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/vault-deep-synthesis)<a href="https://agentmods.dev/commands/eugeniughelbur/obsidian-second-brain/vault-deep-synthesis"><img src="https://agentmods.dev/badge/commands/eugeniughelbur/obsidian-second-brain/vault-deep-synthesis/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/vault-deep-synthesis"><img src="https://agentmods.dev/badge/commands/eugeniughelbur/obsidian-second-brain/vault-deep-synthesis.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 | $0.00028 | $0.00834 |
| Opus 5 | $0.00014 | $0.00417 |
| Sonnet 5 | $0.00006 | $0.00167 |
| Haiku 4.5 | $0.00003 | $0.00083 |
Grade A, and why
vault-deep-synthesis 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.
What it actually says
Use the obsidian-second-brain skill. Execute /vault-deep-synthesis [topic]:
A focused, topic-driven cross-reference of the existing vault. Unlike /obsidian-synthesize (which scans the whole vault for unnamed patterns unprompted), this takes a topic you name and reads every note touching it to produce one consolidated view. Pure vault: no network, no API keys.
- Resolve the topic from the argument. If none, ask what to synthesize.
- Find every note that references the topic - grep and list exhaustively across whatever top-level note folders the vault actually has (read the vault root once; typically
wiki/,Research/, and any project/concept folders named in_CLAUDE.mdperreferences/folder-map.md- do not assume a fixed list, do not sample; see the anti-fabrication rule). Match by every plausible name, alias, and folder. - Read the matching notes and cross-reference them into:
- What the vault agrees on - claims multiple notes corroborate, with
[[wikilinks]]to each. - Contradictions - where notes disagree; name both
[[notes]]and the specific conflict. Do not resolve them here (that is/obsidian-reconcile); just surface them. - Stale claims - dated facts that may no longer hold (cite the note and the date).
- Coverage gaps - questions the topic raises that the vault does not answer.
- What the vault agrees on - claims multiple notes corroborate, with
- Write the synthesis to the concepts folder (resolved per
references/folder-map.md- wiki-stylewiki/concepts/, Obsidian-styleIdeas/) asYYYY-MM-DD - synthesis - <topic-slug>.md(type: synthesis, tagged[research, thinking, vault-deep-synthesis]), listing the source notes it read in frontmatter. - Do NOT modify the source notes - this command only reads and synthesizes. Append a one-line entry to the operation log.
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: Enumerate the matching notes exhaustively, do not sample - a partial scan reported as complete produces confident wrong answers. Never invent a claim, contradiction, or source; if the vault is thin on the topic, say so. 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.
- 11d ago First seen · 29 lines · 28 tokens per session scan A dd52f628579f
vault-deep-synthesis is a command published in the GitHub repository eugeniughelbur/obsidian-second-brain (4,392 stars, last pushed 4d ago), licensed MIT. It adds 28 tokens to every session and 834 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.