Start one supervisor for a repository, fan work out across isolated worktrees, and route CI failures or review comments back to the right agent automatically.
Scanned 6/8/2026
Install via CLI
openskills install agentskillexchange/skills---
name: "Orchestrate parallel coding agents with autonomous CI and review handoff using Agent Orchestrator"
slug: "orchestrate-parallel-coding-agents-with-autonomous-ci-and-review-handoff-using-agent-orchestrator"
description: "Start one supervisor for a repository, fan work out across isolated worktrees, and route CI failures or review comments back to the right agent automatically."
github_stars: 6270
verification: "listed"
source: "https://github.com/ComposioHQ/agent-orchestrator"
author: "Composio"
publisher_type: "organization"
category: "CI/CD Integrations"
framework: "Multi-Framework"
tool_ecosystem:
github_repo: "ComposioHQ/agent-orchestrator"
github_stars: 6270
npm_package: "@aoagents/ao"
npm_weekly_downloads: 3870
---
# Orchestrate parallel coding agents with autonomous CI and review handoff using Agent Orchestrator
Start one supervisor for a repository, fan work out across isolated worktrees, and route CI failures or review comments back to the right agent automatically.
## Prerequisites
Node.js 20+, Git 2.25+, tmux, GitHub CLI
## Installation
No source-backed install or usage instructions could be extracted automatically. Review the upstream project before running this skill in a sensitive workflow.
- Source: https://github.com/ComposioHQ/agent-orchestrator
## Documentation
- https://github.com/ComposioHQ/agent-orchestrator
## Source
- [Agent Skill Exchange](https://agentskillexchange.com/skills/orchestrate-parallel-coding-agents-with-autonomous-ci-and-review-handoff-using-agent-orchestrator/)
No comments yet. Be the first to comment!
Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.