breferrari/obsidian-mind

🌐 English | 日本語 | 中文 | 한국어

An Obsidian vault that gives AI coding agents persistent memory. Built for Claude Code, with working hooks for Codex CLI and Gemini CLI. Start a session, talk about your day, and the agent handles the rest — notes, links, indexes, performance tracking. Every conversation builds on the last.

AI coding agents are powerful, but they forget. Every session starts from zero — no context on your goals, your team, your patterns, your wins. You re-explain the same things. You lose decisions made three conversations ago. The knowledge never compounds.

Give your agent a brain.

You: "start session"
Agent: *reads North Star, checks active projects, scans recent memories*
Agent: "You're working on Project Alpha, blocked on the BE contract.
        Last session you decided to split the coordinator. Your 1:1
        with your manager is tomorrow — review brief is ready."

Works with Claude Code (full support), Codex CLI, and Gemini CLI — same hooks, same commands, same vault.

Install via shardmind install or git clone — same vault either way.

Morning kickoff:

/om-standup
# → loads North Star, active projects, open tasks, recent git changes
# → "You have 2 active projects. The auth refactor is blocked on API contract.
#    Your 1:1 with Sarah is at 2pm — last time she flagged observability."

Brain dump after a meeting:

/om-dump Just had a 1:1 with Sarah. She's happy with the auth work but wants
us to add error monitoring before release. Also, Tom mentioned the cache
migration is deferred to Q2 — we decided to focus on the API contract first.
Decision: defer Redis migration. Win: Sarah praised the auth architecture.

→ Updated org/people/Sarah Chen.md with meeting context
→ Created work/1-1/Sarah 2026-03-26.md with key takeaways
→ Created Decision Record: "Defer Redis migration to Q2"
→ Added to perf/Brag Doc.md: "Auth architecture praised by manager"
→ Updated work/active/Auth Refactor.md with error monitoring task

Incident response:

/om-incident-capture https://slack.com/archives/C0INCIDENT/p123456
# → slack-archaeologist reads every message, thread, and profile
# → people-profiler creates notes for new people involved
# → Full timeline, root cause analysis, brag doc entry

End of day:

You: "wrap up"
# → verifies all notes have links
# → updates indexes
# → brag-spotter finds uncaptured wins
# → suggests improvements

npm install -g shardmind
mkdir my-vault && cd my-vault
shardmind install github:breferrari/obsidian-mind

shardmind install writes into the current directory, so create and enter a fresh folder first. The wizard collects your name, organization, vault purpose, agents to include, and whether to enable QMD; ShardMind then initializes git, optionally bootstraps QMD, and personalizes brain/North Star.md with your answers. Then:

1. Open the installed folder as an Obsidian vault
2. Enable the Obsidian CLI in Settings → General (requires Obsidian 1.12+)
3. Run your agent in the vault directory: claude, codex, or gemini. Codex runs the vault's hooks only once the folder is trusted and each hook approved: see Using with Other Agents.
4. Start talking about work

ShardMind is the package manager for Obsidian vault templates. The install adds a .shardmind/ sidecar that powers the wizard, optional modules (skip what you don't use), and three-way-merge upgrades. With every value at its default the install is byte-equivalent to git clone — clone-UX is preserved exactly. Delete .shardmind/ and shard-values.yaml from the installed vault and it keeps working: ShardMind is additive, not load-bearing.

git clone https://github.com/breferrari/obsidian-mind.git

Or use it as a GitHub template. Skip the wizard, get the bare template. Then run through the same 4 steps above, plus fill in brain/North Star.md with your goals (the ShardMind wizard does this for you).

QMD is where most of the agent's retrieval intelligence comes from. Optional in the strict sense — the vault falls back to grep + the Obsidian CLI — but the experience is meaningfully better with it:

• Semantic recall. Find "what did we decide about caching" even when the note is titled "Redis Migration ADR."
• Brain topics available on demand. Your agent is instructed (via AGENTS.md, which points to .claude/rules/brain-topics.md) to consult brain/ guidance through QMD when the conversation touches a listed topic.
• Subagents get sharper context. context-loader, review-prep, brag-spotter, and friends consult QMD first, then fall back to grep.
• Native agent tools via MCP. Registered as a Model Context Protocol server in .mcp.json — when QMD is installed, mcp__qmd__query, mcp__qmd__get, and mcp__qmd__multi_get appear in the agent's tool menu alongside Read and Edit. Subagents, slash commands, and the main conversation all call the same typed contract. Add another MCP-aware tool later (a database, a ticketing system, a calendar) and it plugs in the same way.

