fleetlisted

# /fleet — agent-fleet orchestration (MCP-backed) The fleet's control surface ships as the **`fleet` MCP server** (`fleet mcp`, registered with Claude). Prefer the MCP tools over shelling `fleet` — they are typed, return structured JSON, and lazy-load their schemas (you only pay context for tools you actually call). Reach for these before bash. ## MCP tools (the Conductor's control surface) | Tool | What | Kind | |---|---|---| | `fleet_validate_plan` | RAIL 2 dry check: parse a plan, report workers + whether scope-claims are disjoint (`disjoint:false` is a refusal verdict, not an error) | read-only | | `fleet_run` | Run a plan. Default dry-run; `live:true` enforces RAIL 2 then dispatches workers detached — poll `fleet_status` | gated dispatch | | `fleet_burn` | Quality-token-burn: run live at high concurrency on real backlog (429-retry + result-accept gate) | dispatch | | `fleet_gate` | RAIL 3 result-accept gate: check the working tree against the plan's claims (`strays` = changes outside all claims) | read-only | | `fleet_status` | Bus snapshot: worker messages, kill-switch state, latest result-accept verdict | read-only | | `fleet_stop` / `fleet_resume` | Engage / clear the global kill switch (STOP) | control | | `fleet_worker_status` | One worker's live state — status, scope-claim, attempt, last heartbeat/finding, drift flags | read-only | | `fleet_worker_memory` | Tail a worker's own running notes (memory.md) | read-only | | `fleet_worker_diff` | A worker's changes with