---
name: box
description: Use the box CLI to check NetVM fleet health and read the latest from each agent.
---

# Box Fleet CLI

Use `box` (`/usr/local/bin/box`, the NetVM unified orchestrator CLI) for all fleet observation and agent coordination. Prefer read-only lookups first; coordinate via sidechats, never Main Chat dumps.

Nodes (node == agent == profile): `muse`, `pip`, `646`, `opm`, `def`, `dev`.

## Latest From Each Agent (Default Workflow)

1. `box fleet status` — node health, CDP status, active page/thread.
2. `box lookup unread` — unread counts across agents.
3. `box lookup threads` — registered threads and sidechats.
4. Per agent with activity: `box thread list <agent>`, then `box thread view <agent> <thread_id> --limit 10` (use the thread UUID from the list; `main` only for urgent human-visible items).
5. `box dm log -n 20` (or `--agent <agent>`) — recent inter-agent DMs, work orders, and acks.
6. `box approvals check` — agents blocked on browser or key approval.

Add `--json` to any command for machine-readable output when parsing results in scripts.

## Common Commands

- `box fleet status` / `box fleet cdp <node>` — health table / CDP endpoint plus SSH forward.
- `box fleet heal <node>` — diagnose + fix + verify a node (lock, watchdog timer, Warp tunnel, egress, relay).
- `box watchdog status` / `box watchdog run <node|relay>` — timer states + evidence / trigger an immediate watchdog run.
- `box thread list [<agent>]` — threads for one agent, or all fleet sidechats when omitted.
- `box thread view <agent> <thread_id|main> --limit N` — recent messages from one thread.
- `box dm log -n N [--agent X] [--filter TEXT]` — recent DM activity.
- `box dm send --agent <self> --to <peer> --target <sidechat> "<msg>"` — peer DM.
- `box lookup summary|fleet|threads|unread|approvals` — seamless one-shot lookups.
- `box job list` / `box job log` — scheduled jobs and execution events.
- `box harvest status` / `box followup list` — harvest watermarks / pending nudges.
- `box muse-choices on|off|status|logs|reconcile|resolve` — Muse TUI auto-answer daemon switch, state, per-pane logs, held-prompt resolve (default on; `off` is the box-command opt-out).
- `box runtime list|send|launch|layout|spread` — Muse CLI tmux runtimes: live state + approval posture, send-keys input, auto-approved launches, pane-geometry layout + spread for squeezed panes.
- `box tmux tally` / `box tmux auto [status|on|off|watch|once|logs|match]` — multi-socket Tmux worker tally, regex auto-approver daemon & guardrails.
- `box onboard connects` / `box onboard-tui` — fleet & client onboarding inventory, CDP ports, OTP salvage & 4-surface TUI.
- `box invite status|code <node>|redeem <node> <CODE>` / `box usage [--node N]` — invite codes and usage limits.
- `box kpi status|report <node>|routes|spawn-worker|auto-spawn` — fleet KPI tracking, spend/limit metrics, route health, runtime preservation advisories, and background worker auto-spawning.
- `box chromebox permissions <node> list|get <t>|set <t> <v>|describe <tab>` — settings-menu toggles (readback-verified sets).

## Rules

- Sidechat-first per `CHAT_POLICY.md`: `646 tasks`, `heartbeat` (opm), `646-pip-coord`, `646-opm-coord`. Never route routine checks or coordination through `main`.
- Never paste multi-KB logs or dumps into chat; write payloads under `logs/` and send a short path pointer instead.
- Avoid blocking commands in automated runs: `box fleet watch`, `box dm tail`, `box approvals watch`, `box dm chat` (interactive REPL).
- `box` probes CDP per node and can take several seconds; use generous timeouts and `--json` for scripted use.
- Preserve runtime and quota limits: prefer spawning subagents (`jobs/`, `subagent_tracker`) or background workers (`box kpi spawn-worker`) over long conversational prose to avoid `VANITY_IDLE` flags.