Is the ULW Plan skill free?

Yes. The skill itself is free from code-yeongyu/oh-my-openagent. SkillProof publishes the install command and an independent test verdict at no cost.

What is the ULW Plan SkillProof Score?

8.8/10 — installs cleanly 4/5, triggers reliably 5/5, output vs. baseline 8/10, docs & honesty 5/5.

How do I install ULW Plan?

Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.

Can I use ULW Plan with Cursor, Copilot, Gemini CLI, Codex or other AI tools?

The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.

ULW Plan

Explore-first planner that turns vague briefs into one decision-complete plan.

by code-yeongyu · code-yeongyu/oh-my-openagent

Tested · Works

Install — copy the command Download source ↗

Test report

Verdict: Tested · Works
Score: 8.8/10
Tested: Jul 13, 2026
Environment: Claude Code 2.x (agent harness)
Upstream re-checked: Aug 10, 2026 · 8b8c027

The skill's own worked example — a 5/min-per-IP rate limit on /login — makes a great acid test: running it surfaced two real owner-decisions (Redis vs in-memory store, response body shape) that a plain baseline plan had silently assumed away instead of asking.

Scored on four weighted criteria — install, triggering, output vs. baseline, docs. How scoring works

Installs cleanly 4/5
Triggers reliably 5/5
Output vs. baseline 8/10
Docs & honesty 5/5

What ULW Plan does

ulw-plan is a codebase-grounded planning consultant ('Prometheus') that explores a repo before asking questions, then writes one decision-complete plan for a downstream coding agent to execute with zero further interview. It triggers on planning requests, vague 'just make it good' briefs, architecture decisions, or explicit asks to be interviewed, and refuses to write or edit product code itself. Best fit for teams already running the 'ultrawork' toolchain (subagent spawning, codegraph, momus review) it was built alongside.

How to install ULW Plan

git clone https://github.com/code-yeongyu/oh-my-openagent
cd oh-my-openagent
mkdir -p ~/.claude/skills
cp -r packages/omo-codex/plugin/components/ultrawork/skills/ulw-plan ~/.claude/skills/ulw-plan

Skills live in ~/.claude/skills/ (global) or .claude/skills/ (per-project). Restart Claude Code after installing.

Commands — how to trigger ULW Plan

/ulw-plan Explore-first planner that turns vague briefs into one decision-complete plan.

It also activates on plain-language prompts like these:

Before we code this, explore the repo and give me one complete plan
I need a decision-complete plan so the agent needs zero follow-up questions
Just make it good, explore first then write the plan, no guessing needed

Frequently asked questions

Is the ULW Plan skill free?: Yes. The skill itself is free from code-yeongyu/oh-my-openagent. SkillProof publishes the install command and an independent test verdict at no cost.
Does ULW Plan work with Claude Code?: We tested it with Claude Code 2.x (agent harness) on Jul 13, 2026. Verdict: Tested · Works. The skill's own worked example — a 5/min-per-IP rate limit on /login — makes a great acid test: running it surfaced two real owner-decisions (Redis vs in-memory store, response body shape) that a plain baseline plan had silently assumed away instead of asking.
What is the ULW Plan SkillProof Score?: 8.8/10 — installs cleanly 4/5, triggers reliably 5/5, output vs. baseline 8/10, docs & honesty 5/5.
How do I install ULW Plan?: Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.
Can I use ULW Plan with Cursor, Copilot, Gemini CLI, Codex or other AI tools?: The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.