xmultiplan

Coordinate Codex and Claude planners and critics to refine plans.

1|Updated Mar 24, 2026

Search Tags:#planning #product development #consensus building #plan refinement #cross-runtime planning

Ready to run

npx skills add https://github.com/choms0521/my-claude-skills --skill xmultiplan

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: xmultiplan
Source: https://github.com/choms0521/my-claude-skills/tree/main/generated/claude/skills/xmultiplan
Command: npx skills add https://github.com/choms0521/my-claude-skills --skill xmultiplan

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) components.

What problem does it solve?

The xmultiplan skill solves the problem of inefficient planning and consensus-building processes by enabling cross-runtime collaboration between planners and critics for plan creation and evaluation.

Core Features & Use Cases

Cross-Runtime Collaboration: Allows planners and critics to work in different runtime environments for a more comprehensive review process.
Customizable Roles: Users can assign the roles of planner and critic to either Codex or Claude, offering flexibility in plan development.
Iterative Feedback Loop: Facilitates a multi-round process for plan refinement, ensuring that all aspects are thoroughly evaluated.
Plan Storage: Stores final plans in the 'docs/plans/' directory for future reference and tracking.

Quick Start

Create a new plan using Codex as the planner and Claude as the critic for the task 'Develop a product launch strategy'.

Frequently Asked Questions about xmultiplan

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

FAQPage Schema

What is cross-runtime consensus planning and how does it refine product development plans?▼

Cross-runtime consensus planning uses iterative feedback loops between planner and critic models, like Codex and Claude, to collaboratively evaluate and refine product development plans across multiple rounds.

How do I set up a plan refinement loop using different AI runtimes?▼

You set up plan refinement by assigning the planner role to one runtime, such as Codex, and the critic role to another, like Claude, then specifying the number of iterative rounds for feedback.

Can I use both Codex and Claude for collaborative plan review?▼

Yes, the skill supports customizable roles, allowing you to assign Codex and Claude as either the planner or the critic to facilitate cross-runtime collaboration and comprehensive plan evaluation.

Does the cross-runtime planning skill execute the final approved plans automatically?▼

No, the skill stores final approved plans in a pending approval state within the docs/plans/ directory without execution, ensuring human oversight before any development actions are taken.

How many iterative rounds are needed for effective plan refinement?▼

The skill allows you to specify the exact number of iterative rounds needed, ensuring thorough evaluation and consensus building between the planner and critic runtimes before final approval.