npm install -g @tobilu/qmd
node --experimental-strip-types .scripts/qmd-bootstrap.ts

The bootstrap is idempotent — safe to re-run. It resolves this vault's index name — the qmd_index field from vault-manifest.json when set, otherwise the vault folder name slugified — reads qmd_context, registers the collection, attaches the context, and builds the index + embeddings. The SessionStart hook and .mcp.json wrapper both read the same manifest field, so CLI queries, the MCP server, and the re-index all scope to the same named SQLite store. This isolates the vault from any other QMD-using vault on the same machine.

If you want to use a different index name (for example, one vault per engineer on a shared workstation), edit qmd_index in vault-manifest.json before running the bootstrap. Once the store is populated, always pass --index <name> to the CLI:

qmd --index obsidian-mind query "what did we decide about caching"
qmd --index obsidian-mind update   # after bulk edits
qmd --index obsidian-mind embed    # after many new notes

QMD runs three small models locally, so there is no API key to set up, no per-query cost, and it works offline:

They download on first use and are cached. QMD offloads to the GPU when it finds one — CUDA on a discrete card, Metal on Apple Silicon — and falls back to CPU otherwise. Check what yours is doing with qmd doctor.

Use qmd 2.5.1 or later. In 2.1, qmd status probes the GPU, and on a machine without one that can take several seconds (4 to 37 s on CI runners, measured 2026-10-13, #349). SessionStart's self-heal reads qmd status under a 5-second limit, so a status that times out leaves it unable to see a broken install.

The three CLI verbs map onto that stack, cheapest first: qmd search is BM25 keywords with no model at all, qmd vsearch is vector-only, and qmd query is the full hybrid. If you want to avoid the larger downloads, search alone is genuinely useful.

The om server sends a lexical and a vector sub-query, so retrieval finds the note that answers your question even when it shares no keywords with it. Practical consequences worth knowing:

• Reads are the expensive side, not writes. A query embeds locally before it can search, so recall with a query takes a couple of seconds while recall without one is near-instant. search over notes is fast — it is the vector step that costs.
• Writing a memory does not wait for the model. The index update is synchronous, so a new memory is immediately retrievable; generating its vector happens in the background, because that only affects where it ranks, not whether it is found.
• No index, no problem. Without QMD the server falls back to lexical matching. Ordering gets worse; nothing disappears.

• Obsidian 1.12+ (for CLI support)
• An AI coding agent: Claude Code (full support), Codex CLI, or Gemini CLI
• Node 22+ LTS (for hook scripts — typically already installed alongside Claude Code / Codex / Gemini CLI)
• Git (for version history)
• QMD (optional, for semantic search)

Note on the Node flag. Hook scripts execute TypeScript directly via Node's --experimental-strip-types flag, stable in Node 22.6+ (Aug 2024) and the default behaviour in Node 23.6+. The flag is marked experimental but has been unchanged across 22 LTS and 24 LTS; if a future Node release retires or renames it, hook commands in .claude/settings.json, .codex/hooks.json, and .gemini/settings.json need a one-line update.

Procedural code owns the environment. The agent owns content. The hooks in .claude/scripts/ handle classification, validation, indexing, and lifecycle injection — deterministic, testable, runs the same for every agent. Writing notes, filing them, linking them, drafting briefs — those are judgments, and they stay with the agent. The two halves meet at small handoffs (hooks inject context, agent reads the vault) so neither has to do the other's job.

Folders group by purpose. Links group by meaning. A note lives in one folder (its home) but links to many notes (its context). Your agent maintains this graph — linking work notes to people, decisions, and competencies automatically. When review season arrives, the backlinks on each competency note are already the evidence trail. A note without links is a bug.

Vault-first memory keeps context across sessions and machines. All durable knowledge lives in brain/ topic notes (git-tracked, Obsidian-browsable, linked). Claude Code's MEMORY.md (~/.claude/) is an auto-loaded index that points to vault locations — never the storage itself. This means memories survive machine changes and are part of the graph.

Sessions have a designed lifecycle. The SessionStart hook auto-injects your North Star goals, active projects, recent changes, open tasks, and the full vault file listing — your agent starts every session with context, not a blank slate. At the end, say "wrap up" and the agent runs /om-wrap-up — verifying notes, updating indexes, and spotting uncaptured wins. The AGENTS.md operating manual governs everything in between: where to file things, how to link, when to split a note, what to do with decisions and incidents.

