Agent Orchestration

SkillAI & models

Your AI can keep a multi-agent workflow on track from start to finish, supervising the work as it happens over multiple passes. Once added, it watches progress, keeps agents moving, and confirms when everything is done. It is built for ongoing coordination, not one-off actions.

Available today. Use it from your connected AI after setup.

Add the skill, then point your AI at an ongoing multi-agent workflow you want it to supervise. Use it for continuous coordination rather than single actions like starting or stopping one agent.

Then ask your AI: use the Agent Orchestration skill

What your AI can do with it

  • Check progress across a multi-agent workflow as it runs
  • Unblock agents that are waiting so work keeps moving
  • Coordinate the order agents work in when one depends on another
  • Pass results from one agent along to the next
  • Resolve conflicts between agents
  • Verify that the full workflow is complete

What this skill tells your AI

The instructions your AI receives, as published by codeaholicguy/ai-devkit in skills/agent-orchestration/SKILL.md and read by ahel’s review.

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.

Loop

If the goal or agent ownership is unclear, run one scan/detail pass. Ask the user once only if context is still insufficient.

  1. Scan agents.
  2. Assess agents needing attention with detail --tail 10.
  3. Act: approve, clarify, correct, delegate, relay, verify, or escalate.
  4. Report one brief status line.
  5. Sleep 10-60s and repeat.

Completion

Finish when all assigned work is verified, blocked with a clear reason, or stopped by the user. Summarize per-agent outcomes, verification, unresolved issues, and next step.

Signals

GitHub stars
2k
Forks
250
Last commit
Sep 2026
Advanced
Catalog kind
skill
Gateway key
agent-orchestration
Source
github.com/codeaholicguy/ai-devkit