Three commands, one task lifecycle: /roll, /rock, /work

Building on plain markdown task files in backlog/in_progress/done, the actual technique is splitting the agent loop into three slash commands that each do exactly one thing.

/roll researches the codebase and writes a task file - it implements nothing, which is what keeps planning honest and reviewable. /rock picks up one task and takes it end to end: implement, run the check suite, review the result against the task's own acceptance criteria, refresh the e2e scenarios, commit. /work is a thin loop over a list of task IDs that hands each one to a fresh subagent, so the main context never carries state from the previous task, and parks anything needing a human decision instead of stopping the whole batch.

The split matters more than the commands. A single do-everything command quietly merges planning into implementation and you lose the reviewable step in the middle.