The lifecycle hooks handle routing automatically:

On Claude Code 2.1.287 or later, the vault also ships a mod: .claude/skills/obsidian-mind/, a plugin whose code runs inside Claude Code. It runs the vault's own hook scripts and changes only how their output reaches the session:

• Session context arrives as an instruction file, the way AGENTS.md does. It is re-read whole after compaction and /clear (as hook output it shrinks to a pointer), it reaches general-purpose subagents (hook output never does), and it is not cut at Claude Code's 10,000-character hook limit. Its budget is eager_layer_instruction_budget_bytes in vault-manifest.json; sections that never shrink, such as open tasks, can still take it past that. /memory lists it as .claude/session-context.md.
• The Stop report becomes one line under the answer. When the findings change you see a line beneath Claude's reply, starting with the mod's name — obsidian-mind: vault check: …. Claude Code joins the names of the plugins that answered on Stop with +, so when another plugin also answers, the label reads obsidian-mind+<plugin>: vault check: …. Claude gets the full report with your next message, unseen. A finding marked urgent gets Claude's attention at once instead, once per message you send (a second one waits inside the report); the template's own report has none.

For each event it handles, the mod tells the matching hook to stand down. Wherever the mod does not load, the hooks run exactly as before: Codex and Gemini, older Claude Code, a session started in a vault subfolder (launch from the vault root, or /cd there and /clear), or a folder you have not trusted. It loads only after you accept Claude Code's trust prompt for the vault.

A mod is unsandboxed code that runs with your permissions, so check what it does before trusting the folder: claude plugin validate .claude/skills/obsidian-mind lists every event it hooks and every call it makes (it runs the vault's own scripts, writes the context file, remembers in its own store which report each session was shown, and can submit a prompt for an urgent finding, nothing else). To turn it off, add "enabledPlugins": { "obsidian-mind@skills-dir": false } to .claude/settings.local.json.

The two lines that matter in its output, for this version of the mod:

  ❯ ./register.ts hooks: classic.SessionStart, prompt.context, classic.Stop, turn.complete, prompt.submit, turn.start
  ❯ ./register.ts calls: $.fs.write, $.process.run (via runScript), $.prompt.submit, $.session.root, $.state.get, $.state.set, $.store.get (via setShown, shownFor), $.store.set (via setShown), $.ui.invalidate

obsidian-mind does not dump your entire vault into context. It uses tiered loading to keep token costs low:

SessionStart loads lightweight context — small excerpts from key files, filenames, and git summary — not full note contents. Five mechanisms keep the eager layer honest as the vault grows: source-aware injection (resume/compact re-inject only volatile sections — the static bulk is already in-conversation), an injection-size meter as the last line of every injection (you always see what context costs), an injection budget that enforces what the meter measures (over the ceiling, the cheapest-to-lose sections degrade to pointers — and the meter names every one it dropped, because a silent loss is worse than the bloat), a single hook spawn per write (the QMD refresh rides the validation hook), and listing collapse (any folder past a note-count threshold folds to one count line, so a vault can't outgrow the ceiling through whichever folder nobody thought to configure). Both the budget and the threshold are tunable in vault-manifest.json, and the budget is held under Claude Code's 10,000-character hook output cap whatever it is set to, because past the cap a session receives only a 2,000-character preview. The agent queries by meaning via QMD before reading files, so it pulls only what's relevant. The classification hook is one lightweight Node call per message. The validation hook only fires on markdown writes and skips excluded paths.

obsidian-mind works with Claude Code, Codex CLI, Gemini CLI, Antigravity and Grok. Every agent reads one instruction file, AGENTS.md. The hook scripts in .claude/scripts/ and the commands in .claude/commands/ are agent-agnostic — pure Markdown, TypeScript, and shell with no SDK dependencies. .claude/rules/ holds guidance only Claude Code can use (its skills, subagents, auto-memory index, hooks and mod), and the sections AGENTS.md moved out to stay under its size cap. Claude Code and Grok load every file there at session start, so Claude keeps the whole manual; the other agents read a moved section when AGENTS.md points them to it.

