# Work tracking Keep one current queue, not an ever-growing transcript. For each item record: goal, branch/worktree, run if any, verified evidence, current state and next action. Keep old history separately; stale statuses must not compete with the current list. Distinguish source prepared, tests passed, visually checked, landed and deployed. A run marked failed may contain valuable commits; a succeeded run is not proof that a phone was updated. Check current Git/server/device state before reporting. Split features into small independent edits. Start ready items concurrently and explain actual bottlenecks, not hypothetical conflicts. Delegate routine work; take over directly when that is simpler than another failed recovery cycle. Resume from retained evidence. Do not blindly repeat completed stages or make a different pipeline land an earlier pipeline's work. Preserve every unfinished branch/commit and unknown dirty file. A failed item does not stop unrelated work. Use background `pipelines wait` for active runs. After completion inspect the actual outcome and advance the work, not just announce that it stopped. Report concise results, blockers needing a decision and exact next actions.