---
name: Agent Orchestration
slug: agent-orchestration-2
category: AI Engineering
description: Agent Orchestration coordinates dependencies between multiple AI agents, polls their progress, unblocks waiting agents, relays outputs, resolves conflicts, and verifies completion. Use it for ongoing multi-agent supervision rather than one-off agent actions.
github: "https://github.com/codeaholicguy/ai-devkit/tree/main/skills/agent-orchestration"
language: TypeScript
stars: 1581
forks: 242
install: "npx degit https://github.com/codeaholicguy/ai-devkit/tree/main/skills/agent-orchestration ~/.claude/skills/agent-orchestration"
installs_to: ~/.claude/skills/agent-orchestration
source_path: skills/agent-orchestration/SKILL.md
collection_size: 25
category_size: 2451
collection_url: "https://dirskills.com/collections/codeaholicguy/ai-devkit"
added: 2026-08-19T07:26:17.548Z
last_synced: 2026-08-19T07:26:17.548Z
canonical_url: "https://dirskills.com/skills/agent-orchestration-2"
---

# Agent Orchestration

Agent Orchestration coordinates dependencies between multiple AI agents, polls their progress, unblocks waiting agents, relays outputs, resolves conflicts, and verifies completion. Use it for ongoing multi-agent supervision rather than one-off agent actions.

**Install:**

```bash
npx degit https://github.com/codeaholicguy/ai-devkit/tree/main/skills/agent-orchestration ~/.claude/skills/agent-orchestration
```

## README

# 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.

## 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.