wisnuwiry/padu
Native desktop app for orchestrating AI coding agents (Claude Code, Codex, Cursor CLI) — built in Rust, no Electron, instant launch.
ARCHETYPE
Pragmatist
A balanced, no-drama setup: some rules, some tools, nothing extreme.
Copy this rig
$ git clone --depth 1 https://github.com/wisnuwiry/padu 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 wisnuwiry/padu/.agents/skills/gpui-perf-audit .claude/skills/gpui-perf-audit $ npx degit wisnuwiry/padu/.agents/skills/mobile-ui .claude/skills/mobile-ui $ npx degit wisnuwiry/padu/.agents/skills/multiplatform-release .claude/skills/multiplatform-release $ npx degit wisnuwiry/padu/.agents/skills/pre-pr-review .claude/skills/pre-pr-review $ npx degit wisnuwiry/padu/.agents/skills/protocol-parity-sync .claude/skills/protocol-parity-sync $ npx degit wisnuwiry/padu/.agents/skills/provider-driver-dev .claude/skills/provider-driver-dev
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 (6)
Similar rigs
devinat1/agent-ready-codebase-templates
Config-only overlays for making codebases ready for AI coding agents
Minimalist 787 tok · · Q5
repository-standards/core
The repository standard: align, verify, drift 0. A method a repository can be measured against, and the tree it ships.
Fort Knox 8.6k tok · · Q53
kamiletar/letar
Open workshop: schema-driven forms for React, Vue and Angular (@letar/forms), plus a monorepo maintained by a team of AI agents — with the rules and incident write-ups they work by.
Orchestrator 17.9k tok · · Q48
kookr-ai/kookr
A smart attention router for developers running multiple AI coding agents.
Skill Collector 11.1k tok · · Q25