Agent Orchestration

This turns Claude into a team lead that autonomously manages multiple AI agents until work is done. It runs a continuous loop: scans agent statuses, reads their progress, sends instructions, and coordinates dependencies without asking you to check in manually. The skill is opinionated about ownership (you drive the loop, never wait for permission to check again) and includes guardrails for what it can approve versus when to escalate. Useful when you've spun up several agents on related tasks and don't want to babysit the handoffs. The verify skill integration means it actually checks diffs and runs tests before calling something complete.

GitHub stars: 1.3K
last updated: Jun 11, 2026

View on GitHub

Install

$ npx -y skills add codeaholicguy/ai-devkit --skill agent-orchestration --agent claude-code

Installs into .claude/skills of the current project.

Files

Agent Orchestration

Use only for multi-agent supervision: coordinating dependencies, polling progress, unblocking waiting agents, relaying outputs, resolving conflicts, and verifying completion across agents. For one-off list/detail/send/start/kill work, use agent-management or agent-communication.

Use agent-management for safe agent selection and lifecycle actions. Use agent-communication for list/detail/send mechanics. Use verify before accepting any agent's completion claim.

Rules

Own the loop until assigned work is complete, blocked, or stopped.
Run agent list --json before each pass; never assume names/statuses.
Inspect waiting, idle, unknown, missing, or stale agents before acting.
Send self-contained instructions and avoid duplicate follow-ups.
Sequence agents that touch the same files; relay only relevant upstream output.
Escalate only for repeated failures, unresolved conflicts, product/business decisions, or destructive/shared/production/security-sensitive actions.