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-brainstorm)<a href="https://agentmods.dev/commands/eugeniughelbur/obsidian-second-brain/obsidian-brainstorm"><img src="https://agentmods.dev/badge/commands/eugeniughelbur/obsidian-second-brain/obsidian-brainstorm/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-brainstorm"><img src="https://agentmods.dev/badge/commands/eugeniughelbur/obsidian-second-brain/obsidian-brainstorm.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 | $0.00027 | $0.01270 |
| Opus 5 | $0.00014 | $0.00635 |
| Sonnet 5 | $0.00005 | $0.00254 |
| Haiku 4.5 | $0.00003 | $0.00127 |
Grade A, and why
obsidian-brainstorm 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 10d 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.
How it starts
The opening of the file, as written. The whole thing — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Use the obsidian-second-brain skill. Execute /obsidian-brainstorm $ARGUMENTS:
The optional argument is the topic. If not provided, infer it from recent conversation, or ask "What are we brainstorming?"
Every other thinking tool in this skill is a single-shot analytical pass. This one is different: it is stateful and multi-turn - you interview the user one question at a time until the idea has actually converged, and only then write anything. Do not rush to the output. The interview IS the tool.
Phase 1 - ground in the vault (silent, no LLM theatrics)
- Read
_CLAUDE.mdfirst if it exists in the vault root - Search the vault for the topic: related project notes, past decisions (Key Decisions sections, ADRs), idea fragments, and open questions (
TBD,TODO, open-question sections). This is context for your questions - do not dump it at the user - Note contradictions or prior failures the vault records about this topic; they become questions in Phase 2
Phase 2 - the interview (one question per turn, hard rule)
Ask exactly one question per turn. Prefer multiple-choice (2-4 concrete options plus "other") over open questions - options force clarity. Draw each question from whichever of these six categories is least resolved:
- Problem framing - what actually hurts today? Who feels it?
- Constraint surfacing - time, money, skills, platform, non-negotiables
- Trade-off forcing - "if you could only have one of X or Y, which?"
- Scope bounding - what is explicitly OUT of the first version?
- Prior-decision linking - "your vault records [[decision]] - does that still hold here?"
- Anti-goals - what outcome would make this a failure even if it "works"?
Track convergence against this checklist (internally - do not show a scoreboard):
- problem stated in one sentence
- hard constraints known
- at least one trade-off explicitly decided
- first-version scope bounded
- linked to (or consciously departing from) prior vault decisions
- anti-goals named
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.
- 10d ago First seen · 71 lines · 27 tokens per session scan A e05ef16c3a00
obsidian-brainstorm is a command published in the GitHub repository eugeniughelbur/obsidian-second-brain (4,376 stars, last pushed 3d ago), licensed MIT. It adds 27 tokens to every session and 1,270 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
second-brain-mapping
Map your vault: extract structured metadata from every typed file, surface cross-doc insights, optionally build a knowledge graph.
setup-vault-types
Configure which document types your vault uses (journals, books, meetings, clients, etc.) and scaffold extractors.
cierre
A sales call just ended: turn its transcript into the full follow-up (CRM, tasks, email draft, reminder, coaching).
daily-journal
Daily journal interview and entry creator with emotional floor tagging.
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).