ultra-plan

Community

Run an end-to-end spec-to-fix loop autonomously.

AuthorCopeeeTang
Version1.0.0
Installs0

System Documentation

What problem does it solve?

It solves the problem of turning an unclear or multi-step goal into a complete, verifiable implementation workflow without repeatedly interrupting the user—by generating a requirements spec, executing it, evaluating results with acceptance checks, and performing bounded fixes when failures occur.

Core Features & Use Cases

  • End-to-end loop orchestration: Performs interview/spec creation, execution via Codex, evaluation via automated checks plus a judge review, and up to two fix iterations when blockers or major issues are found.
  • Acceptance-criteria driven delivery: Requires an auto-executable acceptance criteria section (CMD/METRIC) and runs those checks to determine pass/fail.
  • Autonomous vs collaborative control: Defaults to autonomous execution that minimizes user involvement, while supporting a collaborative mode that prompts the user for step-by-step confirmations.
  • Role-symmetric guardrails: Uses Claude as planner/judge and Codex as executor/fixer, ensuring Claude does not directly modify code during review/fix decisions.

Quick Start

Use ultra-plan when you want the assistant to clarify requirements and then automatically execute, test, review, and (if needed) fix the work until it produces a final report for your task.

Dependency Matrix

Required Modules

None required

Components

scripts

💻 Claude Code Installation

Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.

Please help me install this Skill:
Name: ultra-plan
Download link: https://github.com/CopeeeTang/copeee-skills/archive/main.zip#ultra-plan

Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
View Source Repository

Agent Skills Search Helper

Install a tiny helper to your Agent, search and equip skill from 471,000+ vetted skills library on demand.