Executing Plans

---
name: executing-plans
description: Execute a written implementation plan batch-by-batch — load it, review critically, implement task by task, and stop for review between batches. Use when you have a written implementation plan to execute in a separate session with review checkpoints.
license: MIT
metadata:
  author: Jesse Vincent
  source: Derived from https://github.com/obra/superpowers
---

# 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 superpowers: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 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 superpowers:finishing-a-development-branch
- Follow that skill to verify tests, present options, execute choice

## 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.

## Workspace mode

When the plan was authored in workspace mode (caller is `/orc:flow` or `/orc:plan` with `--repos`), each slice carries a `repo:` annotation. Execution rules:

- Before each slice, **`cd` into the slice's `repoPath`** (passed by the caller as input). All git, test, lint, and edit commands MUST run inside that repo's tree.
- **Sibling repos are off-limits.** A slice tagged `repo: api` may not edit files in `<workspaceRoot>/ui/`. The worktree-path boundary already enforces this physically; treat any urge to cross it as a bug in the plan, not in your execution — escalate.
- The plan's **Cross-repo contract** section (when present) is frozen for the duration of execution. If a slice would change an endpoint shape, schema, or message format listed there, stop and surface — that's a plan change, not an implementation choice.
- **Restore-before-act** extends to per-repo state. On resume, read both `<workspaceRoot>/.orc/<branch>/files/checkpoint.md` (workspace-level cursor) **and** `<repoPath>/.orc/<branch>/files/progress.md` (this repo's slice log) before executing the next slice.
- When dispatched in parallel for a workspace plan (one implementer per repo), treat your `repo` + `repoPath` as your full universe — sibling implementers are operating in their own repos simultaneously.

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