primeline-ai

Plan Refine — Testing skill for Claude Code

Testing community

Autonomously stress-test and harden a plan through 6 adversarial perspectives.

How to install Plan Refine

Installs to ~/.claude/commands/primeline-ai-universal-planning-framework-plan-refine.md

Terminal

mkdir -p ~/.claude/commands && curl -fsSL https://raw.githubusercontent.com/primeline-ai/universal-planning-framework/HEAD/.claude/commands/plan-refine.md -o ~/.claude/commands/primeline-ai-universal-planning-framework-plan-refine.md

Restart Claude Code, or start a new session, for it to be picked up.

What Plan Refine does

description: Autonomously stress-test and harden a plan through 6 adversarial perspectives argument-hint: [plan-file-path] [--team] model: sonnet

Autonomous Plan Hardening (Stage 1.5)

You are hardening this plan: `$ARGUMENTS`

Read the plan file and stress-test it from 6 adversarial perspectives. Fix what you can, flag what needs user input. Do NOT ask the user any questions - work autonomously.

Pre-Flight Checks

Read the plan file using the Read tool
**Check idem

Alternatives in Testing

Paperjury — Pre-submission AI review stress-test for research papers 1k ★
Spec Driven Development — Drive Kandev feature work through spec, plan, independent tasks, implementation, QA, and verification 697 ★
Adversarial Spec — A Claude Code plugin that iteratively refines product specifications by debating between multiple LLMs until a 514 ★