Ultrawork Mode

by code-yeongyu

Ultrawork Mode is an AI Engineering skill for Claude Code, published by code-yeongyu in oh-my-openagent.

67.8K stars5.5K forkson code-yeongyu/oh-my-openagentAdded 2026/08/13Repository updated 2026/08/13

View source on GitHub Download repo ZIP

aiai-agentsanthropicchatgptclaudeclaude-skillscodexcursorgeminiideopenaiopencodeorchestrationtuitypescript

Install in seconds

Install Ultrawork Mode

Copy Ultrawork Mode into your Claude Code skills folder. Run the command in your terminal, or review the source on GitHub before installing.

terminal

npx degit https://github.com/code-yeongyu/oh-my-openagent/tree/dev/packages/omo-senpi/skills/ultrawork ~/.claude/skills/ultrawork

Requires Node.js. Downloads this skill only — not the rest of the repository — into your Claude Code skills folder.

Without Node.js

git clone https://github.com/code-yeongyu/oh-my-openagent.git

Clones the whole repository, then copy the skill’s own directory into your skills folder yourself.

In this catalog

Source file: packages/omo-senpi/skills/ultrawork/SKILL.md in code-yeongyu/oh-my-openagent
Installs to: ~/.claude/skills/ultrawork
Collection: One of 21 skills cataloged from this repository
Category: AI Engineering — 2451 skills

What Ultrawork Mode does

Ultrawork Mode activates a strict, evidence-driven coding workflow directive in omo-senpi when a prompt contains ultrawork or ulw, injecting it as a hidden context message ahead of the user's text.

Ultrawork Mode is cataloged under AI Engineering on DirSkills. Ultrawork Mode comes from a repository tagged ai, ai-agents, anthropic, chatgpt and claude.

Documentation

README

Excerpt

MANDATORY: First user-visible line this turn MUST be exactly: ULTRAWORK MODE ENABLED!

[CODE RED] Maximum precision. Outcome-first. Evidence-driven.

MEMORY: ALWAYS ACTIVELY RECORD AND REFERENCE MEMORY. CONSULT MEMORY BEFORE ASKING THE USER, AND SAVE DURABLE FACTS, DECISIONS, AND CORRECTIONS AS THEY EMERGE.

Role

Expert coding agent. Ship verified work. No process narration.

Deliver EXACTLY what the user asked, end-to-end working, proven by captured evidence: a failing-first proof that went RED→GREEN through the cheapest faithful channel, plus real-surface proof sized by the tier below. TESTS ALONE NEVER PROVE DONE — a green suite means the unit-level contract holds, not that the user-facing behavior works.

This is the opening of the README. Read the full README on GitHub.

Commands Ultrawork Mode provides

Slash commands named in this skill’s SKILL.md, listed in the order they first appear.

/glob

Frequently asked about Ultrawork Mode

What else does code-yeongyu publish alongside Ultrawork Mode?
Ultrawork Mode is one of 21 skills that DirSkills catalogs from code-yeongyu/oh-my-openagent, the repository it ships in. Its siblings there include Codex QA, Dead Code Removal and Get Unpublished Changes. Each one is a separate skill with its own page in this directory, installs the same way Ultrawork Mode does, and is maintained by code-yeongyu in that same repository. The rest of the collection is listed on the code-yeongyu/oh-my-openagent page.
How does Ultrawork Mode compare to other AI Engineering skills?
Ultrawork Mode ranks #76 by stars among the 2451 AI Engineering skills in this catalog. The most-starred ones next to it are Architecture Decision Records, AI-First Engineering and Agentic OS. DirSkills ranks by the star count of the repository each skill ships in, so that order reflects how popular those repositories are rather than any review of Ultrawork Mode against them. Open each page to compare what they document and how they install.