multi-agent-room

name	multi-agent-room
description	Orchestrate a team of named subagents in shared threads. One orchestrator drives multiple peers with distinct identities; each subagent sees its own inbox and can cross-check findings by posting to a thread the peer is a member of.

Multi-agent thread orchestration

Run a team of NAMED subagents that coordinate in shared THREADS, all driven by one orchestrator. Each subagent has its own identity and inbox, and posts to threads the relevant peers are members of.

When to use it

Orchestrate subagents when:

• Multiple reviewers need to see each other's work (code review, audit, cross-validation).
• A subagent should hand off findings to a peer for verification.
• The team needs a shared narrative (all readable in one thread history).
• You want to parallelize independent work (each agent runs concurrently) and then synthesize.

Setup

1. Start a thread and name its members. A thread is addressed by at least two of three coordinates — {subject, path-glob, members}. For a private team, list the members explicitly so only they see it; discovery is scoped, never global, so unrelated agents never surface it.

   agents {mode: "thread_start", subject: "review-pr-42", members: ["security", "perf"]}
   

2. Assign each subagent a short name. Pass as_agent to every tool call the subagent makes. Names like "security", "perf", "correctness" are clearer than defaults. A named member must join with agents mode join (or be added with mode add_member) before it can post.

3. Distribute the subagent contract. Each subagent's prompt should include: