obsidian-second-brain turns an Obsidian vault into persistent, searchable memory for Claude Code and other command-line coding agents, storing knowledge as linked Markdown notes. It is for developers, founders, writers, and researchers who want agents to retain project context across sessions. Its catalogue entries provide commands, hooks, a plugin, a skill, and instructions for capturing, finding, and maintaining that memory.
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.
git clone --depth 1 https://github.com/eugeniughelbur/obsidian-second-brainWrote 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.
[](https://agentmods.dev/commands/eugeniughelbur/obsidian-second-brain/obsidian-graduate)<a href="https://agentmods.dev/commands/eugeniughelbur/obsidian-second-brain/obsidian-graduate"><img src="https://agentmods.dev/badge/commands/eugeniughelbur/obsidian-second-brain/obsidian-graduate/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.
<a href="https://agentmods.dev/commands/eugeniughelbur/obsidian-second-brain/obsidian-graduate"><img src="https://agentmods.dev/badge/commands/eugeniughelbur/obsidian-second-brain/obsidian-graduate.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00018 | $0.00914 |
| Opus 5 | $0.00009 | $0.00457 |
| Sonnet 5 | $0.00004 | $0.00183 |
| Haiku 4.5 | $0.00002 | $0.00091 |
Grade A, and why
obsidian-graduate 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 13d 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.
What it actually says
Use the obsidian-second-brain skill. Execute /obsidian-graduate $ARGUMENTS:
The optional argument is the idea title, tag, or keyword. If not provided, scan recent notes for ideas tagged #idea or in the ideas folder (resolved per references/folder-map.md) and present them for selection.
- Read
_CLAUDE.mdfirst if it exists in the vault root. Resolve the ideas folder and projects folder perreferences/folder-map.md(wiki-style: ideas inwiki/concepts/, projects inwiki/projects/; Obsidian-style:Ideas/,Projects/). - Find the idea to graduate:
- If argument given: search the ideas folder, daily notes, and captures for a matching idea (fuzzy match)
- If no argument: list recent ideas (last 14 days) and ask the user to pick one
- Read the full idea note and any linked notes for context
- Research the vault for related content:
- Existing projects that overlap
- People who were mentioned in connection with this idea
- Past decisions that relate
- Similar ideas that were previously explored (to avoid reinventing)
- Generate a full project spec:
- Project note in the projects folder (resolved above) with the full
type: projectschema fromreferences/ai-first-rules.md(type: project,date,updated,status: planning,tags: [project],related-people,related-projects,ai-first: true) plusgraduated-from: "[[Idea Note]]" - Description: what this project is and why it matters
- Goals: 3-5 concrete outcomes
- Key tasks: broken into phases with priorities
- Open questions: what still needs answering
- Related notes: links to everything relevant found in step 4
- Project note in the projects folder (resolved above) with the full
- Create board entries:
- Add a card to the relevant kanban board in
BacklogorThis Week - Add individual task cards if multiple phases
- Add a card to the relevant kanban board in
- Update the original idea note:
- Add
status: graduatedto frontmatter - Add a link to the new project note
- Add
- Link the new project from today's daily note
- Report: what was created, what was linked, what needs the user's input
The idea doesn't die - it evolves. The original note stays as the origin story, the project note becomes the execution plan.
AI-first rule: Every note created or updated by this command MUST follow references/ai-first-rules.md - ## For future agent preamble, rich frontmatter (type, date, tags, ai-first: true, plus type-specific fields), recency markers per external claim, mandatory [[wikilinks]] for every person/project/concept referenced, sources preserved verbatim with URLs inline, and confidence levels where applicable. If that path does not resolve from your working directory, search upward for it; if you still cannot read it, say so before writing rather than producing a note that silently skips the rule. The vault is for future agent retrieval - not human reading.
Anti-fabrication: Search exhaustively before claiming any note, person, or file is absent - false absence is the most common failure mode - and never invent facts, entities, or dates (mark unknowns as TBD). See the anti-fabrication and search-completeness hard rules in references/ai-first-rules.md.
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.
- 13d ago First seen · 47 lines · 18 tokens per session scan A 1b7480e850ec
obsidian-graduate is a command published in the GitHub repository eugeniughelbur/obsidian-second-brain (4,415 stars, last pushed 5d ago), licensed MIT. It adds 18 tokens to every session and 914 once invoked, about $0.0001 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.
Other commands, from other repositories
cierre
A sales call just ended: turn its transcript into the full follow-up (CRM, tasks, email draft, reminder, coaching).
deconstruct
First-principles analyst: surface hidden assumptions, find foundational truths, rebuild from scratch.
diagnose
Run a self-check on your AI Brain Starter install (CLAUDE.md, Meta folder, skills, hooks, MCPs).
instinct-import
Import a portable YAML instinct pack with confidence-gated merge (Instinct Engine).
meeting-todos
Extract action items from a meeting note and route them to the right to-do file.
optimize-brain
Deep vault optimization: CRM, graphs, dashboards, compression, wikilinks.