autoplan

Execute CEO, design, eng, and DX reviews sequentially with auto-decisions.

Updated Apr 13, 2026
One-click install
npx skills add https://github.com/legotec73/gstack --skill autoplan-legotec73
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: autoplan
Source: https://github.com/legotec73/gstack/tree/main/autoplan
Command: npx skills add https://github.com/legotec73/gstack --skill autoplan-legotec73

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Auto-review pipeline — reads the full CEO, design, eng, and DX review skills from disk and runs them sequentially with auto-decisions using 6 decision principles. Surfaces taste decisions (close approaches, borderline scope, codex disagreements) at a final approval gate. One command, fully reviewed plan out.

Core Features & Use Cases

  • Sequentially executes CEO, design, eng, and DX reviews to produce an end-to-end plan assessment.
  • Proactively suggests decisions and surfaces contextual taste notes at the final gate.
  • Enables a single-command workflow to generate a fully reviewed plan from existing skill definitions.

Quick Start

Run /autoplan on your current feature branch to trigger the full review gauntlet.

Frequently Asked Questions about autoplan

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I automate end-to-end plan reviews for software engineering projects?

You can automate an end-to-end plan review by running a single command that sequentially executes CEO, design, eng, and DX review skills, returning a consolidated verdict with auto-decisions.

What is the best way to run sequential design and engineering reviews on a feature branch?

The best way to run sequential reviews is using an automated pipeline that reads review skills from disk and executes them in sequence, enforcing decision principles and surfacing taste decisions at a final gate.

Can I trigger a full gate workflow for my software plans with a single command?

Yes, you can trigger a full gate workflow with a single command that proactively prompts when a plan file exists, executing the review gauntlet and surfacing contextual taste notes for approval.

How do decision principles work during an automated software plan review?

Decision principles work by enforcing six specific rules during the automated review process, enabling auto-decisions for standard plan elements while surfacing borderline scope and disagreements at the final approval gate.

Does auto-review work without manual intervention for feature branch plans?

Auto-review works without manual intervention by using auto-decisions to process standard plan elements, only halting at a final approval gate to surface taste decisions like close approaches or codex disagreements.

What limitations exist when surfacing taste decisions in an automated plan review?

The limitation is that while standard elements receive auto-decisions, taste decisions such as close approaches, borderline scope, and codex disagreements must be manually reviewed at the final approval gate.