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-decide)<a href="https://agentmods.dev/commands/eugeniughelbur/obsidian-second-brain/obsidian-decide"><img src="https://agentmods.dev/badge/commands/eugeniughelbur/obsidian-second-brain/obsidian-decide/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-decide"><img src="https://agentmods.dev/badge/commands/eugeniughelbur/obsidian-second-brain/obsidian-decide.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 | $0.00020 | $0.01108 |
| Opus 5 | $0.00010 | $0.00554 |
| Sonnet 5 | $0.00004 | $0.00222 |
| Haiku 4.5 | $0.00002 | $0.00111 |
Grade A, and why
obsidian-decide 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 — 47 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-decide $ARGUMENTS:
Two depths, one command. The optional argument narrows focus to a topic. Add --formal (or lead with adr) to write a full Architecture Decision Record instead of a one-line log entry.
- Default (lightweight): capture decisions from the conversation as dated one-liners in the relevant project notes. Use for the steady stream of choices made while working.
--formal(ADR): write one structured decision record with context, options, rationale, and consequences. Use for a structural or directional decision worth a full writeup (a folder reorg, a convention adopted, an idea graduated, a stack choice).
- Read
_CLAUDE.mdfirst if it exists in the vault root.
Lightweight mode (default)
- Scan the conversation for decisions made - conclusions, choices, commitments, direction changes. If a topic argument is given, focus there.
- Find the relevant project note(s) - search the vault if needed.
- Append each decision to the project note's
## Key Decisionssection with today's date. - Log a summary in today's daily note. If a decision affects multiple projects, log it in all of them.
Formal mode (--formal)
- Identify the structural decision - from the argument or recent conversation (a project graduated, a folder reorganized, a convention adopted, a concept promoted to hub). To surface decisions already made in code but never recorded, run
uv run --directory "SKILL_ROOT" scripts/mine_commit_decisions.py --repo <project> --json(the skill root was given at session start as Skill root; substitute it forSKILL_ROOT) - it scans git history for decision-shaped commits ("switch to", "replace", "adopt", "rename", "migrate") and returns ADR candidates. - Create a decision record in the decisions folder resolved per
references/folder-map.md(wiki-stylewiki/decisions/YYYY-MM-DD - Title.md, Obsidian-styleKnowledge/ADR-YYYY-MM-DD - Title.md), with frontmatterdate,type: adr,status: accepted,tags: [adr, decision],ai-first: true. Structure:- Decision - one-line summary of what was decided.
- Context - what prompted it (the problem or trigger).
- Options Considered - 2-3 alternatives evaluated.
- Rationale - why this option over the others.
- Consequences - what changes as a result (notes created, moved, restructured).
- Related - links to affected project notes, people, ideas.
- Update the relevant project note's
## Key Decisionssection with a link to the record, and updateindex.md. - Append to the operation log (
Logs/YYYY-MM-DD.mdif it exists, elselog.md) and link from today's daily note.
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 · 47 lines · 20 tokens per session scan A 8bb81a56051b
obsidian-decide is a command published in the GitHub repository eugeniughelbur/obsidian-second-brain (4,376 stars, last pushed 3d ago), licensed MIT. It adds 20 tokens to every session and 1,108 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.
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).