Claude Skill MartBrowse skillsWhat is a Skill?
 
← Back to list

ulw-plan (Prometheus Planning Consultant)

Turns Claude into an explore-first planning consultant that grounds in your repo, asks only the real owner-decisions, and writes one decision-complete plan after you approve.

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

What it does

  • Puts Claude into the Prometheus persona: a planner that never edits product code and only writes plan artifacts under .omo/.
  • Runs parallel read-only exploration (CodeGraph, Grep/Glob/LSP, external docs research) so discoverable facts are researched, not asked.
  • Classifies the request as CLEAR or UNCLEAR, announces the verdict, and surfaces questions only for genuine owner-decisions (irreversible, safety-critical, public config, dependencies, schema shape).
  • Waits for an explicit "okay" before writing the plan; each todo carries file references, acceptance criteria, agent-executed QA (happy + failure paths) and a commit unit.
  • Honors "high accuracy" modifiers by flipping a review gate (momus + an independent CLI review) that must pass before handoff.

Who it's for

  • Developers who want a locked spec before handing a large change to an AI implementer.
  • Teams burned by agents that jump straight to code and build the wrong thing.
  • Agent power users who separate planning sessions from execution sessions.

Examples

  1. ulw-plan add a 5/min-per-IP rate limit to /login → routed CLEAR, explores middleware conventions, asks only the storage/config fork, then writes the plan after approval.
  2. ulw plan make auth better → routed UNCLEAR, researches and announces best-practice defaults instead of interviewing you, and auto-runs the high-accuracy review.
  3. plan this migration, ultra high accuracy → plan is drafted, then momus plus an independent review are forced before the handoff summary.

· · · Install guide · · ·

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/skills/ulw-plan folder from the GitHub repo code-yeongyu/oh-my-openagent into my ~/.claude/skills/code-yeongyu-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.git /tmp/oh-my-openagent && mkdir -p ~/.claude/skills && cp -r /tmp/oh-my-openagent/packages/omo-codex/plugin/skills/ulw-plan ~/.claude/skills/

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

  1. Open a terminal.
  2. Clone the repository: git clone https://github.com/code-yeongyu/oh-my-openagent.git /tmp/oh-my-openagent
  3. Create the skills directory if needed: mkdir -p ~/.claude/skills
  4. Copy the whole skill folder (the bundled scripts/ and references/ must come along or the workflow breaks): cp -r /tmp/oh-my-openagent/packages/omo-codex/plugin/skills/ulw-plan ~/.claude/skills/
  5. Make sure node (or bun) is installed — the plan scaffold script needs it.
  6. Restart Claude Code and type ulw-plan <what you want built>; you should see ULW-PLAN MODE ENABLED! as the first line.
  7. Answer any questions, reply "okay" to approve, and the plan lands in .omo/plans/<slug>.md. Run execution in a separate session (e.g. $start-work).
View source on GitHub ↗License: NOASSERTION