AI Skill MartBrowse skillsPromptsProgramsLearnWhat is a Skill?
 
← Back to list

ulw-plan — Explore-First Planning Consultant

Grounds itself in your codebase, asks only the questions exploration can't answer, and after your explicit okay writes one decision-complete work plan a worker can execute with zero follow-up interview.

Dev & CodingAdvanced★ 67,531⑂ 5,507AI score 8/10Last updated: Aug 9, 2026

What it does

  • Switches Claude into the Prometheus planner persona: reads, searches, and analyzes, but never edits product code and never delegates implementation.
  • Fans out parallel read-only exploration (LSP → ast-grep → rg) plus external doc research to settle facts before asking anything.
  • Classifies intent as CLEAR or UNCLEAR and announces the verdict: clear requests get only genuine owner-decision questions; fuzzy ones get researched best-practice defaults instead of an interview.
  • Writes the plan only after your explicit approval, into .omo/plans/<slug>.md, with column-zero task rows (- [ ] 1. title), per-task agent-executed QA (happy + failure path), a final verification wave, and a dependency matrix.
  • Keeps a durable draft at .omo/drafts/<slug>.md so a session can resume after compaction.
  • Defaults to a high-accuracy plan review gate (momus) before handoff.

Who it's for

  • Developers who want a real design doc before touching a large refactor or feature.
  • Leads who need a hard guardrail against an agent jumping straight into implementation or inventing an "MVP" scope cut.
  • Users of the oh-my-openagent (omo-senpi / OpenCode) harness with subagent delegation.

Example uses

  1. "Add a 5/min-per-IP rate limit to /login" → routed CLEAR, explores middleware and existing test patterns, asks only the owner-decisions, then writes the plan after approval.
  2. "Make auth better" → routed UNCLEAR, no extra questions, adopts and announces researched defaults, then runs the high-accuracy review automatically.
  3. "Break this migration down, high accuracy" → sets review_required, produces the plan, then reports the review verdict without starting work.

· · · 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-senpi/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 AI Skill Mart.
Copy the packages/omo-senpi/skills/ulw-plan folder from the GitHub repo code-yeongyu/oh-my-openagent into my ~/.claude/skills/code-yeongyu-ulw-plan-2/.
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 && mkdir -p ~/.claude/skills && cp -r oh-my-openagent/packages/omo-senpi/skills/ulw-plan ~/.claude/skills/ulw-plan

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

  1. Open a terminal and go to a working directory.
  2. Clone the repo: git clone https://github.com/code-yeongyu/oh-my-openagent.git
  3. Create the skills folder: mkdir -p ~/.claude/skills
  4. Copy the skill: cp -r oh-my-openagent/packages/omo-senpi/skills/ulw-plan ~/.claude/skills/ulw-plan
  5. Verify the bundled references/ folder and scripts/scaffold-plan.mjs came along — they are required to scaffold plan artifacts.
  6. Make sure Node.js (node -v) or bun is installed.
  7. Restart Claude Code and ask for ulw-plan, or say "make a plan before coding".
  8. You should see ULW-PLAN MODE ENABLED! as the first line. Note that the momus / metis reviewers are omo-senpi-specific, so the high-accuracy review step may be skipped in a vanilla Claude Code environment.
View source on GitHub ↗License: NOASSERTION