claudex-plan

Name: claudex-plan
Availability: InStock
Author: m2ai-portfolio

Gate code execution until a plan passes adversarial review and receives explicit approval.

4|1|Updated Apr 11, 2026

Search Tags:#planning #governance #gate #stop-hook #adversarial-review #code-approval

Ready to run

npx skills add https://github.com/m2ai-portfolio/m2ai-skills-pack --skill claudex-plan

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: claudex-plan
Source: https://github.com/m2ai-portfolio/m2ai-skills-pack/tree/main/skills/claudex-plan
Command: npx skills add https://github.com/m2ai-portfolio/m2ai-skills-pack --skill claudex-plan

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Stops execution until a plan is adversarially reviewed and explicitly approved, preventing quick jumps to implementation.

Core Features & Use Cases

Stop-hook gated planning: requires explicit approval after multiple review rounds.
Plan-first and plan-during modes for risky tasks like migrations, architecture changes, and multi-service launches.
Works with Claude Code workflows to enforce plan survival before coding.

Quick Start

Tell Claude to start a planning gate for a high-stakes task and seek explicit approval before coding.

Frequently Asked Questions about claudex-plan

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

FAQPage Schema

How do I enforce a plan approval gate before coding starts?▼

A planning gate stops execution until a plan survives adversarial review and receives explicit approval. This stop-hook mechanism prevents unsafe rushes to coding during high-stakes tasks like data migrations or multi-service launches.

How do I prevent rush-to-code during risky data migrations and security refactors?▼

Prevent rush-to-code by applying a stop-hook gating mechanism to high-stakes tasks like data migrations and security refactors. It requires plans to survive multiple adversarial review rounds before any code is written.

Can I configure multiple review rounds for a plan approval gate?▼

Yes, this stop-hook gating mechanism supports configurable review rounds. The plan must survive adversarial review and receive explicit approval commands across these configured rounds before code may be written.

Does the plan approval gate work with plan-during modes or only plan-first workflows?▼

The planning gate supports both plan-first and plan-during modes. This ensures formal plan survival and explicit approval are enforced whether planning occurs entirely beforehand or concurrently within risky workflows.

When should I use an adversarial review gate for code approval in a multi-service launch?▼

Use an adversarial review gate for code approval during high-stakes tasks like multi-service launches, data migrations, and security refactors. It ensures formal plan survival and explicit approval before any code is written.