executing-plans

name	executing-plans
description	Use when you have a written implementation plan to execute in a separate session with review checkpoints

Executing Plans

Overview

Load plan, review critically, execute all tasks, report when complete.

Announce at start: "I'm using the executing-plans skill to implement this plan."

Note: Tell your human partner that Superpowers works much better with access to subagents. The quality of its work will be significantly higher if run on a platform with subagent support (such as Claude Code or Codex). If subagents are available, use subagent-driven-development instead of this skill.

The Process

Step 1: Load and Review Plan

1. Read plan file
2. Review critically — identify any questions or concerns about the plan
3. If concerns: Raise them with your human partner before starting
4. If this is a mothership workspace (mothership.yaml at any ancestor): verify mship status shows an active task BEFORE starting (mship status | jq .resolved_task should be non-null, or .active_tasks should contain the slug you intend to anchor). No active task → stop. Every task needs a WorkItem: tell the user to run mship item new "<title>" --kind <feature|bug|chore|question> then mship spawn "<description>" --work-item <id> first. Then cd into .resolved_task.worktrees.<repo> and do all work and commits there. The mship pre-commit hook refuses commits from outside the worktree, so "just commit on main" is both wrong and blocked. If require_approved_spec: true, the task needs a bound, approved spec before mship phase dev will advance — create/approve one (mship spec …) or pass mship phase dev --bypass-spec-gate. See working-with-mothership.
5. If no concerns: Create TodoWrite and proceed

Step 2: Execute Tasks

For each task:

1. Mark as in_progress
2. Follow each step exactly (plan has bite-sized steps)
3. Run verifications as specified
4. Mark as completed

Step 3: Complete Development

After all tasks complete and verified:

• Announce: "I'm using the finishing-a-development-branch skill to complete this work."
• REQUIRED SUB-SKILL: Use finishing-a-development-branch
• Follow that skill to verify tests, present options, execute choice

In a mothership workspace, finishing-a-development-branch routes through mship finish --body-file <path> (see that skill's Option 2).

When to Stop and Ask for Help

STOP executing immediately when:

• Hit a blocker (missing dependency, test fails, instruction unclear)
• Plan has critical gaps preventing starting
• You don't understand an instruction
• Verification fails repeatedly

Ask for clarification rather than guessing.

When to Revisit Earlier Steps

Return to Review (Step 1) when:

• Partner updates the plan based on your feedback
• Fundamental approach needs rethinking

Don't force through blockers - stop and ask.

Remember

• Review plan critically first
• Follow plan steps exactly
• Don't skip verifications
• Reference skills when plan says to
• Stop when blocked, don't guess
• Never start implementation on main/master branch without explicit user consent

Integration

Required workflow skills:

• using-git-worktrees - REQUIRED: Set up isolated workspace before starting
• writing-plans - Creates the plan this skill executes
• finishing-a-development-branch - Complete development after all tasks