ralplan

Coordinate multi-agent consensus planning to gate vague execution requests before coding.

Updated Mar 31, 2026
One-click install
npx skills add https://github.com/ClementATH/oh-my-claudecode --skill ralplan-clementath
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: ralplan
Source: https://github.com/ClementATH/oh-my-claudecode/tree/main/skills/ralplan
Command: npx skills add https://github.com/ClementATH/oh-my-claudecode --skill ralplan-clementath

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Ralplan intercepts vague or underspecified execution requests and routes them through a structured consensus planning cycle (Planner, Architect, Critic) to produce a clear, testable plan before any implementation begins.

Core Features & Use Cases

  • Consensus-driven planning loop that gates execution with explicit scope, drivers, and options.
  • Supports interactive and deliberate modes for risk management and user involvement.
  • Re-review loops with up to five iterations to ensure quality and alignment across stakeholders.

Quick Start

Use the ralplan command with a task description to initiate consensus planning before execution.

Frequently Asked Questions about ralplan

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

FAQPage Schema
How do I gate coding execution with multi-agent consensus planning?

You can gate coding execution by routing vague requests through a structured Planner, Architect, and Critic loop that produces a testable plan before implementation begins. This consensus-driven cycle ensures explicit scope and risk assessment before any coding work starts.

When do I need architecture review and risk assessment before starting implementation?

Architecture review and risk assessment are needed before implementation when handling high-risk or ambiguous execution requests. A multi-stage consensus planning loop ensures stakeholder alignment and prevents underspecified coding work from proceeding.

What is the best way to handle vague or underspecified execution requests in an automated workflow?

The best way to handle vague execution requests is intercepting them with a structured consensus planning cycle before implementation. Routing underspecified tasks through risk assessment and test planning generates clear, actionable options for stakeholders.

Can I use interactive and deliberate modes for risk management during task planning?

Yes, interactive and deliberate modes are supported for risk management and user involvement during task planning. These modes enable stakeholder participation in the consensus loop, which supports re-review iterations up to five times for quality alignment.

How many re-review iterations are supported in a consensus-driven planning loop?

The consensus-driven planning loop supports re-review loops with up to five iterations to ensure quality and alignment across stakeholders. This multi-stage cycle involving the Planner, Architect, and Critic progressively refines vague requests into testable plans.

Does multi-agent task planning work for high-risk or ambiguous requests across teams?

Multi-agent task planning works across teams for high-risk or ambiguous requests by applying architecture review, risk assessment, and test planning before implementation. The consensus loop gates execution to ensure all stakeholder requirements are explicitly met.