batch-execute

Task

You will be going on a plan execution spree for non-code work. I will provide a list of plans. Execute these plans one by one without interruptions.

Follow the ops:work-autonomously skill throughout.

Steps

1. Check the current branch — if you're already on a feature branch, stay on it. Only create a new branch if you're on main (or the repo's default branch).
2. Identify the batch prefix to process. The user usually names it (e.g. "execute the music batch"); otherwise infer it from the plan files they list, or ask. Plans use the convention plans/<batch>-NN-YYYY-MM-DD-<slug>.md and plans/<batch>-direct-tasks.md so multiple concurrent batches can coexist in plans/.
3. Create a follow-up file per the ops:work-autonomously skill.
4. Build the ordered work queue: merge plan files (plans/<batch>-NN-*.md) and any entries in plans/<batch>-direct-tasks.md into a single list sorted by numeric prefix. Only include files matching this batch's prefix — leave other batches alone. Don't look ahead, don't run items in parallel.
5. Process the queue in order. Plan-file items go through the plan-based flow below; direct-task items go through the direct-task flow.
6. After all items are processed, use the /ops:review-followup skill to walk through follow-up items with the user.
7. When all follow-up items are resolved, confirm with the user to merge the branch. Then perform the merge.

Execution (plan files)

For each plan file, spawn an executor with subagent_type: "ops:executor" and this prompt:

Plan file path: <path to the plan>
Follow-up file path: <path to the follow-up file>

After each executor agent completes:

1. Review its summary for status and any follow-up items. Note the summary's Effort line — if one delegation's effort dwarfs its peers, mention it in the follow-up file so the batch's expensive spots stay visible.
2. Verify the agent persisted insights: check if MEMORY.md or backlog files were updated when appropriate. If the agent produced findings but didn't persist them, do it now.
3. Commit the plan's changes (artifacts + state updates + completed plan) with a descriptive message, naming their paths: git add -- <paths>, then git commit -m "<message>" -- <paths>. Take the paths from the executor's summary and git status; never git add -A or a bare git commit (see ops:work-autonomously, rule 4)