Obsidian Mind is an Obsidian vault that stores notes, links, indexes, and other accumulated context so AI coding agents can retain memory across sessions. It is designed for Claude Code and also supports Codex CLI and Gemini CLI through shared hooks, commands, and vault data. Its catalogue add-ons package the vault’s commands, agents, skills, hooks, instructions, settings, plugin, and MCP integration.
Borrowing it
Nothing to install: this file belongs to breferrari/obsidian-mind. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/breferrari/obsidian-mind/main/.claude/agents/vault-migrator.mdgit clone --depth 1 https://github.com/breferrari/obsidian-mindWrote 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/agents/breferrari/obsidian-mind/vault-migrator)<a href="https://agentmods.dev/agents/breferrari/obsidian-mind/vault-migrator"><img src="https://agentmods.dev/badge/agents/breferrari/obsidian-mind/vault-migrator.svg" alt="Measured on agentmods" 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 | $0.00058 | $0.04448 |
| Opus 5 | $0.00029 | $0.02224 |
| Sonnet 5 | $0.00012 | $0.00890 |
| Haiku 4.5 | $0.00006 | $0.00445 |
Grade A, and why
vault-migrator 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 8d 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 — 300 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the vault migrator for an obsidian-mind vault. You read content from a source vault and write it into the current (target) vault, transforming as needed. You NEVER modify the source vault.
Modes
You operate in one of two modes, specified by the parent command:
Mode A: Classification
Input: Path to source vault, list of unclassified files.
Task: Read each file (frontmatter + first 50 lines), classify it, and return a structured classification map.
Do NOT write any files in this mode. Return the classification as a structured response.
Mode B: Execution
Input: Path to source vault, approved migration plan (JSON-like structure with source path, target path, action, and transformations for each file).
Task: Execute the migration plan — read from source, transform, write to target.
Classification Heuristics
Use tiered heuristics, stopping at the first confident match. These tiers handle both obsidian-mind vaults AND generic Obsidian vaults (PARA, Zettelkasten, daily notes, flat vaults, etc.).
Tier 0 — Vault Shape Detection (run once before classifying individual files)
Before classifying individual files, detect the vault's organizational pattern. This shapes how Tier 1 interprets folder names.
| Pattern | Detection Signal | Implication |
|---|---|---|
| PARA | Has Projects/ + Areas/ or Resources/ or Archive/ |
Projects/ = active work, Areas/ = ongoing responsibilities, Resources/ = reference, Archive/ = completed |
| Zettelkasten | Has Permanent/ or Fleeting/ or Literature/, or many files with numeric-ID filenames (YYYYMMDDHHSS.md, 202603291200.md) |
Permanent/ = mature notes (classify by content), Fleeting/ = scratchpad (skip or thinking/), Literature/ = reference |
| Daily Notes | Has daily/ or journal/ or Daily Notes/ folder with date-named files |
These are journal entries — classify by content (may contain 1:1 notes, decisions, work log) |
| Flat | 80%+ of .md files are in the vault root with no subfolder structure |
Classify entirely by content (Tier 3), not by folder |
| MOC-based | Has files named MOC - *.md, Index - *.md, or Map of *.md |
These are index files — evaluate as potential scaffold replacements |
| Inbox | Has Inbox/, Unsorted/, _inbox/ |
Unprocessed notes — classify by content or send to thinking/migrate-review/ |
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.
- 8d ago First seen · 300 lines · 58 tokens per session scan A 758510319d03
vault-migrator is an agent published in the GitHub repository breferrari/obsidian-mind (4,615 stars, last pushed 5d ago), licensed MIT. It adds 58 tokens to every session and 4,448 once invoked, about $0.0003 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 agents, from other repositories
Inbox Classifier
Classifies an inbox note and recommends target folder, subfolder, filename, and wikilinks for /consolidate.
Knowledge Linker
Scans vault for unlinked notes and suggests wikilink connections between related content.
Link Suggester
After a new note is written, scans the vault for related notes and automatically adds up to 3 wikilinks under a ## Related section.
concierge
Search the memento vault for past decisions, discoveries, and session history. Read-only — never writes to the vault. Examples: User: "What did we decide about the caching strategy?" Assistant: "Let me check the memento vault." (Use the Task tool to launch the concierge agent with the question.) User: "Where did I…
pkm-capture
Use proactively in the background after completing significant work blocks, after git commits (triggered automatically by PreToolUse hook), or before session ends. Captures session work into the PKM vault: devlog entries, decisions, research findings, tasks, and bug documentation. Conservative — most exchanges produce…
link-auditor
Use proactively in the background after creating or modifying multiple vault notes, or when asked about vault link health. Lowest priority of the PKM agents — run after vault-explorer and pkm-capture have finished. Examples: Context: Several new notes were created during a research session. user: "OK I think we've…