agent-orchestration

1# Agent Orchestration
2 
3Use 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`.
4 
5Use `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.
6 
7## Rules
8 
9- Own the loop until assigned work is complete, blocked, or stopped.
10- Run `agent list --json` before each pass; never assume names/statuses.
11- Inspect waiting, idle, unknown, missing, or stale agents before acting.
12- Send self-contained instructions and avoid duplicate follow-ups.
13- Sequence agents that touch the same files; relay only relevant upstream output.
14- Escalate only for repeated failures, unresolved conflicts, product/business decisions, or destructive/shared/production/security-sensitive actions.
15 
16## Loop
17 
18If the goal or agent ownership is unclear, run one scan/detail pass. Ask the user once only if context is still insufficient.
19 
201. Scan agents.
212. Assess agents needing attention with `detail --tail 10`.
223. Act: approve, clarify, correct, delegate, relay, verify, or escalate.
234. Report one brief status line.
24…