By erkandogan
Orchestrate teams of 12 specialized AI agents to collaboratively plan complex tasks, implement code, review for quality and security, debug in parallel, manage git workflows, and execute via persistent multi-project sessions controllable from Telegram or Slack.
npx claudepluginhub erkandogan/oh-my-teamMaster conductor agent. Reads work plans from .sisyphus/plans/, breaks them into tasks, delegates to specialized teammates, verifies every result. Never writes code itself - orchestrates only. Use with /oh-my-team:start-work.
Fast codebase search specialist. Answers 'Where is X?', 'Which file has Y?', 'Find the code that does Z'. Spawn multiple in parallel for broad searches. Read-only.
Autonomous deep implementation worker. Full tool access for complex coding tasks. Explores codebase patterns, implements end-to-end without hand-holding. Use for heavy implementation, debugging, and QA execution.
Session manager for Oh My Team hub. Receives messages from Telegram/Slack. Manages multiple project sessions via omt CLI. Never writes code.
Documentation and OSS research specialist. Finds official docs, best practices, production-quality patterns from open source. Use for external knowledge, library APIs, and battle-tested implementation patterns. Read-only.
Pre-planning gap analyzer. Catches hidden intentions, ambiguities, and AI failure points BEFORE plan generation. Identifies missed questions, scope creep risks, and unvalidated assumptions. Read-only consultant.
Ruthless plan reviewer. Validates work plans for executability and reference accuracy. Approval-biased - only rejects for true blockers (missing files, impossible tasks, contradictions). Maximum 3 issues per rejection.
Read-only strategic technical advisor. High-IQ reasoning specialist for debugging hard problems, architecture design, and code quality review. Use after 2+ failed fix attempts, for multi-system tradeoffs, or after significant implementation.
Strategic planning consultant. Interviews users to gather requirements, researches codebase patterns, generates detailed work plans. Read-only - never writes code. Use for complex tasks that need structured planning before implementation.
Code quality reviewer. Examines code across 10 dimensions: correctness, patterns, naming, errors, types, performance, abstraction, testing, API design, tech debt. Categorizes findings by severity: CRITICAL/MAJOR/MINOR/NITPICK.
Security-focused code reviewer. Checks for OWASP top 10, input validation, auth/authz, secrets exposure, dependency vulnerabilities, crypto usage, path traversal, and error leakage. Only CRITICAL/HIGH findings block review.
Primary orchestrator agent. Handles tasks directly when simple, auto-escalates to planning/teams/review when complex. Uses the full Oh My Team toolkit proactively.
Utility: Detect and remove AI-generated code slop. Finds unnecessary comments, over-engineering, verbose error handling, premature abstractions. Solo operation, no team needed.
Multi-hypothesis parallel debugging with agent teams. Spawns multiple investigators to test competing theories simultaneously. They challenge each other's findings.
Frontend and UI/UX development guidance. Provides patterns for responsive design, accessibility, component architecture, state management, and visual consistency. Load this skill when working on any frontend task.
Utility: Atomic commit workflow. Analyzes changes, groups into logical commits, writes clear commit messages. Solo operation, no team needed.
Strategic planning workflow. Creates an agent team with Prometheus (interview), Metis (gap analysis), and optionally Momus (plan review). Generates detailed work plans to .sisyphus/plans/.
5-agent parallel review gate using agent teams. Spawns Goal Verification, QA Execution, Code Quality, Security Audit, and Context Mining teammates. ALL must pass.
Execute a work plan using Atlas orchestration with agent teams. Reads plan from .sisyphus/plans/, creates a team, spawns specialized teammates to execute tasks in parallel waves.
Force agent team mode. Creates a named team with tmux split panes and spawns specialized teammates. Use this when you want visible, persistent teammates instead of background subagents.
Orchestrate multi-agent teams for parallel code review, hypothesis-driven debugging, and coordinated feature development using Claude Code's Agent Teams
Admin access level
Server config contains admin-level keywords
Executes bash commands
Hook triggers when Bash tool is used
Share bugs, ideas, or general feedback.
Reference skills for Claude Code Tasks and Agent Teams features
AI team role and worker manager for multi-agent development workflows.
24 commands, 8 agents. Loops, swarms, and teams powered by Claude Code's built-in Task System. Native task dependencies, ctrl+t progress, automatic persistence.
Manus-style context engineering for Claude Code Agent Teams. Coordinate multiple agents with shared planning files, structured task assignment, and persistent memory. Based on planning-with-files methodology.
Multi-agent team orchestration for Claude Code. Set up parallel AI agent teams with file-based planning, progress tracking, and role-based collaboration.
Modifies files
Hook triggers on file write and edit operations
Modifies files
Hook triggers on file write and edit operations
Uses power tools
Uses Bash, Write, or Edit tools
Uses power tools
Uses Bash, Write, or Edit tools
Share bugs, ideas, or general feedback.