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-world)<a href="https://agentmods.dev/commands/eugeniughelbur/obsidian-second-brain/obsidian-world"><img src="https://agentmods.dev/badge/commands/eugeniughelbur/obsidian-second-brain/obsidian-world/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-world"><img src="https://agentmods.dev/badge/commands/eugeniughelbur/obsidian-second-brain/obsidian-world.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 | $0.00023 | $0.01178 |
| Opus 5 | $0.00012 | $0.00589 |
| Sonnet 5 | $0.00005 | $0.00236 |
| Haiku 4.5 | $0.00002 | $0.00118 |
Grade A, and why
obsidian-world 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 11d 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 — 64 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-world:
-
Read
_CLAUDE.mdfirst if it exists in the vault root -
Load context progressively - start light, go deeper only as needed:
L0 - Identity (~170 tokens) Read these files if they exist (search for them if paths differ):
SOUL.mdorAbout Me.md- who the user is, communication style, thinking preferencesCRITICAL_FACTS.md- ~120 tokens of always-needed context: timezone, manager, location, company, roleCORE_VALUES.mdorValues.md- decision-making principles and non-negotiables
L1 - Navigation (~1-2K tokens)
- Read
index.md- the catalog of all vault pages. This tells Claude what exists without loading everything. - Read recent operation log (last 10 entries): if
Logs/exists, read today's and yesterday'sLogs/YYYY-MM-DD.md; otherwise readlog.md
L2 - Current State (~2-5K tokens)
- Read
Home.mdorDashboard.md- current top-level priorities - Read today's daily note (if it exists) for what's already in progress
- Read the last 3 daily notes for recent momentum and open threads
- Scan active kanban boards for in-progress and overdue items
- Check for session digests from previous conversations (look for "End of Day" or "Session Digest" sections)
L3 - Deep Context (on demand, ~5-20K tokens)
- Only load if needed for a specific question or task
- Read active project notes (status: active) for current goals and blockers
- Read full source/reference notes (the concept or knowledge folder per
references/folder-map.md- wiki-stylewiki/concepts/orraw/, Obsidian-styleKnowledge/) if the user asks about a specific topic - Identify key people interacted with recently (last 7 days of daily notes)
-
Present a brief status after L0-L2 (do NOT load L3 unless needed):
- Who I am to you: confirm the persona and communication style
- Your current priorities: top 3-5 active threads (from index.md + boards)
- Open threads from last session: anything unfinished (from operation log + daily notes)
- Overdue / needs attention: tasks or projects that are stale
- Today so far: what's already logged today
Keep output concise - this is a boot-up sequence, not a report. The user should glance at it and say "yes, Claude is up to speed" and start working immediately.
- Core memory pinning - during the session, if the user is working on a specific task that requires persistent context (debugging a complex API, reviewing a long document, planning a project), Claude can PIN critical information to a
PINNED.mdfile at the vault root:- Write task-specific facts, schemas, or reference data to
PINNED.md - This file is loaded at L0 alongside SOUL.md and CRITICAL_FACTS.md
- When the task is done, clear
PINNED.md - This prevents critical session context from being lost during long conversations or context compaction
- Claude should proactively suggest pinning when it detects the user is deep in a complex task
- Write task-specific facts, schemas, or reference data to
If identity files (SOUL.md, CRITICAL_FACTS.md) don't exist, offer to create them by asking 5-7 quick questions about the user's role, values, and communication preferences.
If index.md doesn't exist, offer to run /obsidian-init to generate it.
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.
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.
- 11d ago First seen · 64 lines · 23 tokens per session scan A 1abbfdc1ce26
obsidian-world is a command published in the GitHub repository eugeniughelbur/obsidian-second-brain (4,392 stars, last pushed 4d ago), licensed MIT. It adds 23 tokens to every session and 1,178 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
patterns
Scan recent sessions for recurring patterns and turn them into captures (rules, concept notes, writing seeds).
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.