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

ulw-plan — Explore-First Planning Consultant

Turns the agent into a planning consultant that explores the codebase first, asks only the genuine decisions, and writes one decision-complete work plan after your explicit approval.

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

What it does

ulw-plan puts the agent into a strict planning persona ("Prometheus") that never implements.

  • Runs parallel read-only exploration (CodeGraph, Grep/Glob, LSP, external docs) before drawing conclusions.
  • Classifies your intent as CLEAR or UNCLEAR and announces the verdict in one line.
  • Asks only the forks exploration cannot settle; everything reversible gets a recorded best-practice default.
  • Waits for an explicit "okay" before writing .omo/plans/<slug>.md — approval authorizes the plan, not execution.
  • Emits every task as a column-zero checkbox row (- [ ] 1. Title) with references, acceptance criteria, agent-executable QA, and commit boundaries.
  • Saying "high accuracy" forces a dual review pass (momus + oracle) before handoff.

Who it's for

  • Anyone burned by an agent that started editing 30 files before understanding the request.
  • Teams that want a written, reviewable spec before large refactors or new features.
  • Senior engineers who separate plan → approve → execute into distinct sessions.
  • Existing users of the oh-my-openagent / OpenCode workflow.

Examples

  1. Fuzzy brief: "make auth better" → routed UNCLEAR, the skill researches, adopts and announces best-practice defaults, auto-runs high-accuracy review, and hands you a plan without an interview.
  2. Sharp brief: "add a 5/min-per-IP rate limit to /login" → routed CLEAR, it inspects your middleware, asks only owner-level decisions (e.g. counter storage backend), then writes the plan after approval.
  3. You want questions: say "interview me" and the default-adoption filter switches off — every surviving fork comes back to you as a question.

· · · 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/shared-skills/skills/ulw-plan folder from the GitHub repo code-yeongyu/oh-my-openagent into my ~/.claude/skills/code-yeongyu-ulw-plan-3/.
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/shared-skills/skills/ulw-plan ~/.claude/skills/

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

  1. Open a terminal.
  2. Clone the repo to a temp folder: git clone https://github.com/code-yeongyu/oh-my-openagent.git /tmp/oh-my-openagent
  3. Create the skills folder: mkdir -p ~/.claude/skills
  4. Copy the skill: cp -r /tmp/oh-my-openagent/packages/shared-skills/skills/ulw-plan ~/.claude/skills/
  5. Confirm the references/ directory and scripts/scaffold-plan.mjs came along — the skill depends on both.
  6. Make sure Node.js (or Bun) is installed: node -v
  7. Restart Claude Code and activate it yourself by typing "ulw-plan" or "plan this before coding" — the skill deliberately never self-activates.
  8. Plan artifacts land in .omo/drafts/ and .omo/plans/ inside your project; add them to .gitignore if you don't want them committed.
View source on GitHub ↗License: NOASSERTION