From memfleet-skills
Use to get a snapshot of fleet coordination health — active intents, open subscriptions, episode count, conflict counts by class. Triggered by: 'how busy is the fleet', 'are there open conflicts', periodic dashboard refresh, pre-release coordination check.
How this skill is triggered — by the user, by Claude, or both
Slash command
/memfleet-skills:memfleet-fleet-statusThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
One-shot dashboard. Cheap enough to call every few minutes. Returns:
One-shot dashboard. Cheap enough to call every few minutes. Returns:
fleet_status(repo_id?, window_ms?)
Omit repo_id to get a cross-repo rollup.
// Session opener:
fleet_status({ window_ms: 1_800_000 }) // last 30 min
// Interpret:
// high class-C count → conflict storm; read each via query_episodes
// zero active intents → safe to do large refactors
// conflict_density > threshold on a module → avoid or coordinate
The CLI dashboard (fleet-cli) is the interactive face of the same data. Use fleet_status inside agents, fleet-cli for human eyes.
npx claudepluginhub syncable-dev/memfleet-public --plugin memfleet-skillsPresents a real-time snapshot of harness state by reading campaigns, fleet sessions, telemetry, and pending queues. Invoked by /dashboard or phrases like "what's happening".
Active monitoring heartbeat for CAFleet Directors. Watches root Director (180s) and members (720s), wakes monitoring member on due intervals, runs team-facilitation instructions. Load before supervision skill.
Displays Honcho memory system status: connection health, workspace, peers, observation queue, and conclusion count. Invoke via /honcho:status for quick checks.