executing-plans
Executes a written plan with review checkpoints: batch-by-batch progress, verification per step, and stop points for feedback.
Anatomy
| Parent repo | obra/superpowers |
|---|---|
| Path | skills/executing-plans |
| Trigger conditions | "Use when you have a written implementation plan to execute in a separate session" |
| Instruction format | yaml-frontmatter-md |
| Required tools | shell, file-edit |
| Reusability | universal |
| Complexity | medium |
| Ships scripts / examples / tests / boundaries | no / yes / no / yes |
Failure modes
Checkpoint cadence is fixed by the plan's batching; poorly batched plans produce checkpoints that are either noise or too sparse to catch drift.
Verdict
Completes the loop that writing-plans opens. Deviation-handling instructions (stop, report, adjust) are the differentiator; most execution instructions omit them.
Related skills
Blocks the agent from claiming work is complete, fixed, or passing until it has run verification commands and confirmed output. Evidence…
Forces root-cause investigation before any fix: reproduce, hypothesize one cause at a time, test the hypothesis, then patch. Bans…
Frequently asked questions
What does the executing-plans skill do?
Executes a written plan with review checkpoints: batch-by-batch progress, verification per step, and stop points for feedback.
When does executing-plans trigger?
Its stated trigger: "Use when you have a written implementation plan to execute in a separate session". Trigger precision is a scored reliability dimension.