executing-plans git:20260312.c37221cA

Immutable. This exact content never changes and is served at /api/v1/blob/746da8e84b5c9c14.

---
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 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."

## The Process

### Step 1: Load and Review Plan
1. read_file 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 Batch
**Default: First 3 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: Report
When batch complete:
- Show what was implemented
- Show verification output
- Say: "Ready for feedback."

### Step 4: Continue
Based on feedback:
- Apply changes if needed
- Execute next batch
- Repeat until complete

### Step 5: 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 supaconductor: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 mid-batch (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
- Between batches: just report and wait
- Stop when blocked, don't guess
- Never start implementation on main/master branch without explicit user consent

## Conductor Integration (Autonomous Mode)

When invoked with `--plan`, `--track-dir`, and `--metadata` parameters (from Conductor orchestrator):
- read_file plan from `--plan` path
- Execute ALL tasks (not batches of 3) — run autonomously
- Do NOT stop for human feedback between batches
- After each task: use replace tool to mark `[x]` in plan.md with commit SHA
- After all tasks: update `--metadata` checkpoint to `EXECUTE: PASSED`
- Return concise verdict: `{"verdict": "PASS", "tasks_completed": N}`
- If `--resume-from` is provided, skip tasks before that task ID

When these parameters are absent, fall back to the standalone batch workflow above.

## Integration

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