# Process Plan Executor

> Use when you have a written implementation plan to execute in a separate session with review checkpoints

- Skill: `bitranox/process-plan-executor` (Agent Skill, multi-file: 2 files)
- Install (CLI): `npx skillmds@latest add bitranox/process-plan-executor`
- Raw SKILL.md: https://api.skillmd.com/api/skills/bitranox/process-plan-executor/raw
- Safety review: pending
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: Coding & Dev Tools
- Author: bitranox (https://skillmd.com/u/bitranox)
- Updated: 2026-09-17
- Page: https://skillmd.com/skills/bitranox/process-plan-executor

---


# Executing Plans

> Adapted from the superpowers plugin (MIT).

## 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 process-plan-executor skill to implement this plan."

## 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, arm the subagent model gate, and proceed:

       bash "$CLAUDE_PLUGIN_ROOT/hooks/run-python.sh" "$CLAUDE_PLUGIN_ROOT/hooks/skill_receipt.py" start plan-execution

   While armed, any subagent dispatched during this plan (a review helper, a
   verification agent) is DENIED unless it pins `model` explicitly - tiers per
   "Concrete tiers" in bitranox:process-agents-subagent-driven-development.

### 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

When all batches are done:
- Confirm every task in the plan is completed (check the TodoWrite list).
- Run the full test suite and confirm it is green; output pristine (no errors or warnings).
- Disarm the subagent model gate:

      bash "$CLAUDE_PLUGIN_ROOT/hooks/run-python.sh" "$CLAUDE_PLUGIN_ROOT/hooks/skill_receipt.py" end plan-execution

- Summarize what changed across the batches for the architect.
- Per the user's wish, hand off to bitranox:process-ship-finishing-development-branch or open a PR.

## 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

## Integration

**Required workflow skills:**
- **bitranox:process-plan-writing-plans** - Creates the plan this skill executes
- **bitranox:process-agents-subagent-driven-development** - the in-session alternative: drive the same plan through
  implementer and reviewer subagents in this session, instead of executing it yourself in a separate one