Multi-agent orchestration with Ultrawork mode (Sisyphus Mode) for obsessive task completion
Technical writing specialist for creating clear, accurate documentation. Use for README, API docs, architecture docs, and code comments.
Contextual grep for codebases. Answers "Where is X?", "Which file has Y?", "Find the code that does Z". Specify thoroughness: quick, medium, or very thorough.
Expert in frontend UI/UX for visual changes. Use for styling, layout, animation, responsive design, and visual polish. NOT for logic/state changes.
Specialized in external documentation, open-source codebases, and finding implementation examples. Use when working with unfamiliar libraries.
Visual analysis specialist for PDFs, images, screenshots, and diagrams. Extracts and interprets information from visual media.
Matches all tools
Hooks run on every tool call, not just specific ones
Uses power tools
Uses Bash, Write, or Edit tools
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Multi-agent orchestration for Claude Code, inspired by oh-my-opencode
Version: 1.2.0 | Changelog | ROADMAP
A Claude Code plugin providing specialized agents that work together through intelligent delegation.
oh-my-claude-code brings the power of multi-agent orchestration to Claude Code. It provides:
ulw magic keywordconfig/index.js# Add the marketplace
/plugin marketplace add https://github.com/zephyrpersonal/oh-my-claude-code
# Install the plugin
/plugin install oh-my-claude-code@oh-my-claude-code-plugins
git clone https://github.com/zephyrpersonal/oh-my-claude-code.git
/plugin marketplace add ./oh-my-claude-code
/plugin install oh-my-claude-code@oh-my-claude-code-plugins
oh-my-claude-code/
├── .claude-plugin/
│ ├── plugin.json # Plugin manifest
│ └── marketplace.json # Local marketplace config
├── hooks/
│ ├── hooks.json # Hooks configuration
│ ├── ultrawork-detector.js # Detects ulw keyword
│ ├── todo-continuation-enforcer.js
│ └── post-tool-processor.js # Unified PostToolUse handler
├── config/
│ └── index.js # Centralized configuration
├── utils/
│ ├── validation.js # Parameter validation
│ ├── patterns.js # Pre-compiled regex
│ └── progress-reporter.js # Progress visualization
├── commands/
│ └── ulw.md # Slash command
├── agents/
│ ├── orchestrator.md
│ ├── explore.md
│ ├── librarian.md
│ └── ...
├── skills/
│ └── ultrawork/
│ └── SKILL.md
├── docs/
│ └── WEEK1-2-SUMMARY.md # Development summaries
├── ROADMAP.md # 48-week iteration plan
└── package.json
| Agent | Model | Cost | Purpose |
|---|---|---|---|
| orchestrator | inherit | EXPENSIVE | Task classification and delegation |
| explore | haiku | FREE | Internal codebase search |
| librarian | sonnet | CHEAP | External docs and research |
| oracle | opus | EXPENSIVE | Architecture and deep analysis |
| frontend-ui-ux-engineer | sonnet | CHEAP | Visual/UI changes |
| document-writer | sonnet | CHEAP | Technical documentation |
| multimodal-looker | sonnet | CHEAP | PDF/image analysis |
See AGENTS.md for detailed information about each agent.
Ultrawork is a special mode that enables obsessive task completion.
Add ulw, ultrawork, or uw anywhere in your message:
claude "Implement user authentication, ulw"
claude "ulw refactor the database layer"
ULW supports optional parameters for fine-tuned control:
| Parameter | Default | Description |
|---|---|---|
--max-iterations N | 50 | Maximum continuation attempts |
--thoroughness LEVEL | thorough | Search depth: quick, medium, thorough |
--no-diagnostics | (enabled) | Disable auto-diagnostics reminders |
--completion-signal "TEXT" | (none) | Custom completion signal phrase |
Examples:
# Limit iterations
claude "implement auth, ulw --max-iterations 20"
# Custom completion signal
claude "add tests ulw --completion-signal 'all tests pass'"
# Quick search mode
claude "ulw --thoroughness quick fix the typo"
# Combined parameters
claude "refactor cache layer, ulw --max-iterations 30 --thoroughness medium"
"Like Sisyphus, you roll the boulder every day. You don't stop until you reach the top."
npx claudepluginhub zephyrpersonal/oh-my-claude-code --plugin oh-my-claude-codeMulti-agent orchestration for complex tasks using cc-mirror tasks and TodoWrite. Use when tasks require parallel work, multiple agents, sophisticated coordination, or decomposition into parallel subtasks.
Multi-agent orchestrator — supervisor loop that launches agents to implement plans
This skill should be used when the model's ROLE_TYPE is orchestrator and needs to delegate tasks to specialist sub-agents. Provides scientific delegation framework ensuring world-building context (WHERE, WHAT, WHY) while preserving agent autonomy in implementation decisions (HOW). Use when planning task delegation, structuring sub-agent prompts, or coordinating multi-agent workflows.
Agent Script workflows end to end: the ultracodex runner skill (execute multi-agent workflows on the OpenAI Codex CLI), the model-agnostic agent-script-authoring skill, and a seven-shape example gallery.
Cross-session Save/Load, and Ultrawork inspired by oh-my-opencode with Ralph Loops
Multi-agent orchestration system for Claude Code