Agent Skill
Obsidian Second Brain skill
obsidian-second-braineugeniughelbur/obsidian-second-brainSKILL.md
Operate any Obsidian vault as a living, self-rewriting second brain (an evolution of Karpathy's LLM Wiki pattern: sources rewrite existing pages, contradictions reconcile automatically, scheduled agents maintain the vault while you sleep). Use this skill whenever the user asks Claude to read, write, update, search, or manage their Obsidian vault - including saving notes from conversation, creating daily entries, updating kanban boards, logging dev work, managing people notes, capturing decisions, tracking deals, or maintaining any vault structure. Also triggers when the user wants to bootstrap a new vault from scratch, run a vault health check, or drop a _CLAUDE.md into their vault so all Claude surfaces share the same operating rules. Also runs Crew (/crew): one shared logbook so Claude Code, Codex, Cursor, and Grok Bot know what each other did, in any plain folder or the vault. Includes a research toolkit (7 commands: /x-read, /x-pulse, /research, /research-deep, /notebooklm, /youtube, /podcast) for AI-powered research via Grok, Perplexity, NotebookLM, YouTube, and podcast feeds - findings save to the vault automatically following the AI-first vault rule. Use proactively whenever the conversation produces information worth preserving (decisions, people met, projects started, tasks completed, lessons learned, research findings).
always on
290 tokname + description
once used
20,188 tokSKILL.md body
bundled files
10676 scripts
repo stars
4.8kGitHub
Install the Obsidian Second Brain skill
Skills CLI (Claude Code, Codex, Cursor and others)
npx skills add https://github.com/eugeniughelbur/obsidian-second-brain --skill obsidian-second-brain
Claude Code, by hand (all projects)
git clone --depth 1 https://github.com/eugeniughelbur/obsidian-second-brain.git /tmp/obsidian-second-brain mkdir -p ~/.claude/skills cp -R /tmp/obsidian-second-brain ~/.claude/skills/obsidian-second-brain
For one project only, copy the folder into .claude/skills/ in that project instead. The agent picks it up when a task matches its description.
What it costs your context
Agent Skills load in three steps. Tokens counted with the o200k tokenizer; your model's count will differ a little.
| When | What loads | Cost |
|---|---|---|
| Every session | Name and description | 290 tok |
| When the agent uses it | The SKILL.md instructions | 20,188 tok |
| Only if opened | 106 bundled files (792 KB) | varies |
Until it is used, obsidian-second-brain costs about 4.7× less than the median MCP server we measured (1,363 tokens on every turn). Skills vs MCP study
Checks
- Tells the agent to pipe a download into a shell (curl … | sh). That runs whatever the URL serves at that moment, with your permissions.
- Ships scripts the agent can run. Read them before installing.
- The instructions are over 5,000 tokens, the Agent Skills specification's guideline for SKILL.md.
- The instructions are over 500 lines; the specification suggests moving detail into reference files.
- The description is longer than the specification's 1,024-character limit, so some agents may cut or reject it.
Checked 2026-10-22 · method
What's inside
The headings of its SKILL.md. Read the full file on GitHub.
- Obsidian Second Brain
- Quick Start
- 0. Choose vault access method (in order of preference)
- 1. First time in a vault → read CLAUDE.md
- 2. First time with a new user → run discovery
- 3. Bootstrap a new vault
- Core Operating Principles
- AI-first vault rule (applies to every note)
- Never create in isolation
- Bi-temporal facts - never overwrite, always append
- CRITICALFACTS.md - always loaded
- Raw is immutable
- Maintain index.md and log.md
- Per-day operation logs (modernized vaults)
- The vault is a living system
- Two-Output Rule
- Synthesis Hook
- Reconciliation
- Proactive save reminders
- Search before creating
- Never claim absence from memory, never fabricate
- Match the vault's voice
- Frontmatter is mandatory
- Write Rules