Use when you have a written implementation plan to execute in a separate session with review checkpoints
Load plan, review critically, execute tasks in batches, report for review between batches.
Core principle: Batch execution with checkpoints for architect review.
Announce at start: "I'm using the executing-plans skill to implement this plan."
Use hive_status() to get the runnable list — tasks with all dependencies satisfied.
Only done satisfies dependencies (not blocked, failed, partial, ).
cancelledWhen 2+ tasks are runnable:
vscode/askQuestions for a structured choice: "Multiple tasks are runnable: [list]. Run in parallel, sequential, or a specific subset?"vscode/askQuestions is unavailable or a lightweight follow-up is enoughhive_context_write({ name: "execution-decisions", content: "..." }) for future referenceWhen 1 task is runnable: Proceed directly.
For each task in the batch:
hive_worktree_start()When batch complete:
After the batch report, prefer vscode/askQuestions to ask whether the user wants a Hygienic code review for the batch.
Fall back to asking directly in chat only when vscode/askQuestions is unavailable or a lightweight follow-up is enough.
If yes, invoke the @hygienic agent via the agent tool to review implementation changes from the latest batch, then apply feedback before starting the next batch.
Based on feedback:
After all tasks complete and verified:
STOP executing immediately when:
Ask for clarification rather than guessing.
Return to Review (Step 1) when:
Don't force through blockers - stop and ask.