breferrari/obsidian-mind
A self-organizing Obsidian vault that gives AI coding agents persistent memory. Claude Code, Codex CLI, Gemini CLI.
ARCHETYPE
Orchestrator
A bench of specialised subagents. The main agent mostly delegates.
Copy this rig
# review before running: this installs third-party code
$ npx degit breferrari/obsidian-mind/.claude ./rig-obsidian-mind # inspect, then merge into .claude/ MCP servers are added to Claude Code at local scope; env vars are shown as YOUR_… placeholders — we never store values. Files are fetched with degit into a separate folder so you can review before merging.
$ npx degit breferrari/obsidian-mind/.claude/skills/defuddle .claude/skills/defuddle $ npx degit breferrari/obsidian-mind/.claude/skills/excalidraw-diagram .claude/skills/excalidraw-diagram $ npx degit breferrari/obsidian-mind/.claude/skills/json-canvas .claude/skills/json-canvas $ npx degit breferrari/obsidian-mind/.claude/skills/mermaid-visualizer .claude/skills/mermaid-visualizer $ npx degit breferrari/obsidian-mind/.claude/skills/obsidian-bases .claude/skills/obsidian-bases $ npx degit breferrari/obsidian-mind/.claude/skills/obsidian-cli .claude/skills/obsidian-cli $ npx degit breferrari/obsidian-mind/.claude/skills/obsidian-markdown .claude/skills/obsidian-markdown $ npx degit breferrari/obsidian-mind/.claude/skills/qmd .claude/skills/qmd
$ curl -fsSL --create-dirs -o .claude/agents/brag-spotter.md https://raw.githubusercontent.com/breferrari/obsidian-mind/main/.claude/agents/brag-spotter.md $ curl -fsSL --create-dirs -o .claude/agents/context-loader.md https://raw.githubusercontent.com/breferrari/obsidian-mind/main/.claude/agents/context-loader.md $ curl -fsSL --create-dirs -o .claude/agents/correction-sweep.md https://raw.githubusercontent.com/breferrari/obsidian-mind/main/.claude/agents/correction-sweep.md $ curl -fsSL --create-dirs -o .claude/agents/cross-linker.md https://raw.githubusercontent.com/breferrari/obsidian-mind/main/.claude/agents/cross-linker.md $ curl -fsSL --create-dirs -o .claude/agents/people-profiler.md https://raw.githubusercontent.com/breferrari/obsidian-mind/main/.claude/agents/people-profiler.md $ curl -fsSL --create-dirs -o .claude/agents/review-fact-checker.md https://raw.githubusercontent.com/breferrari/obsidian-mind/main/.claude/agents/review-fact-checker.md $ curl -fsSL --create-dirs -o .claude/agents/review-prep.md https://raw.githubusercontent.com/breferrari/obsidian-mind/main/.claude/agents/review-prep.md $ curl -fsSL --create-dirs -o .claude/agents/slack-archaeologist.md https://raw.githubusercontent.com/breferrari/obsidian-mind/main/.claude/agents/slack-archaeologist.md $ curl -fsSL --create-dirs -o .claude/agents/vault-librarian.md https://raw.githubusercontent.com/breferrari/obsidian-mind/main/.claude/agents/vault-librarian.md $ curl -fsSL --create-dirs -o .claude/agents/vault-migrator.md https://raw.githubusercontent.com/breferrari/obsidian-mind/main/.claude/agents/vault-migrator.md
This rig commits no guardrails. Here is the community baseline instead — the deny/ask rules most often found across all 7,204 rigs:
{
"permissions": {
"deny": [
"Read(./.env)",
"Read(**/.env)",
"Read(~/.ssh/**)",
"Bash(rm -rf *)",
"Read(**/*.pem)",
"Bash(rm -rf /)",
"Bash(git push --force:*)",
"Bash(sudo *)",
"Read(.env)",
"Bash(rm -rf /*)",
"Read(./.env.*)",
"Read(~/.aws/**)",
"Bash(git push --force*)",
"Bash(rm -rf:*)",
"Read(**/*.key)",
"Read(**/.env.*)",
"Bash(sudo:*)",
"Bash(git reset --hard*)",
"Bash(git reset --hard:*)",
"Read(.env.*)"
],
"ask": [
"Bash(git push:*)",
"Bash(git push *)",
"Bash(git commit:*)",
"Bash(rm *)",
"Bash(rm:*)",
"Bash(git rebase *)",
"Bash(wget *)",
"Bash(npm publish:*)",
"Bash(git commit *)",
"Bash(gh pr merge *)"
]
}
} MCP servers (1)
| server | source | est. tokens |
|---|---|---|
| qmd | local / custom | 2.5k |
Skills (8)
defuddleexcalidraw-diagramjson-canvasmermaid-visualizerobsidian-basesobsidian-cliobsidian-markdownqmd
Subagents (10)
| brag-spotter model: sonnet | Proactively scans for achievements and wins that aren't in the brag doc yet. Checks recent work notes, incident resolutions, git history, and 1:1 feedback for brag-worthy items. |
