CrisLottz/obsidian-claude-second-brain
AI-ready second brain for Obsidian: plain Markdown + Git, built for Claude Code, readable by any AI, with a zero-token Telegram morning brief.
stack: Python
ARCHETYPE
Automator
Hooks on every lifecycle event: format, lint, notify, log.
Copy this rig
# review before running: this installs third-party code
$ npx degit CrisLottz/obsidian-claude-second-brain/.claude ./rig-obsidian-claude-second-brain # 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 CrisLottz/obsidian-claude-second-brain/.claude/skills/day-close .claude/skills/day-close $ npx degit CrisLottz/obsidian-claude-second-brain/.claude/skills/inbox .claude/skills/inbox $ npx degit CrisLottz/obsidian-claude-second-brain/.claude/skills/ingest .claude/skills/ingest $ npx degit CrisLottz/obsidian-claude-second-brain/.claude/skills/interview .claude/skills/interview $ npx degit CrisLottz/obsidian-claude-second-brain/.claude/skills/journal-close .claude/skills/journal-close $ npx degit CrisLottz/obsidian-claude-second-brain/.claude/skills/new-project .claude/skills/new-project $ npx degit CrisLottz/obsidian-claude-second-brain/.claude/skills/weekly-review .claude/skills/weekly-review $ npx degit CrisLottz/obsidian-claude-second-brain/skills/second-brain-setup .claude/skills/second-brain-setup
This rig commits no guardrails. Here is the community baseline instead — the deny/ask rules most often found across all 16.2k rigs:
{
"permissions": {
"deny": [
"Read(./.env)",
"Read(./.env.*)",
"Read(**/.env)",
"Read(~/.ssh/**)",
"Bash(git push --force:*)",
"Read(**/*.pem)",
"Read(.env)",
"Read(~/.aws/**)",
"Read(**/*.key)",
"Read(**/.env.*)",
"Bash(git push --force*)",
"Bash(rm -rf:*)",
"Bash(rm -rf *)",
"Bash(sudo *)",
"Bash(sudo:*)",
"Bash(rm -rf /)",
"Bash(git push -f:*)",
"Read(.env.*)",
"Bash(git reset --hard*)",
"Bash(rm -rf /*)"
],
"ask": [
"Bash(git push:*)",
"Bash(git push *)",
"Bash(gh pr merge *)",
"Bash(git commit:*)",
"Bash(rm *)",
"Bash(gh pr merge:*)",
"Bash(gh pr create *)",
"Bash(git reset --hard:*)",
"Bash(npm publish:*)",
"Bash(git rebase *)"
]
}
} Skills (8)
Hooks (4)
| event | matcher | runs |
|---|---|---|
| SessionStart | startup|resume|clear|compact | bash "$CLAUDE_PROJECT_DIR/.claude/hooks/run.sh" session-start |
| PostToolUse | Edit|MultiEdit|Write | bash "$CLAUDE_PROJECT_DIR/.claude/hooks/run.sh" post-edit |
| Stop | * | bash "$CLAUDE_PROJECT_DIR/.claude/hooks/run.sh" stop |
| UserPromptSubmit | * | bash "$CLAUDE_PROJECT_DIR/.claude/hooks/run.sh" prompt |
Similar rigs
johnfkoo951/cmds-llm-wiki
LLM Wiki template — Karpathy 3-layer pattern + Gold In Gold Out purpose gate + dual Claude Code·Codex harness (11 commands, 2 hooks, 18 web clipper templates)
Skill Collector 10.4k tok · · Q20
titusmundi/second-brain-starter
A Claude Code skill and a plain-language guide that set up an Obsidian vault an AI can keep up to date. Mac and Windows.
Minimalist 87 tok · · Q0
Aayush9029/mcp-server
MCP server that sends your AI agents' tasks to iPhone, iPad, and Apple Watch
Minimalist 806 tok · · Q3
policani/portable-cross-agent-second-brain-personal
Solo edition of the portable cross-agent second brain — plain markdown, routes to save tokens, no approval gate.
Minimalist 1.8k tok · · Q3