aontwit/pitwall
The agent loop that queues your work, proves every PR, and leaves the merge to you.
ARCHETYPE
Skill Collector
Ten-plus skills loaded on demand. A procedural-knowledge library.
Copy this rig
$ git clone --depth 1 https://github.com/aontwit/pitwall 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 aontwit/pitwall/plugin/skills/brake .claude/skills/brake $ npx degit aontwit/pitwall/plugin/skills/doctor .claude/skills/doctor $ npx degit aontwit/pitwall/plugin/skills/drive .claude/skills/drive $ npx degit aontwit/pitwall/plugin/skills/gauge .claude/skills/gauge $ npx degit aontwit/pitwall/plugin/skills/init .claude/skills/init $ npx degit aontwit/pitwall/plugin/skills/lap .claude/skills/lap $ npx degit aontwit/pitwall/plugin/skills/merge-order .claude/skills/merge-order $ npx degit aontwit/pitwall/plugin/skills/pitwall .claude/skills/pitwall $ npx degit aontwit/pitwall/plugin/skills/plan .claude/skills/plan $ npx degit aontwit/pitwall/plugin/skills/queue .claude/skills/queue $ npx degit aontwit/pitwall/plugin/skills/secretary .claude/skills/secretary $ npx degit aontwit/pitwall/plugin/skills/stop .claude/skills/stop $ npx degit aontwit/pitwall/plugin/skills/ticket .claude/skills/ticket
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 (13)
Similar rigs
mlophez/polix-ai
Declarative guardrails for Claude Code: one polix.yaml decides what the agent may not touch, what must pass and what runs at every step.
Automator 1.1k tok · · Q15
sravan27/context-os
Cut Claude Code token usage by 40.9% and ship a CI gate for coding-agent cost leaks. Stdlib Python hook + GitHub Action for Claude Code, Codex, Cursor, and agentic coding teams.
Pragmatist 680 tok · · Q0
archcore-ai/archcore
Spec-driven development and context engineering for Claude Code, Cursor, Codex, and GitHub Copilot — backed by project context in Git.
Minimalist 337 tok · · Q0
kadiresen/context-bank
Your AI memory bank is eating your context window. Capped, git-committed, retrieval-first project memory shared by every agent via AGENTS.md.
Pragmatist 546 tok · · Q15