Help us improve
Share bugs, ideas, or general feedback.
Share bugs, ideas, or general feedback.
Share bugs, ideas, or general feedback.
By mrzhbr
Oh My OpenCode workflows ported to Claude Code — multi-agent orchestration with intent gating, planning pipelines, team orchestration, failure recovery, and autonomous execution
npx claudepluginhub mrzhbr/oh_my_openclaude --plugin omoSlash command definitions for OmO. Each `.md` file defines one command that users invoke via `/omo:<name>` in Claude Code.
Intelligent git workflow: atomic commits with style detection, rebase surgery, history archaeology
Generate session continuation context for handoff between sessions
Generate CLAUDE.md files for project directories and auto-configure Serena MCP for LSP support
Prometheus planning pipeline: interview, research, draft, gap analysis, plan, validate
Subagent definitions for the OmO multi-agent orchestration system. Each `.md` file defines one agent with frontmatter metadata and behavioral instructions.
Task conductor that executes plans by delegating to other agents. Never codes directly. Verifies every delegation result.
Team conductor — decomposes work into waves, spawns parallel workers, verifies integration
Fast codebase exploration agent. Quickly maps relevant code areas using grep, glob, and targeted reads. Strictly read-only.
The Legitimate Craftsman — Senior Staff Engineer for deep autonomous end-to-end execution. Self-manages exploration, planning, implementation, and verification.
Matches all tools
Hooks run on every tool call, not just specific ones
Executes bash commands
Hook triggers when Bash tool is used
Share bugs, ideas, or general feedback.
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge.
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge.
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Add 'ultrawork' to any prompt for maximum parallel execution.
OpenAgentsControl — multi-agent orchestration for Claude Code. Context-aware development with skills, subagents, parallel execution, and automated code review.
Multi-agent workflow extension with Claude Code support
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.
Describe your goal, approve the spec, then step away — Claude and Codex loop together until it's right.
Harness-native ECC plugin for engineering teams - 63 agents, 249 skills, 79 legacy command shims, reusable hooks, rules, MCP conventions, and operator workflows for Claude Code plus adjacent agent harnesses
Modifies files
Hook triggers on file write and edit operations
Modifies files
Hook triggers on file write and edit operations
External network access
Connects to servers outside your machine
External network access
Connects to servers outside your machine
Uses power tools
Uses Bash, Write, or Edit tools
Uses power tools
Uses Bash, Write, or Edit tools
Share bugs, ideas, or general feedback.
A Claude Code plugin that ports the multi-agent orchestration workflows from Oh My OpenCode into Claude Code's plugin system.
What it does: Transforms Claude Code from a single-agent assistant into an orchestrated multi-agent system with structured planning, delegation, verification, and failure recovery.
# Clone the repo
git clone https://github.com/mrzhbr/Oh_my_OpenClaude.git
# Copy the plugin to your Claude plugins directory
cp -R Oh_my_OpenClaude ~/.claude/plugins/omo
# Enable the plugin
claude plugin install --path ~/.claude/plugins/omo
Then restart Claude Code. The commands will be available as /ultrawork, /plan, /start-work, /team, etc.
claude plugin install doesn't work)Clone and copy:
git clone https://github.com/mrzhbr/Oh_my_OpenClaude.git
cp -R Oh_my_OpenClaude ~/.claude/plugins/omo
Add to ~/.claude/settings.json:
{
"enabledPlugins": {
"omo": true
}
}
Add to ~/.claude/plugins/installed_plugins.json inside the "plugins" object:
"omo": [
{
"scope": "user",
"installPath": "~/.claude/plugins/omo",
"version": "1.0.0",
"installedAt": "2026-03-10T00:00:00.000Z",
"lastUpdated": "2026-03-10T00:00:00.000Z"
}
]
Restart Claude Code.
| Command | What it does |
|---|---|
/ultrawork <task> | Full autonomous execution — explores, plans, implements, verifies. Won't stop until done. |
/plan <goal> | Creates a detailed implementation plan through interviews, research, and gap analysis. |
/start-work [plan] | Executes a plan via the Atlas task conductor — delegates work, verifies results. |
/team <task or plan> | Spawns Briareus for parallel worker orchestration — decomposes work into waves, runs multiple agents simultaneously. |
/init-deep [dir] | Generates CLAUDE.md files for your project directories + auto-configures Serena LSP + sets up permissions. |
/handoff | Creates a session continuation document so you can pick up in the next session. |
/refactor <desc> | Safe refactoring with impact analysis, abort conditions, and verification. |
/ralph-loop <task> | Keeps working iteratively until the task is fully complete. |
/git-master | Intelligent git: atomic commits with style detection, rebase surgery, history search. |
/stop-continuation | Emergency stop — halts all loops and resets state. |
| Agent | Role |
|---|---|
| sisyphus-junior | Focused task executor — does exactly what it's told, no more |
| hephaestus | "Senior Staff Engineer" — deep autonomous worker for complex tasks |
| prometheus | Strategic planner — interviews, researches, writes implementation plans |
| metis | Gap analyzer — finds hidden requirements and AI-slop patterns in plans |
| momus | Plan validator — "Can someone execute this without getting stuck?" |
| atlas | Task conductor — delegates work sequentially, verifies every result |
| briareus | Team conductor — the "Hundred-Handed One" — decomposes work into waves and runs multiple workers in parallel |
| oracle | Architecture consultant — called when things fail or decisions are complex |
| librarian | Documentation hunter — searches codebase, GitHub, and web in parallel |
| explorer | Fast grep — quickly maps relevant code areas |
| Hook | What it does |
|---|---|
| keyword detector | Type "ultrawork" or "ulw" to auto-activate full execution mode |
| write guard | Blocks overwriting files you haven't read — prevents accidental clobbers |
| verify reminder | Nudges to re-read files after every edit |
| comment checker | Flags AI-slop comments ("// increment counter") |
| failure tracker | After 3 failures: stops, reverts, consults Oracle agent |
| idle detector | Catches premature wrap-up when tasks remain incomplete |
| todo enforcer | Prevents stopping with incomplete todos (with exponential backoff) |
| team tracker | Logs Briareus worker completions during team sessions |
| team stop guard | Prevents stopping during active Briareus team sessions |
| MCP | Purpose | Requires |
|---|---|---|
| serena | LSP-powered code intelligence (find refs, rename, symbols) | uvx (Python) |
| grep_app | Search GitHub code via grep.app | uvx (Python) |
| context7 | Fetch up-to-date library documentation | npx (Node.js) |
Auto-detects your project type and runs the right checker:
bash ~/.claude/plugins/omo/scripts/diagnostics.sh
Supports: TypeScript, Python, Rust, Go, Java, C#, Ruby, Swift.