fo-dispatch-recovery

# First Officer Dispatch Recovery (Claude) The two Claude dispatch exception bodies, each read only at its own failure trigger in `claude-fo-dispatch.md` — never at boot, never on a session where dispatch never fails. ## Break-Glass Manual Dispatch The resident trigger line already covers the first action (report the helper failure — command, exit code, stderr — to the captain before proceeding). Fill this template directly as the degraded fallback: Populate `{numbered checklist}` with the output of `«dispatch.checklist»(entity, stage)`; do not rebuild its rules here. ``` Agent( subagent_type="{dispatch_agent_id}", name="{worker_key}-{slug}-{stage}", // if this exceeds 64 chars, cap it the way `spacedock dispatch build` does: keep the {worker_key} prefix and -{stage} suffix and, on id-style: sd-b32, replace the slug with a fixed-length prefix of the entity id (id-less slug workflows truncate the slug head instead) run_in_background=true, // named background worker, no team_name model="{effective_model}", prompt="## First action\n\nBefore anything else, invoke your operating contract:\n\n Skill(skill=\"spacedock:ensign\")\n\nThis loads the shared ensign discipline (stage-report format, background-task polling, worktree ownership, completion signal protocol). Do not paraphrase; call the tool.\n\nYou are working on: {entity title}\n\nStage: {stage}\n\n### Stage definition:\n\n{copy stage subsection from README verbatim}\n\nRead the entity ...