plan

Create testable work plans with acceptance criteria and execution handoffs.

Updated Apr 10, 2026
One-click install
npx skills add https://github.com/lpjhelder/kronon-forge --skill plan-lpjhelder
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: plan
Source: https://github.com/lpjhelder/kronon-forge/tree/main/skills/plan
Command: npx skills add https://github.com/lpjhelder/kronon-forge --skill plan-lpjhelder

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Planning prevents wasted effort, scope creep, and missed edge cases by turning vague or broad requests into concrete, testable work plans and clear handoffs for execution. The plan skill structures discovery, creates acceptance criteria, and produces implementation steps grounded in codebase evidence so execution starts from a solid foundation.

Core Features & Use Cases

  • Interactive Interview Mode: Conducts single-question-at-a-time requirements gathering and consults lightweight codebase exploration before asking the user.
  • Direct Mode: Generates a comprehensive plan immediately from a detailed request.
  • Consensus (RALPLAN-DR) & Review Modes: Runs Planner → Architect → Critic loops with formal RALPLAN-DR summaries, ADR output, pre-mortems for high-risk work, and quality gating before approval.
  • Execution Handoffs: Produces .forge/plans artifacts, available-agent rosters, and concrete launch hints for $ralph and $team without editing source code directly.
  • Quality Constraints: Enforces testable acceptance criteria, file/line evidence for claims, and sequential architect/critic checks for consensus reviews.

Quick Start

Ask the plan skill to create a consensus work plan to add JWT authentication across the API, including risks, testable acceptance criteria, and an implementation roadmap.

Frequently Asked Questions about plan

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

FAQPage Schema
How do I turn vague project ideas into actionable work plans with testable acceptance criteria?

To turn vague ideas into actionable work plans, use interactive interview mode to gather requirements one question at a time, ensuring outputs include testable acceptance criteria, file-level evidence, and explicit handoff guidance for execution agents.

What is a consensus review process for software architecture planning?

A consensus review for software architecture planning runs Planner, Architect, and Critic loops to validate work. It produces formal RALPLAN-DR summaries, Architecture Decision Records, and pre-mortems for high-risk work before granting approval.

How do I gather requirements for a codebase-informed implementation roadmap?

You can gather requirements for a codebase-informed roadmap using interactive interview mode, which consults lightweight codebase exploration before asking you questions, grounding the implementation steps in actual file-level evidence.

Can I generate a comprehensive software project plan immediately from a detailed request?

Yes, you can generate a comprehensive software project plan immediately from a detailed request using direct mode, which produces implementation steps, testable acceptance criteria, and execution handoffs without an interactive interview.

What is included in an execution handoff for implementation agents?

An execution handoff for implementation agents includes .forge/plans artifacts, available-agent rosters, and concrete launch hints for execution agents, ensuring the next stage starts from a solid foundation without editing source code directly.

When should I use pre-mortems and quality gating in project scoping?

You should use pre-mortems and quality gating during project scoping when dealing with high-risk work, enforcing sequential architect and critic checks to validate consensus reviews before approving the actionable work plan.