| context-loader model: sonnet | Load all vault context about a specific topic — person, project, incident, team, or concept. Gathers notes, backlinks, mentions, timeline, and produces a synthesized briefing. |
| correction-sweep model: sonnet | Find every note restating a corrected fact and classify each as authoritative, restatement, or historical. Discovery and judgement only — never edits. Invoked by /om-correct, or when a fact has been c |
| cross-linker model: sonnet | Scan recent or specified notes for missing wikilinks. Finds mentions of people, projects, teams, competencies, and incidents that should be linked but aren't. Suggests missing bidirectional links for |
| people-profiler model: sonnet | Bulk create or update person notes from Slack profiles. Given user IDs or names, checks Slack for role/title/team, checks vault for existing notes, creates missing ones, updates stale ones, and update |
| review-fact-checker model: sonnet | Verify every factual claim in a review draft against vault sources. Returns verified/unverified/flagged claims. |
| review-prep model: sonnet | Aggregate performance review material from the vault for a given period. Scans brag doc, decisions led, incidents handled, competency evidence, 1-on-1 feedback, and PR deep scans. Invoke via /om-revie |
| slack-archaeologist model: sonnet | Deep reconstruction of Slack conversations. Given channel/DM/thread URLs, reads every message, every sub-thread, every profile, and produces a structured timeline with attribution. Use for incident re |
| vault-librarian model: sonnet | Run vault maintenance: detect orphan notes, find broken wikilinks, validate frontmatter completeness, flag stale active notes, check cross-linking integrity. Invoke via /om-vault-audit or when the use |
| vault-migrator model: sonnet | Classify, transform, and migrate vault content from a source vault into this obsidian-mind instance. Two modes: classification (analyze source, return map) and execution (given approved plan, perform |
Hooks (5)
| event | matcher | runs |
|---|---|---|
| SessionStart | startup|resume|clear|compact | node --disable-warning=ExperimentalWarning --experimental-strip-types "$(r="${CLAUDE_PROJECT_DIR:-.}"; d="$r"; while [ ! -f "$d/vault-manifest.json" ] && p="$(dirname "$d")" && [ "$d" != "$p" ]; do d="$p"; done; [ -f "$d/vault-manifest.json |
| UserPromptSubmit | * | node --disable-warning=ExperimentalWarning --experimental-strip-types "$(r="${CLAUDE_PROJECT_DIR:-.}"; d="$r"; while [ ! -f "$d/vault-manifest.json" ] && p="$(dirname "$d")" && [ "$d" != "$p" ]; do d="$p"; done; [ -f "$d/vault-manifest.json |
| PostToolUse | Write|Edit | node --disable-warning=ExperimentalWarning --experimental-strip-types "$(r="${CLAUDE_PROJECT_DIR:-.}"; d="$r"; while [ ! -f "$d/vault-manifest.json" ] && p="$(dirname "$d")" && [ "$d" != "$p" ]; do d="$p"; done; [ -f "$d/vault-manifest.json |
| PreCompact | * | node --disable-warning=ExperimentalWarning --experimental-strip-types "$(r="${CLAUDE_PROJECT_DIR:-.}"; d="$r"; while [ ! -f "$d/vault-manifest.json" ] && p="$(dirname "$d")" && [ "$d" != "$p" ]; do d="$p"; done; [ -f "$d/vault-manifest.json |
| Stop | * | node --disable-warning=ExperimentalWarning --experimental-strip-types "$(r="${CLAUDE_PROJECT_DIR:-.}"; d="$r"; while [ ! -f "$d/vault-manifest.json" ] && p="$(dirname "$d")" && [ "$d" != "$p" ]; do d="$p"; done; [ -f "$d/vault-manifest.json |
Slash commands (20)
/om-capture-1on1/om-correct/om-dump/om-humanize/om-incident-capture/om-intake/om-meeting/om-peer-scan/om-prep-1on1/om-project-archive/om-review-brief/om-review-peer/om-self-review/om-slack-scan/om-standup/om-tidy/om-vault-audit/om-vault-upgrade/om-weekly/om-wrap-up
Similar rigs
kepano/obsidian-skills
Agent skills for Obsidian. Teach your agent to use Obsidian CLI and open formats including Markdown, Bases, JSON Canvas.
Pragmatist 392 tok ·
descryx/nix-config
my nix config
Pragmatist 2.1k tok ·
Eflarus/claude-dotfiles
Opinionated Claude Code dotfiles — global standards, custom agents, RFC workflow, skills, hooks & statusline
Skill Collector 2.1k tok ·
bgarcia-ai/ClaudeOS
Reference template for structuring Claude Code projects to maximize performance. 5-layer memory architecture, self-improvement loop, skills, agents, hooks, and multi-platform workflow.
Automator 11.2k tok ·