Multi-agent orchestration for Claude Code. Specialist agents handle planning, execution, code review, debugging, and research with evidence-based verification.
npx claudepluginhub utsavbalar1231/oh-my-claudeagent --plugin oh-my-claudeagentThis plugin requires configuration values that are prompted when the plugin is enabled. Sensitive values are stored in your system keychain.
statuslineModePreferred OMCA statusline mode: off, direct, or daemon (default: direct).
${user_config.statuslineMode}enableKeywordTriggersOptional compatibility setting for legacy keyword-trigger workflows (default: false).
${user_config.enableKeywordTriggers}Create a strategic work plan via Prometheus-style interview and structured plan drafting.
Persistence loop that prevents stopping until task is verified complete by oracle.
Start a work session from a Prometheus-generated plan.
Maximum parallel execution mode. Spawns multiple agents simultaneously for fastest completion.
Ultrawork persistence loop. Like ralph, but requires Oracle verification before the loop exits. No iteration limit — only oracle-verified completion exits.
Focused task executor that works alone without delegation. Use for implementing specific tasks, bug fixes, feature additions, and code changes. Maintains strict task discipline and verification before completion.
Codebase search specialist for finding files, patterns, and implementations. Use when asking "Where is X?", "Which file has Y?", or "Find the code that does Z". Fire multiple in parallel for broad searches.
Build-fixer agent that resolves build failures, type errors, toolchain issues, and dependency problems. Named after the divine blacksmith. Use when builds fail, types don't check, or dependencies break.
External documentation and open-source code researcher. Use when looking up library usage, finding implementation examples in OSS, retrieving official documentation, or researching best practices for unfamiliar packages.
Pre-planning consultant that analyzes requests before planning. Use when requirements are ambiguous, scope is unclear, or you need to identify hidden intentions, potential AI-slop patterns, and gaps before creating a work plan.
Rigorous work plan reviewer that catches gaps, ambiguities, and missing context. Use after creating a work plan to validate clarity, verifiability, and completeness before execution. Ruthlessly critical to prevent implementation failures.
Multimodal analyst for images, PDFs, and diagrams. Use when you need interpreted/extracted data from visual content rather than raw file contents. Analyzes screenshots, UI mockups, architecture diagrams, and document pages.
Read-only strategic advisor for architecture decisions, debugging hard problems, and code reviews. Use after 2+ failed fix attempts, for multi-system tradeoffs, unfamiliar patterns, or when completing significant work that needs verification.
Strategic planning consultant that conducts requirement interviews and generates detailed work plans. Use when starting a new feature, refactoring project, or any work that needs structured planning before implementation.
Master orchestrator for complex multi-agent workflows. Use when coordinating multiple specialists, planning obsessively with todos, assessing search complexity, and delegating strategically. Ideal for open-ended tasks requiring parallel execution.
Cancel the currently active Ralph Loop.
Consolidate agent project memories and notepad learnings into a unified summary
Browser automation with persistent page state. Use when users ask to navigate websites, fill forms, take screenshots, extract web data, test web apps, or automate browser workflows.
Designer-turned-developer who crafts stunning UI/UX even without design mockups. Use for UI components, styling, layout, animations, and visual design work.
MUST USE for ANY git operations. Atomic commits, rebase/squash, history search (blame, bisect, log -S). Triggers: 'commit', 'rebase', 'squash', 'who wrote', 'when was X added', 'find the commit that'.
Unified GitHub triage for issues AND PRs. 1 item = 1 background Agent (executor). Issues: answer questions from codebase, analyze bugs, assess features. PRs: review changes, assess merge safety. All parallel, all background.
Create a detailed context summary for continuing work in a new session. Use when context is getting long, session quality is degrading, or the context window is approaching capacity.
Fix build failures, type errors, and toolchain issues via the Hephaestus build-fixer.
Generate hierarchical AGENTS.md files. Root + complexity-scored subdirectories.
Pre-planning analysis via the Metis consultant. Catches gaps, identifies risks, surfaces hidden requirements.
