Ultrawork

This is a Hermes-native ultrawork workflow skill.

Why This Exists

ultrawork exists to choose one-owner, ordered-dependency, or independent-frontier execution for an accepted implementation plan without letting concurrency blur ownership, verification, worker protocol, worktree isolation, or observed runtime evidence. It also carries four named internal capabilities absorbed from sibling engines: coordinated_scope (coordinated worker lanes), delivery_boundary (one bounded plan-to-PR cycle), single_owner_persistence (one owner finishes and verifies), and durable_checkpoint (durable goal ledger with checkpoints and a final gate).

First Steps

• Initialize the phase todo before engine work (todo init) in ONE tool, never both: todo_list when todo_list is in your tool list or tool_search finds it (OMH mirrors it), else omh_todo; an accepted plan stays in omh_todo. Declare numbered phases in delivery order — bootstrap, one implement/verify/deliver task per lane or work unit, independent review lanes, and an evidence-and-cleanup close, one task per observable outcome — keep exactly one item active, and update states as lanes complete, so the run walks a bounded checklist. Phase names and task titles are written in English as short labels even when the conversation runs in another language, since the HUD checklist is an operator surface.

Do Not Use When