From ops
Presents a read-only dashboard of all Claude sessions (local and remote) showing token types, CRS relay health, account utilization, and per-session details. Useful for fleet monitoring.
How this skill is triggered — by the user, by Claude, or both
Slash command
/ops:ops-fleet [--once] [--tui] [--all] [--no-color] [--no-ec2][--once] [--tui] [--all] [--no-color] [--no-ec2]This skill is limited to the following tools:
The summary Claude sees in its skill listing — used to decide when to auto-load this skill
Unified, read-only dashboard over the whole Claude session fleet — local `claude --bg`
Unified, read-only dashboard over the whole Claude session fleet — local claude --bg
sessions plus any remote box reached over SSM — built from claude agents --json,
claude daemon status, the account-rotation daemon state, and the CRS (Claude Relay
Service) relay. It renders, it never mutates.
The dashboard sources everything live; nothing needs to be parsed by this skill:
claude agents --json (authoritative; nameless sessions fall back to their session id).http://127.0.0.1:${CRS_PORT:-3005}/health, allowlist at
~/.claude/scripts/account-rotation/crs-allowlist.json, recent 429/529 from the relay window.~/.claude/state/fleet-ec2.json,
TTL ~45s); degrades to refreshing… / empty when unavailable.These paths are the standard account-rotator install locations
(scripts/install-account-rotator-linux.sh). If the rotator isn't installed the CRS /
account / remote rows simply degrade to ? — the session table still renders.
Run the bin script and relay its output verbatim (strip ANSI for the chat block):
${CLAUDE_PLUGIN_ROOT}/bin/ops-fleet $ARGUMENTS
Behavior:
q to quit).--once/--snapshot force a single render · --tui/--watch [secs] force the loop ·
--all include completed sessions · --no-color plain · --no-ec2 skip the remote SSM round-trip.CRS_PORT=NNNN (default 3005; 3000 is the legacy alias).ALWAYS render the dashboard to the user first — re-emit the snapshot inside a fenced code
block (keep the box-drawing/bars/layout, strip ANSI). Below it add a one-line summary:
total sessions + token-type breakdown, anything blocked or flapping (high att:), CRS
health, and any account ≥90% util. The dashboard is the deliverable; the summary is the footnote.
End with a single line noting the live full-screen TUI is ${CLAUDE_PLUGIN_ROOT}/bin/ops-fleet
(or --tui) in a real terminal.
npx claudepluginhub lifecycle-innovations-limited/claude-ops --plugin opsLaunches a machine-wide dashboard showing all active Claude Code sessions with token usage, sub-agents, and needs-approval badges. Complements per-run /site-view.
Starts, stops, or checks dot-dash server for real-time browser dashboard monitoring Claude Code sessions, streaming transcripts via WebSocket, and prompt injection.
Manages multi-account Claude Max rotation with keychain token swapping and CRS relay-pool auto-prioritization. Useful when running multiple Claude accounts with rotation enabled.