ralplan

Coordinate consensus planning for vague startup execution requests.

1|1|Updated Apr 13, 2026
One-click install
npx skills add https://github.com/Cheggin/request-for-startups --skill ralplan-cheggin
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: ralplan
Source: https://github.com/Cheggin/request-for-startups/tree/main/skills/ralplan
Command: npx skills add https://github.com/Cheggin/request-for-startups --skill ralplan-cheggin

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Coordinate consensus planning for vague startup execution requests by gating them through a multi-agent planner / review loop, ensuring clear scope and risk assessment before work commences.

Core Features & Use Cases

  • Orchestrates Planner, Architect, and Critic passes to produce a bounded, auditable plan.
  • Supports --interactive and --deliberate flags to adjust engagement level and guardrails.
  • Returns a final plan with ADR-style documentation and explicit decisions.

Quick Start

Invoke ralplan with a vague startup task to trigger the Planner/Architect/Critic consensus loop.

Frequently Asked Questions about ralplan

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

FAQPage Schema
How do I turn vague startup execution requests into concrete, auditable plans?

Consensus planning gates vague startup execution requests through a multi-agent loop to produce a concrete, auditable plan. It orchestrates Planner, Architect, and Critic passes to ensure clear scope and risk assessment before any work commences.

What is multi-agent consensus planning and how does it work for software engineering tasks?

Multi-agent consensus planning coordinates a Planner, Architect, and Critic pass to review and bound a vague task. This chain gates the initial prompt, resolving ambiguities and assessing risks before execution to output a final, auditable plan.

How do I generate ADR-style decision records for architectural plans?

You can generate ADR-style decision records by running a vague request through the Planner, Architect, and Critic consensus loop. The final plan output includes explicit ADR-style documentation of architectural decisions made during the gating process.

Can I use interactive and deliberate modes to adjust guardrails during plan generation?

Yes, you can use the --interactive and --deliberate flags to adjust the engagement level and guardrails during plan generation. These flags control how the multi-agent Planner, Architect, and Critic passes orchestrate the consensus loop.

Does this consensus planning approach work for evaluating risk and scope before execution?

Yes, the multi-agent consensus loop is specifically designed for risk assessment and scope bounding before execution. The Architect and Critic passes review the Planner's initial output to ensure all vague startup requests are fully evaluated and bounded.

What are the limitations of using a multi-agent planner review loop for task execution?

The multi-agent planner review loop focuses entirely on gating requests and generating auditable plans before work starts. It does not execute the task itself; it only outputs a final plan with ADR-style decisions, requiring separate orchestration for actual implementation.