Observed with scratch vaults as of 2026-10-06 (Claude Code 2.1.291, Codex CLI 0.160.0, Gemini CLI 0.37.1 discovery log, Antigravity 1.3.0, Grok 1.0.46); the measurements are in #321. A test keeps AGENTS.md under 22,000 bytes, so no agent cuts it off.

Claude Code — full support. Hooks, commands, subagents, and the memory system all work out of the box.

Codex CLI — hook config at .codex/hooks.json wires the same hook scripts Claude Code uses — session context, message classification, and write validation work automatically. Commands work as regular prompts (e.g. type om-standup without the / prefix).

Codex runs a project's hooks only once two kinds of trust are in place (observed with Codex CLI 0.160.0 as of 2026-10-13, #345):

• The vault folder is trusted. Codex records this in ~/.codex/config.toml under [projects.'<path>']. On Windows the key is the \\?\-prefixed path, e.g. [projects.'\\?\C:\path\to\vault'].
• Each hook is approved. Codex stores each approval as a trusted_hash under [hooks.state]. Approving them in an interactive codex session is expected to write these (inferred: the #345 check stood in for them with --dangerously-bypass-hook-trust, a flag for one non-interactive run).

Until both are in place, Codex runs no hook, and the session gets no vault context.

Gemini CLI — hook config at .gemini/settings.json maps Gemini's event names to the shared hook scripts, and its context.fileName setting points Gemini at AGENTS.md. Gemini reads custom commands only as TOML, so .gemini/commands/ holds a generated wrapper per command that injects the command's .md (node --experimental-strip-types .scripts/gemini-commands.ts regenerates them).

Antigravity and Grok — read AGENTS.md for vault conventions. Their hook, skill and command layers are tracked in #322 and #323.

Other agents (Cursor, Windsurf, GitHub Copilot, JetBrains AI) — read AGENTS.md for vault conventions. Hook support varies by agent.

Your vault normally only helps while you are sitting in it. The om MCP server changes that: a coding session in any other repository can search your notes, read them, follow the graph, and record what it learned back into the vault.

claude mcp add --scope user om node "/absolute/path/to/your-vault/.claude/scripts/om-mcp.mjs"

User scope is the right default here: it registers in your own config, so the server is available in every directory on the machine with nothing added to any repository. No env var is needed either, because the launcher resolves the vault from its own location.

{
  "mcpServers": {
    "om": {
      "command": "node",
      "args": ["/absolute/path/to/your-vault/.claude/scripts/om-mcp.mjs"]
    }
  }
}

Add this to that project's own instruction file (CLAUDE.md or AGENTS.md), filling in the triggers:

## Where design decisions live

Design rationale for this project is recorded outside this repo, reachable
through the `om` MCP server.

- **`search`** reaches the written record: why a choice was made, what was
  rejected, what a constraint was set against. **Start here.**
- **`expand`** shows a known note's links and backlinks, which is cheaper than
  searching again for its neighbourhood.
- **`recall`** returns short durable lessons scoped to this project. It is empty
  until sessions put things in it, so early on it returns nothing, and that is
  *not* evidence the record is missing.
- **`health`** when something that should be there cannot be found. Every failure
  in this layer looks identical from outside (no results), and this tells them
  apart.

Consult the record before changing:

- <the storage format or schema>
- <the ID or key semantics>
- <the public surface: CLI flags, API shape, exported names>

If that record and this repo disagree, the record holds the *why*. Reconcile
before changing behaviour.

**Say what came back, in whatever you write before implementing:** a plan, a
design note, an issue comment. Name the recorded decisions the work rests on,
anything you found that argues *against* the approach, and an explicit "nothing
recorded on this" when the record is empty, which is a finding rather than a
blank to skip. Consulting once at the start of a task is consulting at the
moment you know least about what you will need; writing the result down moves it
to the moment you commit, while a contradiction is still free to fix.

## Recording what you learn

Two tools, and picking the wrong one is the common mistake. The test is whether
it would help someone working on a **different** project.

- **`remember`** stores a durable lesson: a constraint you discovered, a gotcha
  that cost time, a rule that generalises. Set `confidence`
  (`verified` / `inferred` / `unverified`) honestly and supply `verification`
  when you claim `verified`. For something specific to this project use
  `scope: "project"` with `projects: ["<this-repo>"]`. Reach for
  `scope: "platform"` before `"general"`: a dependency's quirk or a language's
  rule is platform-level however hard-won, and `general` claims it would help
  someone whose stack shares nothing with yours. When you do claim `general`,
  supply `generality` saying why, the same way `verification` backs `verified`.
- **`record_work`** files what happened *here*: changes, decisions and the
  alternatives rejected, what was learned, what is still open, how it was
  verified.

