Claude Skill MartBrowse skillsQuick linesLearn by videoTerminal guideWhat is a Skill?
 
← Back to list

ulw-plan (Prometheus Planning Consultant)

Turns a vague or large request into ONE decision-complete work plan: explores the codebase first, asks only the forks it cannot resolve, and writes the plan only after your explicit approval.

Dev & CodingAdvanced★ 67,531⑂ 5,507AI score 7/10Last updated: Aug 9, 2026

What it does

  • Switches the agent into Prometheus, a planning consultant: it prints ULW-PLAN MODE ENABLED! as the first line and pledges no product-code edits until you explicitly approve.
  • Runs parallel read-only exploration (Read/Grep/Glob, CodeGraph, external doc research) so discoverable facts are researched, never asked.
  • Makes one intent verdict — CLEAR vs UNCLEAR — and announces it. CLEAR means a short interview on genuine owner-decisions; UNCLEAR means it adopts and announces best-practice defaults instead of interrogating you.
  • Scaffolds a resumable draft at .omo/drafts/<slug>.md via scripts/scaffold-plan.mjs, gates on your okay, then writes .omo/plans/<slug>.md with strict task rows (- [ ] 1. ... for implementation, - [ ] F1. ... for final verification).
  • Every todo carries reference paths, acceptance criteria, agent-executed QA (happy + failure path), and a commit unit, so the downstream worker needs zero further interview.

Who it's for

  • Anyone who wants scope and design pinned down in writing before letting an AI touch a large refactor or feature.
  • Developers tired of the model jumping straight into implementation on an underspecified brief.
  • Teams already on the oh-my-openagent / ultrawork stack (Codex CLI, multi_agent spawn, codegraph).
  • Workflows that separate planning from execution sessions (e.g. $start-work).

Examples

  1. Sharp request: "add a 5/min-per-IP rate limit to /login" → routed CLEAR; it inspects existing middleware and test conventions, asks only the one or two forks the repo can't settle, then writes the plan after approval.
  2. Fuzzy request: "make auth better" → routed UNCLEAR; instead of interviewing you it researches, announces best-practice defaults, and automatically runs the dual high-accuracy review.
  3. High-accuracy modifier: saying "deep review" in any later turn sets review_required: true and triggers the momus + Codex CLI review on the existing plan in that same turn.

· · · Install guide · · ·

Try it now, no install

Paste this into Claude to use the skill without installing anything.

Read the instructions in this file and follow them to help me:
https://raw.githubusercontent.com/code-yeongyu/oh-my-openagent/HEAD/packages/omo-codex/plugin/components/ultrawork/skills/ulw-plan/SKILL.md

What I want: (describe your task here)

If Claude can't open the link, open it yourself and paste the contents instead.

↓ If it works for you, download the ZIP below and install it. Then it runs on its own — no pasting each time.

Install in the Claude app (no terminal)
  1. Download the ZIP with the button below.
  2. In Claude, open Settings → Capabilities and turn on 'Code execution and file creation'. (one time)
  3. Go to Customize → Skills → + → 'Upload a skill' and upload the ZIP.
↓ Download ZIP
Install in Claude Code

Let Claude do it — paste this into Claude Code

Install the skill I found on Claude Skill Mart.
Copy the packages/omo-codex/plugin/components/ultrawork/skills/ulw-plan folder from the GitHub repo code-yeongyu/oh-my-openagent into my ~/.claude/skills/ulw-plan/.
When it's done, tell me in one line what this skill can do.

Install with a command instead

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

⚠ This is a third-party skill. Check the source repository before installing.

  1. Open a terminal and clone the repo: git clone https://github.com/code-yeongyu/oh-my-openagent /tmp/omo
  2. Confirm the skill folder exists: ls /tmp/omo/packages/omo-codex/plugin/components/ultrawork/skills/ulw-plan
  3. Create your skills directory: mkdir -p ~/.claude/skills
  4. Copy the whole folder so bundled references/ and scripts/ come with it: cp -r /tmp/omo/packages/omo-codex/plugin/components/ultrawork/skills/ulw-plan ~/.claude/skills/
  5. Make sure Node.js 18+ (or Bun) is installed for scripts/scaffold-plan.mjs: node -v
  6. Restart Claude Code and trigger it with a message like ulw-plan: plan this refactor before coding.
  7. Note: without multi_agent spawn or codegraph tools the skill still works, but parallel subagent research falls back to plain Read/Grep/Glob exploration.
View source on GitHub ↗License: NOASSERTION