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

Ultrawork Mode (Evidence-Driven Work Directive)

Triggered by the keyword 'ultrawork' or 'ulw', it forces a failing-proof-first, real-surface-QA, cleanup-receipt workflow before anything can be called done.

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

What it does

  • A "maximum precision" operating directive that activates whenever a prompt contains ultrawork or ulw.
  • Classifies the change set once into LIGHT or HEAVY, which sizes the number of success criteria, the reviewer loop, and how much evidence must be captured.
  • Enforces a strict loop: capture a failing proof (RED) first, then the smallest production change to reach GREEN, then run the real-surface proof yourself (curl -i, a real pty/TUI, a real browser, or OS-level GUI automation) and save the artifact.
  • Keeps an append-only durable notepad created with mktemp holding the plan, file:line findings, RED/GREEN captures and evidence paths, so state survives context compaction.
  • Requires paired cleanup receipts for every QA resource (server PIDs, tmux sessions, browser contexts, ports, temp dirs) — no receipt, no completed criterion.
  • Also covers commit hygiene (one atomic commit per verified increment, mimicking existing history), subagent delegation/wait discipline, and explicit stop rules.

Who it's for

  • Developers tired of agents claiming success from inference instead of proof.
  • Team leads who want TDD and observable verification imposed on agent work.
  • omo/Codex users with create_goal, update_plan, and multi-agent tools (other stacks need tool-name substitutions).

Examples

  1. ulw fix the email validation bug → classified LIGHT, one failing test captured, minimal fix, proven with a real curl -i returning 400 plus body.
  2. ultrawork add the payment webhook integration → external integration forces HEAVY: 3+ criteria (happy path, boundary, adjacent regression), each with a literal scenario and artifact, plus a reviewer subagent loop until approval.
  3. ulw check the broken colors in this TUI screen → instead of tmux capture-pane, render through a real xterm.js web terminal, screenshot color/CJK width evidence, then log the session teardown receipt.

· · · 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/ultrawork/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/ultrawork folder from the GitHub repo code-yeongyu/oh-my-openagent into my ~/.claude/skills/ultrawork/.
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-codex/plugin/components/ultrawork/skills/ultrawork ~/.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
  3. Create the skills folder: mkdir -p ~/.claude/skills
  4. Copy the skill: cp -r oh-my-openagent/packages/omo-codex/plugin/components/ultrawork/skills/ultrawork ~/.claude/skills/
  5. Restart Claude Code (or Codex) and confirm ultrawork appears in the skill list.
  6. In omo it is injected by a UserPromptSubmit hook; without that hook, just write "work in ultrawork mode" in your prompt to trigger it.
  7. If your environment lacks create_goal, update_plan, or multi_agent_v1, edit SKILL.md to map those steps onto your available tools (e.g. TodoWrite, Task).
View source on GitHub ↗License: NOASSERTION