A dependency limitation that would bite any project is a `remember`. "Landed the
watch engine and here is what it cost" is a `record_work`. Do both when both are
true.

Three to five triggers, and name specific nouns. Consult it before changing the storage format, ID semantics, or the CLI surface works. Check the vault for context is exactly the advisory phrasing that gets skipped, because it gives the model nothing to match against the task in front of it.

Anchor the consultation to an artifact, not to a moment. "Consult before changing X" fires once, at the start of a task, which is when the session knows least about what it will need. Requiring the result to appear in whatever the project writes before implementing turns consultation from something a session intends to do into something an artifact is incomplete without. Measured across a day of real use: captures ran roughly four times heavier than consultations, because remember fires on an event (you just learned something) while consulting fires on intention. Event-triggered behaviour happens; intention-triggered behaviour decays.

What the session gets: search (semantic + keyword), expand (a note's links and backlinks), recall (durable lessons scoped to that repo), remember (record a lesson), record_work (file what happened), reason (judgement across several notes), and health (is the wiring intact?). Plus your notes as readable resources.

reason is the one that thinks. The others retrieve; this one reads the vault with a second Claude session and answers questions that need judgement across notes — is what I am about to do consistent with what these six notes decided? It seeds itself from search, so you never have to search first. It runs on your own CLI default model, so the vault answers at the level you are already working at, and nothing about it is capped: it is Claude, on your machine, under your auth. Every call is logged with its cost, turns, model and wall time. Its answers are marked confidence: inferred and are never recorded as memories on their own — your session decides whether any of it is worth keeping.

Repos are identified by folder name, which is right until it isn't — two repos both called api share one identity and therefore each other's memories. Drop a .om-project file with a distinct name at the repo root to separate them; health tells you which repo it thinks is calling and where that name came from.

Cross-repo memory with an epistemic contract. A lesson learned in one repo reaches the repos it was scoped to and no others. Reach is declared at write time, never guessed at read time, so a sibling project does not inherit another's constraints. Everything recorded carries confidence: verified | inferred | unverified, dated volatile facts, and provenance derived server-side — a session cannot claim to be a project it is not. Corrections supersede rather than overwrite, so the store gets more trustworthy as it grows instead of accumulating contradictions.

Which notes it serves. Your vault, your notes, your session — the default is simply what your vault already declares as your content (user_content_roots), at the granularity you wrote it (work/active/, not all of work/). Set mcp_exposed_roots in vault-manifest.json only if this vault holds material that is not yours to share — employer-confidential notes, a client's data. A note tagged private is never served, and memories are never served as ordinary notes, since they carry their own scope. One case reads across the two: when a capture's promoted: marker carries an anchor, recall serves that block out of brain/ so a foreign repo gets the corrected version rather than the capture as first written — bounded by this same policy, so a private or withheld note is refused there too.

Every read is logged with the calling repo, so "what did that session actually see" is answerable afterwards.

Want the mechanics? ARCHITECTURE.md → Reaching the Vault From Another Repo walks the whole layer with diagrams: the four MCP surfaces and why the non-tool ones matter, the identity handshake, a search call traced end to end, how each memory's reach is evaluated, the write path, and every failure mode against the signal that reveals it.

Morning: Run /om-standup. Your agent loads your North Star, active projects, open tasks, and recent changes. You get a structured summary and suggested priorities.

Throughout the day: Talk naturally. Mention a decision you made, an incident that happened, a 1:1 you just had, a win you want to remember. The classification hook nudges the agent to file each piece correctly. For bigger brain dumps, use /om-dump and narrate everything at once.

End of day: Say "wrap up" and the agent invokes /om-wrap-up — verifies notes, updates indexes, checks links, spots uncaptured wins.

Weekly: Run /om-weekly for cross-session synthesis — North Star alignment, patterns, uncaptured wins, and next-week priorities. Run /om-vault-audit to catch orphan notes, broken links, and stale content.

Review season: Run /om-review-brief manager and get a structured review prep document with all the evidence already linked.

Defined in .claude/commands/. Run them in Claude Code, Codex CLI, or Gemini CLI.

Specialized agents that run in isolated context windows. They handle heavy operations without polluting your main conversation.

