firstmate-orca

Use this as the operator checklist for Firstmate's experimental Orca runtime backend. It does not replace AGENTS.md, docs/orca-backend.md, or harness-adapters.

Orca is a runtime backend, not an agent harness. The runtime backend owns the task endpoint and, for Orca, the task worktree. The harness is the agent process launched inside that endpoint, such as claude, codex, opencode, pi, pi-signed, grok, or kimi. Load harness-adapters for harness-specific launch, interrupt, resume, trust-dialog, and skill-invocation facts.

Implementation details, metadata fields, teardown guarantees, and limitations live in docs/orca-backend.md. docs/verification/runtime-backends.md "Orca" owns active smoke evidence. Prefer the bin/fm-* helpers over raw orca commands. Use raw orca only when the helper surface cannot answer the inspection question, and keep the recorded firstmate metadata as the task identity.

Preflight

Work from the current firstmate home or repo root. If FM_HOME is set, remember that operational state lives under $FM_HOME while the helper scripts still run from this repo's bin/.

Before switching or spawning against Orca:

• Confirm Orca is intentionally selected through --backend orca, FM_BACKEND=orca, or local config/backend.
• Confirm the Orca app is running and the backend readiness checks pass before expecting spawn to work.
• Inspect active state/*.meta records before changing backend selection.
• Treat a backend switch as affecting future spawns only; existing tasks keep their recorded backend.
• Reconcile watcher wakes before unrelated work, especially if Orca tasks are already in flight.

Spawn

Use bin/fm-spawn.sh so firstmate creates the brief, worktree, terminal, metadata, status file, and watcher surface together. Pass --backend orca for a one-off Orca task, or rely on the already-selected Orca backend when that selection is intentional.