Configure ~/.claude/ for oh-my-claudeagent — injects orchestration block, checks deps, inspects setup state
MUST USE for any browser-related tasks. Browser automation via Playwright MCP - verification, browsing, information gathering, web scraping, testing, screenshots, and all browser interactions.
Intelligent refactoring with codebase awareness, test verification, and step-by-step execution.
Stop ALL continuation mechanisms for the current session — ralph loop, boulder state, and auto-continuation. Use when you need to pause automated work and take manual control.
Multi-agent system for Claude Code. Specialist agents for planning, execution, review, debugging, research — with persistence, parallel execution, and natural language activation.
claude plugin marketplace add UtsavBalar1231/oh-my-claudeagent
claude plugin install oh-my-claudeagent@omca
Or from inside a Claude Code session:
/plugin marketplace add UtsavBalar1231/oh-my-claudeagent
/plugin install oh-my-claudeagent@omca
Add to your project's .claude/settings.json so team members get the plugin automatically:
{
"extraKnownMarketplaces": {
"omca": {
"source": {
"source": "github",
"repo": "UtsavBalar1231/oh-my-claudeagent"
}
}
},
"enabledPlugins": {
"oh-my-claudeagent@omca": true
}
}
For GitHub Enterprise Server, use full git URLs in the source:
{
"extraKnownMarketplaces": {
"omca": {
"source": {
"source": "git",
"url": "git@github.example.com:org/oh-my-claudeagent.git"
}
}
}
}
/plugin marketplace update omca
Rebuild the locally-installed plugin cache from your dev tree:
bash scripts/package-plugin.sh ~/.claude/plugins/cache/omca/oh-my-claudeagent/$(jq -r .version .claude-plugin/plugin.json)/
Use --dry-run first to preview the file list. The script excludes dev artifacts (.omca/, .mypy_cache/, UPGRADE.md, tests/, etc.) that should not ship.
/plugin uninstall oh-my-claudeagent@omca
Run /oh-my-claudeagent:omca-setup to configure and verify dependencies. Then:
/oh-my-claudeagent:start-work — execute a ready planSpecialist agents, skills via slash commands or keyword triggers, bundled MCP servers (omca: structural search + state, grep.app: public code search, context7: library docs), hooks for persistence, context injection, and auto-approval.
jquvpython3 3.10+ast-grep CLI (ast-grep or sg)OMCA.md — Complete guide: agents, skills, workflows, MCP tools, runtime state, troubleshootingCLAUDE.md — Contributor internals: hook map, cross-file patterns, adding componentsBased on oh-my-openagent by @code-yeongyu.
MIT
Team-oriented workflow plugin with role agents, 27 specialist agents, ECC-inspired commands, layered rules, and hooks skeleton.
Matches all tools
Hooks run on every tool call, not just specific ones
Admin access level
Server config contains admin-level keywords
Executes bash commands
Hook triggers when Bash tool is used
Semantic search for Claude Code conversations. Remember past discussions, decisions, and patterns.
Upstash Context7 MCP server for up-to-date documentation lookup. Pull version-specific documentation and code examples directly from source repositories into your LLM context.
Comprehensive startup business analysis with market sizing (TAM/SAM/SOM), financial modeling, team planning, and strategic research
Comprehensive .NET development skills for modern C#, ASP.NET, MAUI, Blazor, Aspire, EF Core, Native AOT, testing, security, performance optimization, CI/CD, and cloud-native applications
Permanent coding companion for Claude Code — survives any update. MCP-based terminal pet with ASCII art, stats, reactions, and personality.
Executes bash commands
Hook triggers when Bash tool is used
Modifies files
Hook triggers on file write and edit operations
External network access
Connects to servers outside your machine
Uses power tools
Uses Bash, Write, or Edit tools
Modifies files
Hook triggers on file write and edit operations
External network access
Connects to servers outside your machine
Uses power tools
Uses Bash, Write, or Edit tools