The vault doubles as a performance tracking system:

1. Competency notes in perf/competencies/ define your org's competency framework — one note per competency
2. Work notes link to competencies in their ## Related section, annotated with what was demonstrated
3. Backlinks accumulate automatically — review prep becomes reading the backlinks panel on each competency note
4. Brag Doc aggregates wins per quarter with links to evidence notes
5. /om-peer-scan deep-scans a colleague's GitHub PRs and writes structured evidence to perf/evidence/
6. /om-review-brief generates a full review brief by aggregating everything: brag entries, decisions, incidents, competency evidence, and 1:1 feedback

The bases/ folder contains database views that query your notes' frontmatter properties. They update automatically as notes change.

Home.md embeds these views, making it the vault's dashboard.

Home.md                 Vault entry point — embedded Base views, quick links
AGENTS.md               Operating manual — read by every agent, every session
vault-manifest.json     Template metadata — version, structure, schemas
.shardmindignore        Files excluded from `shardmind install` (CONTRIBUTING, translations, marketing media)
CHANGELOG.md            Version history
CONTRIBUTING.md         Template development checklist
README.md               Product documentation
LICENSE                 MIT license

bases/                  Dynamic database views (Work Dashboard, Incidents, People, etc.)

work/
  active/               Current projects (1–3 files at a time)
  archive/YYYY/         Completed work, organized by year
  incidents/            Incident docs (main note + RCA + deep dive)
  1-1/                  1:1 meeting notes — named <Person> YYYY-MM-DD.md
  Index.md              Map of Content for all work

org/
  people/               One note per person — role, team, relationship, key moments
  teams/                One note per team — members, scope, interactions
  People & Context.md   MOC for organizational knowledge

perf/
  Brag Doc.md           Running log of wins, linked to evidence
  brag/                 Quarterly brag notes (one per quarter)
  competencies/         One note per competency (link targets)
  evidence/             PR deep scans, data extracts for reviews
  <cycle>/              Review cycle briefs and artifacts

brain/
  North Star.md         Goals and focus areas — read every session
  Memories.md           Index of memory topics
  Key Decisions.md      Significant decisions and their reasoning
  Patterns.md           Recurring patterns observed across work
  Gotchas.md            Things that have gone wrong and why
  Skills.md             Custom workflows and slash commands

reference/              Codebase knowledge, architecture maps, flow docs
thinking/               Scratchpad for drafts — promote findings, then delete
templates/              Obsidian templates with YAML frontmatter

.claude/
  rules/                Claude Code-only guidance, loaded beside AGENTS.md
  commands/             20 slash commands
  agents/               10 subagents
  scripts/              Hook scripts + charcount.ts utility
  skills/               Obsidian + QMD skills, and the obsidian-mind mod
  settings.json         5 hooks configuration

.scripts/                Vault-level tooling — QMD bootstrap (run once on a fresh clone)

.shardmind/             ShardMind sidecar — only used if installed via `shardmind install`
  shard.yaml            Manifest (name, version, modules, hooks)
  shard-schema.yaml     Wizard values + module gating
  hooks/                bootstrap (git init + QMD), personalize (North Star), post-update

Templates with YAML frontmatter, each including a description field for progressive disclosure:

• Work Note — date, description, project, status, quarter, tags
• Decision Record — date, description, status (proposed/accepted/deprecated), owner, context
• Thinking Note — date, description, context, tags (scratchpad — delete after promoting)
• Competency Note — date, description, current-level, target-level, proficiency table
• 1:1 Note — date, person, key takeaways, action items, quotes
• Incident Note — date, ticket, severity, role, timeline, root cause, impact

kepano/obsidian-skills pre-installed in .claude/skills/:

• obsidian-markdown — Obsidian-flavored markdown (wikilinks, embeds, callouts, properties)
• obsidian-cli — CLI commands for vault operations
• obsidian-bases — Database-style .base files
• json-canvas — Visual .canvas file creation
• defuddle — Web page to markdown extraction

A custom skill in .claude/skills/qmd/ that teaches the agent to use QMD semantic search proactively — before reading files, before creating notes (to check for duplicates), and after creating notes (to find related content that should link to it).

This is a starting point. Adapt it to how you work:

The easiest way — just tell your agent:

Update this vault to the latest obsidian-mind from https://github.com/breferrari/obsidian-mind

The agent will pull the latest changes, resolve conflicts, and update infrastructure files. Works with Claude Code, Codex CLI, or Gemini CLI.

