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-synthesize)<a href="https://agentmods.dev/commands/eugeniughelbur/obsidian-second-brain/obsidian-synthesize"><img src="https://agentmods.dev/badge/commands/eugeniughelbur/obsidian-second-brain/obsidian-synthesize/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-synthesize"><img src="https://agentmods.dev/badge/commands/eugeniughelbur/obsidian-second-brain/obsidian-synthesize.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 | $0.00960 |
| Opus 5 | $0.00008 | $0.00480 |
| Sonnet 5 | $0.00003 | $0.00192 |
| Haiku 4.5 | $0.00002 | $0.00096 |
Grade A, and why
obsidian-synthesize 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 /obsidian-synthesize:
This command can run manually or as a scheduled agent. It thinks for you.
-
Read
_CLAUDE.mdfirst if it exists in the vault root -
Read
index.mdto understand all existing pages -
Read recent operation log: if
Logs/exists, read the last 2-3Logs/YYYY-MM-DD.mdfiles; otherwise readlog.md(last 20 entries) -
Scan for synthesis opportunities - spawn parallel subagents:
-
Cross-source agent: read all sources ingested in the last 7 days (
raw/). Find concepts that appear in 2+ unrelated sources. If the same idea shows up in a podcast transcript AND an article AND a daily note - that's a synthesis candidate. -
Entity convergence agent: scan the entities folder (resolved per
references/folder-map.md) for people who appear together in multiple contexts but have no explicit connection page. If Person A and Person B keep showing up in the same projects/decisions - write a connection note. -
Concept evolution agent: scan the concepts folder (resolved per
references/folder-map.md) for ideas that have been updated 3+ times. Track how the concept evolved - write a "Concept Evolution" section showing the timeline of how the user's thinking changed. -
Orphan rescue agent: find notes in any note folder (enumerate the folders present, per
references/folder-map.md) with no incoming links that contain claims or ideas that SHOULD be linked to existing pages. Create the missing links and explain why.
-
-
For each synthesis found:
- Create
Synthesis - Title.mdin the concepts folder (resolved perreferences/folder-map.md) with:--- date: YYYY-MM-DD tags: - concept - synthesis auto_generated: true --- - Document: what pattern was found, which sources/notes it came from (with links), what it means, and a suggested action
- Link the synthesis page FROM all the source notes it references
- Create
-
Update
index.mdwith new synthesis pages -
Append to the operation log: if
Logs/exists write**HH:MM** - synthesize | X synthesis pages created, Y orphans rescued, Z connections foundtoLogs/YYYY-MM-DD.md; otherwise append## [YYYY-MM-DD] synthesize | X synthesis pages created, Y orphans rescued, Z connections foundtolog.md -
If a daily note exists for today, add a Synthesis section with a brief summary
The vault should generate its own insights. Not just when asked - on its own schedule.
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: Search exhaustively before claiming any note, person, or file is absent - false absence is the most common failure mode - and never invent facts, entities, or dates (mark unknowns as TBD). 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 · 53 lines · 16 tokens per session scan A b655ed18a15d
obsidian-synthesize is a command published in the GitHub repository eugeniughelbur/obsidian-second-brain (4,392 stars, last pushed 4d ago), licensed MIT. It adds 16 tokens to every session and 960 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).
cierre
A sales call just ended: turn its transcript into the full follow-up (CRM, tasks, email draft, reminder, coaching).
deconstruct
First-principles analyst: surface hidden assumptions, find foundational truths, rebuild from scratch.
instinct-import
Import a portable YAML instinct pack with confidence-gated merge (Instinct Engine).
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.