Routes tasks to appropriate Task tool agents (subagents). Triggers on complex multi-step tasks, research, code review, exploration, or any task benefiting from specialized agent execution...
Routes tasks to appropriate Task tool subagent types for parallel or specialized execution.
| Agent | Purpose | Best For |
|---|---|---|
| general-purpose | Multi-step research | Complex questions, code search |
| Explore | Codebase exploration | Find files, understand patterns |
| Plan | Implementation planning | Architecture, strategy |
| claude-code-guide | Claude Code help | Feature questions, how-to |
| orchestrator | Multi-domain coordination | Complex multi-agent workflows |
| strategy-analyzer | Deep strategic analysis | Refactoring, optimization |
| architect | Recursive decomposition | Complex system design |
| gemini | Long context analysis | Large codebases, multi-file bugs |
| researcher | Web research | Finding answers, investigating |
| engineer | Professional implementation | PRD execution, debugging |
Activate when task involves:
# Complexity scoring
complexity_factors:
files_affected: weight 0.3
domains_involved: weight 0.25
steps_required: weight 0.25
research_needed: weight 0.2
# Thresholds
spawn_agent_if:
complexity >= 0.7 OR
files > 20 OR
domains > 2 OR
explicit_request
Task Complexity Assessment
ā
āāā Exploration needed?
ā āāā Quick search? ā Explore (quick)
ā āāā Pattern finding? ā Explore (medium)
ā āāā Deep analysis? ā Explore (very thorough)
ā
āāā Implementation?
ā āāā From PRD? ā engineer
ā āāā Architecture? ā architect
ā āāā Strategy? ā strategy-analyzer
ā
āāā Research?
ā āāā Web search? ā researcher
ā āāā Claude Code docs? ā claude-code-guide
ā āāā Codebase context? ā gemini
ā
āāā Multi-domain?
ā āāā orchestrator
ā
āāā Code review?
āāā superpowers:code-reviewer (via skill)
| Task Type | Primary Agent | Alternatives |
|---|---|---|
| