agent-orchestration
Agent Orchestration is a Claude Code skill that manages multi-agent workflows by continuously monitoring agent statuses, tracking progress, sending targeted instructions, and coordinating work across multiple agents without requiring user intervention between steps. Use this skill when managing complex projects with multiple specialized agents, coordinating parallel or sequential agent tasks, or maintaining oversight of agent progress and automatically resolving issues or escalating blockers to the user.
git clone --depth 1 https://github.com/codeaholicguy/ai-devkit /tmp/agent-orchestration && cp -r /tmp/agent-orchestration/skills/agent-orchestration ~/.claude/skills/agent-orchestrationSKILL.md
# 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.
AI DevKit · Exchange information with active Codex, Claude Code, and other AI agents using ai-devkit agent list, detail, and send. Use when an agent needs to find another active agent, read its recent context, send it information, or request information back.
AI DevKit · Manage running AI agents with ai-devkit agent commands. Use when an agent needs to identify itself, list agents, start workers, inspect agent detail, assign work, group agents, resume sessions, stop agents, or delegate work to other agents.
AI DevKit · Use when the user asks to brainstorm, ideate, generate ideas, expand options, challenge ideas, pressure-test ideas, compare concepts, narrow choices, name something, plan content angles, explore strategy, evaluate product ideas, technical approaches, experiments, or decisions.
AI DevKit · Compare implementation with design and requirements docs to ensure alignment.
AI DevKit · Pre-push code review against design docs.
AI DevKit · Safe git commit workflow for AI coding agents. Use when the user asks to commit, prepare a commit, stage changes, create a PR-ready checkpoint, or finish work with a conventional commit while avoiding unrelated user changes.
AI DevKit · Design phase guidance for reviewing feature design against requirements. Use when the user wants to validate architecture, review design docs, resolve design trade-offs, or run dev-lifecycle phase 3.
AI DevKit · Implementation phase guidance for executing feature plans and checking implementation against design. Use when the user wants to implement planned tasks, update implementation docs, verify code matches design, or run dev-lifecycle phases 5 and 7.