If you cloned the repo directly:

cd your-vault
git pull origin main

New files appear automatically and hook scripts are updated in place. If you edited CLAUDE.md, the pull stops on it, because you changed a file the template deleted: move your additions out as Troubleshooting describes, then delete it.

If you forked the repo:

git remote add upstream https://github.com/breferrari/obsidian-mind.git
git fetch upstream
git merge upstream/main

Resolve any conflicts in files you customized (typically AGENTS.md, brain/ notes; a CLAUDE.md you edited conflicts with its deletion, see Troubleshooting). Infrastructure files (.claude/scripts/, .codex/, .gemini/) should merge cleanly.

Already cloned obsidian-mind and want the wizard, optional modules, and three-way-merge upgrades without losing your customizations? shardmind adopt reconciles your existing vault into a managed v6 install — keeping every byte of your edits and only adding the .shardmind/ sidecar + shard-values.yaml:

npm install -g shardmind
shardmind adopt github:breferrari/obsidian-mind

The 2-way diff UI walks you through any local changes, asks per-file what to keep, then writes the engine metadata. Result: a v6-managed vault with your existing content intact, ready for shardmind update from there forward. No re-cloning.

Using a pre-v5 obsidian-mind, or migrating from a totally different Obsidian vault? The /om-vault-upgrade command migrates your content into the latest template:

# 1. Clone the latest obsidian-mind
git clone https://github.com/breferrari/obsidian-mind.git ~/new-vault

# 2. Open it in your agent
cd ~/new-vault && claude   # or codex, or gemini

# 3. Run the upgrade pointing to your old vault
/om-vault-upgrade ~/my-old-vault

The agent will:

1. Detect your vault version (v1–v3.x, or identify it as a non-obsidian-mind vault)
2. Inventory every file — classify as user content, scaffold, infrastructure, or uncategorized
3. Present a migration plan — you see exactly what will be copied, transformed, and skipped
4. Execute after your approval — transforms frontmatter, fixes wikilinks, rebuilds indexes
5. Validate — checks for orphans, broken links, missing frontmatter

Your old vault is never modified. Use --dry-run to preview the plan without executing.

Claude Code ignores the vault's conventions. Claude Code reads a CLAUDE.md in place of AGENTS.md and skips AGENTS.md without saying so. Two ways that happens:

• A leftover CLAUDE.md in the vault. An update keeps a CLAUDE.md you edited. The session hygiene flags say CLAUDE.md present beside AGENTS.md, and /om-vault-upgrade lists it under Move out. Move what you added to .claude/rules/local.md (or into AGENTS.md if every agent needs it, keeping AGENTS.md under 23 KB, where the hygiene flags start: Antigravity stops reading it at ~24,000 bytes), then delete CLAUDE.md. Nothing is merged automatically.
• A CLAUDE.md in a folder above the vault. Claude Code reads that one too, and AGENTS.md is skipped. The hygiene flag cannot see it, because it checks the vault root only. Move the vault out from under that folder, or move that file's content somewhere it applies only where you want it.

Gemini CLI loads no instructions when started in a vault subfolder. Gemini's context search walks up the folders, but its settings lookup does not, so a session started in a subfolder never reads the vault's .gemini/settings.json and never learns to look for AGENTS.md. Start Gemini from the vault root.

Gemini ignores what you added to GEMINI.md. Gemini now reads AGENTS.md (through .gemini/settings.json), so a leftover GEMINI.md is never loaded. The hygiene flags say GEMINI.md present beside AGENTS.md, and /om-vault-upgrade lists it under Move out. Move your additions to AGENTS.md, then delete it.

Grok reads nothing from the vault. Grok loads project instructions only from a trusted folder. Trust the vault once: run /hooks-trust in a Grok session, or launch with --trust. One grant covers MCP, LSP, hooks, project instructions and project skills.

Issues and bug reports welcome. Code contributions go through assignment: comment on an issue to ask for it, and open a PR once it's assigned to you. A PR for an issue not assigned to you is closed without review. See CONTRIBUTING.md.

• kepano/obsidian-skills — Official Obsidian agent skills
• James Bedford — Vault structure philosophy, separation of AI-generated content
• arscontexta — Progressive disclosure via description fields, session hooks

Created by Brenno Ferrari — Senior iOS Engineer in Berlin, building developer tools with Claude Code.

MIT