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/create-command)<a href="https://agentmods.dev/commands/eugeniughelbur/obsidian-second-brain/create-command"><img src="https://agentmods.dev/badge/commands/eugeniughelbur/obsidian-second-brain/create-command/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/create-command"><img src="https://agentmods.dev/badge/commands/eugeniughelbur/obsidian-second-brain/create-command.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 | $0.00016 | $0.02201 |
| Opus 5.5 | $0.00006 | $0.00880 |
| Sonnet 5.5 | $0.00003 | $0.00440 |
| Haiku 4.5 | $0.00002 | $0.00220 |
Grade A, and why
create-command 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 26d 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 — 172 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Use the obsidian-second-brain skill. Execute /create-command $ARGUMENTS:
This command runs a short interview, then writes a new commands/<name>.md file that the build pipeline picks up automatically. The user never touches frontmatter, never edits a template, and never copies an existing command file.
Hard rule: You MUST use the AskUserQuestion tool for every question in this flow. ONE question per call. Wait for the answer before the next question. Do not batch.
The optional argument is a free-text seed describing what the command should do (e.g., summarize my notion pages and save to vault). If given, use it to pre-fill suggestions in the interview. If empty, the first question opens with "what problem do you want to solve?".
Fast path (skip the interview when the seed already answers it)
If the seed argument is detailed enough to fill every field yourself - the intent is clear AND you can confidently derive a name, category, trigger phrases, the step outline, and whether it writes to the vault - do NOT run the six-question interview. Instead:
- Draft the complete spec (name, category, triggers, 3-5 steps, vault-write yes/no) from the seed.
- Present it in ONE AskUserQuestion tool call as a single confirm-or-adjust gate: option A "Create it as specced" (show the name + one-line behaviour), option B "Let me adjust" (falls back to the full interview). Include the proposed name in the option label so the user sees it.
- On "Create it as specced", validate the name (Phase 2 checks: regex
^[a-z][a-z0-9-]*$, andcommands/<name>.mddoes not already exist), then jump straight to Phase 8 (generate the file) and Phase 9 (confirm).
Only the truly under-specified seeds need the full interview. A seed like "summarize my notion pages and save to vault as AI-first notes, call it obsidian-notion, research category" is enough to fast-path. When in doubt, run the interview - one confirmation is fine, but never invent behaviour the seed did not state (see the anti-fabrication rule).
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.
- 26d ago Changed · +1 lines d357311728e5
- 1mo ago First seen · 171 lines · 16 tokens per session scan A ac9f879da73f
create-command is a command published in the GitHub repository eugeniughelbur/obsidian-second-brain (4,858 stars, last pushed 2d ago), licensed MIT. It adds 16 tokens to every session and 2,201 once invoked, about $0.0001 per session on Opus 5.5. 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.
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).
evolve
Cluster hardened instincts into a proposed Command / Skill / Agent (Instinct Engine).