playingpossumm/loose-ends
A second brain that records knowledge and tracks commitments, then creates loops and nudges you to close them.
field: Productivity
ARCHETYPE
Pragmatist
A balanced, no-drama setup: some rules, some tools, nothing extreme.
Copy this rig
# review before running: this installs third-party code
$ npx degit playingpossumm/loose-ends/.claude ./rig-loose-ends # 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 playingpossumm/loose-ends/.claude/skills/ask .claude/skills/ask $ npx degit playingpossumm/loose-ends/.claude/skills/bootstrap .claude/skills/bootstrap $ npx degit playingpossumm/loose-ends/.claude/skills/brief .claude/skills/brief $ npx degit playingpossumm/loose-ends/.claude/skills/capture .claude/skills/capture $ npx degit playingpossumm/loose-ends/.claude/skills/close .claude/skills/close $ npx degit playingpossumm/loose-ends/.claude/skills/ingest-all .claude/skills/ingest-all $ npx degit playingpossumm/loose-ends/.claude/skills/ingest .claude/skills/ingest $ npx degit playingpossumm/loose-ends/.claude/skills/lint .claude/skills/lint $ npx degit playingpossumm/loose-ends/.claude/skills/unsource .claude/skills/unsource
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 (9)
Similar rigs
MetamusicX/zissa-wiki
Zissa Wiki — an LLM-maintained research knowledge base in plain markdown, maintained by any AI agent (Claude, Codex, Gemini, DeepSeek, Kimi, Grok, Mistral or any chat app). Implements Karpathy's LLM Wiki pattern; checks every quote against
Pragmatist 4.4k tok · · Q18
vagmcs/dots
My dotfiles
YOLO Cowboy 1.3k tok · · Q5
Kolibee-GmbH/m2b
Your second brain for Claude Code: one store for what you know about people, agreements and your own life, across all your projects and machines. "Remind me on Friday" becomes a task, a fact with an end date is rewritten once the day has pa
Skill Collector 1.6k tok · · Q0
piotrmechlinski/executive-brain
A private vault for executives, run by Claude Code: meetings, decisions, risks and people, each row with its source.
Pragmatist 3.8k tok · · Q34