Obsidian Second Brain Plugin for Claude Code

What is the Obsidian Second Brain plugin?

The Obsidian Second Brain plugin is a Claude Code plugin that turns an Obsidian vault into an AI-assisted knowledge system. It bundles nine skills and nine slash commands covering PKM methodology, note templates, vault health checks, semantic search, and web clipping, connected to your vault through the Obsidian MCP server, the Obsidian CLI, and qmd.

Without it, Claude has no built-in knowledge of Obsidian's file formats, linking conventions, or CLI. With it installed, Claude can read and write notes the way a careful Obsidian user would — using [[wikilinks]] instead of markdown links, preserving frontmatter, applying callout syntax, and keeping notes connected to Maps of Content (MOCs) instead of orphaned in a folder. We built this plugin because we manage our own research, client notes, and project history in Obsidian at Rhize Media, and we got tired of Claude producing notes that looked right but broke every vault convention we actually rely on.

This is one plugin in a broader marketplace of Claude Code plugins — see Rhize plugins for Claude Code for the full catalog and installation instructions.

What problem does it solve?

A vault full of notes is not the same thing as a working second brain. Most Obsidian vaults accumulate captured content — clipped articles, meeting notes, half-finished ideas — without the connective tissue that makes a knowledge system useful: links between related notes, consistent tagging, MOCs that summarize a topic, and a repeatable process for turning fleeting notes into permanent ones.

This plugin addresses that gap on three fronts. First, it teaches Claude actual PKM methodologies (Zettelkasten, PARA, progressive summarization) so it applies them instead of writing generic bullet points into a markdown file. Second, it wires Claude into your vault through the Obsidian MCP server and CLI so it can read, write, search, and reorganize notes directly rather than guessing at file paths. Third, it adds semantic search via qmd, so Claude can find conceptually related notes even when they share no exact keywords — a real limitation of plain full-text search once a vault grows past a few hundred notes.

What skills does the plugin ship?

The plugin ships nine skills split into two groups: knowledge-workflow skills that shape how Claude thinks about your vault, and format skills that activate automatically when Claude touches a specific Obsidian file type. You don't invoke skills directly — Claude loads them in the background when your request matches their trigger conditions.

The format skills are the ones you'll notice least and rely on most. Ask for "a project tracker base with columns for title, status, and due date" and the obsidian-bases skill activates on its own to produce a correctly structured .base file — you never have to name the skill.

What commands does it provide?

The plugin ships nine slash commands grouped into research, capture, and vault-health workflows. Each command composes multiple skills and tools automatically — /vault-research, for example, draws on defuddle, second-brain, vault-templates, and the CLI in a single pipeline.

How does the research pipeline work?

/vault-research is the command that best shows what the plugin is for. Point it at a URL and it clips the content with Defuddle, creates a properly formatted note with metadata, writes a summary, searches your vault for related notes, suggests connections, and logs the research in your daily note — one command, one pipeline, several skills working together.

Point it at a topic instead of a URL and the behavior changes: it searches the web, lets you pick sources, processes each one through the same pipeline, and offers to build a synthesis note once it's done. In our own vault at Rhize Media, we use this for technical deep-dives — running /vault-research transformer architecture advances produces a properly linked note set instead of a wall of text we'd have to break apart and connect manually.

Three example prompts that show the range of the command set:

• /vault-research https://example.com/interesting-article — clip, summarize, and connect a single source
• /vault-connect recent — find your most isolated recent notes and weave them into the graph
• /vault-recall What decisions did we make about the API architecture? — ask the vault a question and get a cited, synthesized answer instead of a list of search hits

/vault-recall is worth calling out specifically: it uses qmd's hybrid search (BM25 plus vector plus LLM re-ranking) to pull the most relevant notes, then reads them and composes an answer with [[wikilink]] citations back to the source notes, while flagging contradictions and knowledge gaps it finds along the way. Without qmd installed it falls back to keyword search — still functional, just less precise on questions phrased differently than the source notes.

How does vault health checking work?

/vault-align runs a structured audit against five dimensions: structure (folder organization), connectivity (links and MOCs), consistency (frontmatter and tags), processing (whether captures actually become permanent notes), and plugin utilization. Running /vault-align check on a vault that's accumulated six months of unmanaged notes typically surfaces broken links, orphan notes with no incoming or outgoing connections, and tag drift — the same three problems, in our experience, that quietly make a vault stop being useful.

The command has four modes. check produces a scored report with prioritized suggestions. fix executes the single highest-impact improvement and re-checks the affected area. migrate builds and executes a full batch reorganization plan — file moves, tag consolidation, frontmatter standardization — with per-phase approval, using obsidian move so wikilinks don't break. plugins audits your installed community plugins against what your vault archetype needs.

What sets up the vault correctly the first time?

New vaults, or existing vaults you want to reorganize, start with /vault-setup. It interviews you about your role and workflow, audits your existing notes if you have any, generates a personalized folder structure, templates, dashboard, and MOC scaffold, and — for existing vaults — offers an opt-in migration to move everything into the new structure without losing links. It also writes a _vault-setup-log.md note that /vault-align later reads to know what your vault is supposed to look like.

What are the setup prerequisites?

The plugin depends on three separate integrations, each with its own setup step, plus one optional dependency for semantic search.

Installation itself is simple: accept the plugin when Claude Code presents it, or install the .plugin file from your vault's skills folder. The bundled .mcp.json auto-registers the Obsidian MCP server connector.

What happens automatically in the background?

Three hooks run without you invoking anything. A SessionStart hook loads the plugin's commands, skills, connectors, and vault path at the start of every session. A PreToolUse hook fires on any Write or Edit to a vault markdown file and enforces second-brain conventions — wikilinks instead of markdown links, callout syntax, frontmatter preservation, tags, and parent MOC linking. A PostToolUse hook fires after Claude reads a vault note and suggests following its wikilinks, checking related tags, or running /vault-connect or /vault-align. All three are scoped to your vault path — anything outside it passes through untouched — and they fail silently with a three-second timeout rather than blocking your work.

Who is this plugin for?

It's built for anyone running Obsidian as an active knowledge system rather than a folder of loose notes — researchers processing sources into permanent notes, writers building a MOC-linked idea graph, consultants tracking client history across engagements, or anyone doing periodic reviews of their own thinking. It assumes you already use Obsidian; it won't migrate you off another note tool, and the CLI- and MCP-dependent commands need Obsidian running in the background. If your vault is a flat folder of unlinked notes today, /vault-setup is the intended starting point, not /vault-research or /vault-align.

Getting started

If you're new to the plugin, start with /vault-setup for a structure that matches how you work, then reach for /vault-capture and /vault-daily day to day, layering in /vault-research, /vault-connect, and /vault-recall once you have enough notes for connections to matter. Run /vault-align check periodically — it's the fastest way to catch broken links and orphan notes before they pile up.

For the rest of the marketplace this plugin ships alongside, see Rhize plugins for Claude Code. The plugin source and installation instructions are on GitHub, and background on the underlying methodology is documented on Obsidian's own help site.