Coordinate Codex and Claude planners and critics to refine plans.
npx skills add https://github.com/choms0521/my-claude-skills --skill xmultiplan
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
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.
Create a new plan using Codex as the planner and Claude as the critic for the task 'Develop a product launch strategy'.
High-intent search queries and answers about installing and using this skill.
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.
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.
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.
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.
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.
cyanluna-gitCoordinate six agents to move tasks through a seven-column Kanban pipeline.
rseReboot task plans in software development environments via ASE MCP tools.
riethmayerOrchestrate consensus planning with Planner, Architect, and Critic review cycles.
masharrattOrchestrate container-based CFN Loop execution with agent spawning and consensus collection.
