# Pipelines project ## Ownership and execution The user owns the project. The manager is responsible for finishing authorized work, not merely assigning it. Use pipelines, direct work or delegation as appropriate. The manager may implement, review, fix tests, resolve conflicts, merge and deliver. When a pipeline blocks progress, diagnose it and take over directly when useful. Do not create another recovery workflow just to complete an existing item. ## Pipelines are selected, not invented - For a task that can run in a pipeline, select an existing pipeline and put the task-specific detail in the run prompt. Do not create a pipeline or a new version because an existing prompt does not fit exactly. - Create, edit, or publish a pipeline only when the user explicitly asks for that pipeline change in the current conversation. This includes `pipelines new`, `pipelines edit`, `pipelines submit`, draft/import flows, and publishing through `rpc`, the API, or direct database writes. - Never publish a pipeline version as a side effect of solving a run request. If no existing pipeline fits, stop and report the gap; ask before authoring. ## Small changes, parallel progress Split features into small independently testable changes. Keep stage roles and handoffs short. Run independent items concurrently in separate worktrees; small overlapping edits are normal merge work, not an automatic reason to serialize. Use Luna for pipeline stages unless the user requests otherwise. ## Preserve and verify Read the relevant area map for build and test commands. Preserve existing branches, commits and uncommitted work. Never reset, discard or delete unrelated work. Resolve conflicts by preserving compatible intent; inspect the actual diff. Run focused tests while editing and relevant integration tests before landing. Check branch ancestry after landing, not before a server delivery gate can run. A failed item does not stop unrelated items. Keep unfinished work referenced. ## Finish and report Track code, checks, landing, deployment and device installation separately. Show changed paths and actual diff evidence; flag missing captures rather than claiming no changes. Report failures and decisions concisely. Update relevant rules, skills and documentation when they are the requested task; ordinary feature work can leave a focused docs/notes entry instead. Use the current-source skill installer to refresh managed installed skills. Do not restart a shared service over active work. Do not use the personal Fold for tests; it is a delivery device. Follow the device leases in app/AGENTS.md. Ask only for genuinely missing decisions or destructive/out-of-scope actions, not routine steps already covered by the user's request.