  • 생성 노트: ~/vault/00_Wiki/AI_Generated/
  • 재사용 노트북: NotebookLM 웹 UI에서 확인 가능 (쿼리 기록 자동 동기화)

ADR

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 · 55 lines · 571 tokens per session scan A 34ed853423ee

Subscribe to this mod's changes

notebooklm-wiki-pipeline CLAUDE.md is an instructions file published in the GitHub repository capitalparser/notebooklm-wiki-pipeline (93 stars, last pushed 3mo ago), licensed MIT. It adds 571 tokens to every session, about $0.0029 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 2026-08-30.

Claude CodeDocumentsPDFResearchgoogle-driveknowledge-managementmcpnotebooklmobsidian
Related

Other instructions, from other repositories

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,469 tokens

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens