zorahrel/jarvis
Personal AI setup in the open: Claude Code, Codex, jcode and an OpenClaw assistant. Public half here, private half in an encrypted git submodule — a pattern you can copy.
ARCHETYPE
Skill Collector
Ten-plus skills loaded on demand. A procedural-knowledge library.
Copy this rig
# review before running: this installs third-party code
$ npx degit zorahrel/jarvis/outside/.claude ./rig-jarvis # 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 <redacted>-image .claude/skills/chatgpt-image $ npx degit <redacted>-security-audit .claude/skills/config-security-audit $ npx degit <redacted>-model .claude/skills/domain-model $ npx degit <redacted>-loop .claude/skills/gauntlet-loop $ npx degit <redacted>-image-edit .claude/skills/gemini-image-edit $ npx degit <redacted> .claude/skills/graphify $ npx degit <redacted>-me .claude/skills/grill-me $ npx degit <redacted> .claude/skills/orchestrator $ npx degit <redacted>-hunter .claude/skills/product-hunter $ npx degit <redacted> .claude/skills/pulse $ npx degit <redacted>-factory .claude/skills/reel-factory $ npx degit <redacted> .claude/skills/restart $ npx degit <redacted>-pass .claude/skills/senior-pass $ npx degit <redacted>-hooks .claude/skills/suno-hooks $ npx degit <redacted>-forge .claude/skills/tool-forge $ npx degit <redacted>-research .claude/skills/trend-research $ npx degit <redacted>-language .claude/skills/ubiquitous-language $ npx degit <redacted>-reel .claude/skills/watch-reel $ npx degit <redacted>-out .claude/skills/zoom-out
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 (19)
Similar rigs
just3ws/vdots
A native-first Neovim configuration — Lua, vim.pack, built-in LSP, and a ;-leader keymap.
Skill Collector 3.0k tok · · Q3
JensRoland/agent-config
My AI coding agent configs
Pragmatist 2.7k tok · · Q8
just3ws/zdots
An observable Zsh control plane: local AI, service lifecycle, a knowledge layer, and a full CLI — restorable in one command.
MCP Hoarder 29.5k tok · · Q8
Cloonar/coding-lab
Self-hosted, phone-first control panel for coding agents — interactive sessions and unattended issue-to-PR runs on your git repos.
Skill Collector 1.1k tok · · Q0