ObsidianDataWeave: NotebookLM, Atomization, and LLM Wiki

ObsidianDataWeave: NotebookLM, Atomization, and LLM Wiki is a skill for Claude Code, Codex from howdeploy/deploychan_mcp. It costs 72 tokens per session (1,849 once invoked), scanned A, original, MIT.

A toolkit that connects NotebookLM, a Google research and note-taking service, with an Obsidian vault, a local knowledge-management folder. It can turn documents into linked notes and build a searchable wiki layer.

In plain words
What is it for?
Managing NotebookLM sources, importing DOCX files from Google Drive, splitting them into atomic Zettelkasten notes, creating wiki content, and full-text searching an Obsidian vault.
Why use it?
It reduces the manual work of moving research and documents into organized notes that can be searched and connected.

Skill for Claude CodeCodex

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/howdeploy/deploychan_mcp/obsidian-dataweave
Any agent
npx skills add howdeploy/deploychan_mcp --skill obsidian-dataweave
Clone the repo
git clone --depth 1 https://github.com/howdeploy/deploychan_mcp

Made for: Claude Code, Codex.

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 ObsidianDataWeave: NotebookLM, Atomization, and LLM Wiki

README.md
[![agentmods](https://agentmods.dev/badge/skills/howdeploy/deploychan_mcp/obsidian-dataweave.svg)](https://agentmods.dev/skills/howdeploy/deploychan_mcp/obsidian-dataweave)
Your own site
<a href="https://agentmods.dev/skills/howdeploy/deploychan_mcp/obsidian-dataweave"><img src="https://agentmods.dev/badge/skills/howdeploy/deploychan_mcp/obsidian-dataweave.svg" alt="Measured on agentmods" height="20"></a>
Per session 72 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,849 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 $0.00072 $0.01849
Opus 5 $0.00036 $0.00924
Sonnet 5 $0.00014 $0.00370
Haiku 4.5 $0.00007 $0.00185

Measured 5d ago against content hash 566c8d6c5cfa, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

ObsidianDataWeave: NotebookLM, Atomization, and LLM Wiki 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.

content/skills/obsidian-dataweave/SKILL.md · 135 lines

How it starts

The opening of the file, as written. The whole thing — 135 lines — stays where its author put it; the contents beside it link to each section on GitHub.

ObsidianDataWeave

Turns Claude Code and Codex into a full control panel for NotebookLM and your Obsidian vault. You run deep research, manage sources, and pull notes out of notebooks — all with a single natural-language command. In parallel, it imports .docx from Google Drive and atomizes them into Zettelkasten notes with a MOC, tags, and wikilinks. On top — an isolated LLM Wiki layer (a compiled base in the Karpathy style), and FTS5 memory — a full-text index of the entire vault without a single external dependency. Public: howdeploy/ObsidianDataWeave, MIT.

Both clients are supported natively: Claude Code (a global skill) and Codex Desktop / CLI / IDE (a native global skill of its own).

Four Layers

  1. NotebookLM → Obsidian. Programmatic control of NotebookLM through notebooklm-py as a library (not the CLI — strictly one-shot, no retry duplication). Deep/fast research, source management, dedup, note extraction, and atomization into the vault.
  2. .docx → Obsidian. Import from Google Drive (rclone) → parse → atomize → write.
  3. LLM Wiki. A compiled wiki on top of the atomic notes: it accumulates through an explicit merge (not RAG, not a recompute on every query), linked with [[wikilinks]].
  4. FTS5 memory. A local full-text index of the whole vault on stdlib SQLite, bm25 + snippets, auto-updates after every write. Search for agents.

Installation

git clone https://github.com/howdeploy/ObsidianDataWeave.git
cd ObsidianDataWeave
bash install.sh --vault-path "/path/to/your/vault"

Or hand the agent this one line and it does the rest: "clone https://github.com/howdeploy/ObsidianDataWeave.git and run bash install.sh --vault-path "/path/to/vault" in the cloned directory".

The installer checks for Python 3.10+, installs the dependencies (python-docx, pyyaml), and creates a config.toml with the vault path. After installation the skill works from any directory.

Mode Flag What it registers
claude (default) --mode claude A global skill in ~/.claude/skills/obsidian-dataweave/ plus a block appended to ~/.claude/CLAUDE.md
codex --mode codex A native global skill in ~/.agents/skills/obsidian-dataweave/ for Codex Desktop / CLI / IDE
local --mode local Dependencies and config only

Read the full file on GitHub · 135 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. 5d ago First seen · 135 lines · 72 tokens per session scan A 566c8d6c5cfa

Subscribe to this mod's changes

ObsidianDataWeave: NotebookLM, Atomization, and LLM Wiki is a skill published in the GitHub repository howdeploy/deploychan_mcp (11 stars, last pushed 6d ago), licensed MIT. It adds 72 tokens to every session and 1,849 once invoked, about $0.0004 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.

Related

Other skills, from other repositories

llm-wiki

Build and maintain a persistent, interlinked Obsidian-compatible markdown wiki using Karpathy's LLM Wiki pattern. Extension-backed with auto-generated metadata, guardrails, and 14 custom tools (+3 opt-in agent-trajectory tools).

zosmaai/pi-llm-wiki · 52 tokens

kb-lint

Health check for the PARA Knowledge Base. Detects orphan documents, broken links, index drift, tag issues, and stale content. Run periodically or as part of weekly review.

ernestolee13/para-knowledge-base · 39 tokens

kb-query

Query the PARA Knowledge Base to find information, synthesize answers from vault documents, inspect recent activity when needed, and record compact query telemetry when configured. Use for any question about Obsidian vault content, projects, references, logs, links, or cross-document analysis.

ernestolee13/para-knowledge-base · 57 tokens

kb-init

Initialize or adopt a portable PARA Knowledge Base in an Obsidian vault. Detects numbered, standard, or configured roots; creates indexes and a log when requested; and installs shared rules/config for Claude Code, Codex, and local consumers.

ernestolee13/para-knowledge-base · 52 tokens

memento

Capture durable knowledge from the current work session into Memento Vault. Use when the user asks to remember, save, capture, or record decisions, discoveries, bug fixes, or reusable patterns.

sandsower/memento-vault · 41 tokens

inception

Run or preview Memento Vault consolidation. Use when the user asks to consolidate, find patterns, run inception, preview clusters, or synthesize cross-session themes.

sandsower/memento-vault · 35 tokens