agent-orchestration
AI DevKit · Supervise multi-agent workflows over repeated passes: poll progress, unblock waiting agents, coordinate dependencies, relay outputs, resolve conflicts, and verify completion. Use only for ongoing multi-agent coordination, not one-off list/detail/send/start/kill action
Install
npx skills add https://github.com/codeaholicguy/ai-devkit/tree/main/skills/agent-orchestration
claude plugin marketplace add https://llmmart.ai/marketplace.json && claude plugin install codeaholicguy-ai-devkit@llmmart
git clone https://github.com/codeaholicguy/ai-devkit.git
The skills CLI installs just this skill, for any of its supported agents. Claude Code installs the whole codeaholicguy/ai-devkit collection as a plugin from our marketplace. Git is the plain clone.
Skill manifest
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 --jsonbefore 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.
- Scan agents.
- Assess agents needing attention with
detail --tail 10. - Act: approve, clarify, correct, delegate, relay, verify, or escalate.
- Report one brief status line.
- Run
ai-devkit agent wait --json(add--id/--groupto watch only your agents), then repeat. It blocks until an agent moves to waiting, idle, or exited, or until its 5-minute default timeout;reason: "timeout"is normal, so do a light scan and wait again. If your command timeout is shorter, run it in the background or raise that timeout. Never use a longsleep: harnesses block or kill it.
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.
Files (ai-devkit)
-
agents
-
openai.yaml 406 B
Loading…
-
-
SKILL.md 2.2 KB
--- name: agent-orchestration description: "AI DevKit · Supervise multi-agent workflows over repeated passes: poll progress, unblock waiting agents, coordinate dependencies, relay outputs, resolve conflicts, and verify completion. Use only for ongoing multi-agent coordination, not one-off list/detail/send/start/kill actions." --- # 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. Run `ai-devkit agent wait --json` (add `--id`/`--group` to watch only your agents), then repeat. It blocks until an agent moves to waiting, idle, or exited, or until its 5-minute default timeout; `reason: "timeout"` is normal, so do a light scan and wait again. If your command timeout is shorter, run it in the background or raise that timeout. Never use a long `sleep`: harnesses block or kill it. ## 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.
Comments (0)
Sign in to join the conversation.
Reviews (0)
No reviews yet.
No comments yet.