combinaut/ai-agent-orchestration
Run a team of Claude Code and Codex agents you can watch: one Coordinator, architects that plan, workers in visible terminal panes. One-line install for macOS and Linux.
stack: Python
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 combinaut/ai-agent-orchestration/skills ./rig-ai-agent-orchestration/skills $ npx degit combinaut/ai-agent-orchestration/hooks ./rig-ai-agent-orchestration/hooks
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 combinaut/ai-agent-orchestration/skills/architect .claude/skills/architect $ npx degit combinaut/ai-agent-orchestration/skills/coordinate .claude/skills/coordinate $ npx degit combinaut/ai-agent-orchestration/skills/defend-pr .claude/skills/defend-pr $ npx degit combinaut/ai-agent-orchestration/skills/finalize-change-footprint .claude/skills/finalize-change-footprint $ npx degit combinaut/ai-agent-orchestration/skills/finalize-code-comments .claude/skills/finalize-code-comments $ npx degit combinaut/ai-agent-orchestration/skills/finalize-sweep .claude/skills/finalize-sweep $ npx degit combinaut/ai-agent-orchestration/skills/review-prs .claude/skills/review-prs
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 (7)
Similar rigs
suneel944/agent-parley
Run Claude Code, Codex, Copilot, Gemini, OpenCode and Amp side by side in isolated Git worktrees, with shared issue ownership, reservations and explicit handoffs.
Minimalist 439 tok · · Q0
agenticmail/agenticmail
Email, SMS & phone-call infrastructure for AI agents — send and receive real email and text messages, and place agent-driven outbound voice calls, all programmatically
Pragmatist 10.2k tok · · Q3
ShaitanLyss/volery
Direct a whole studio of Claude Code agents from one wall — see at a glance who's working, who's asking, and who's been left waiting.
Pragmatist 19.4k tok · · Q5
xelth-com/claude-codex-consult
Claude Code skill + PowerShell bridge that lets Claude consult OpenAI Codex (any model) mid-task over your ChatGPT subscription: fork/resume threads, read-only sandbox, file ledger of every consultation
Minimalist 257 tok · · Q0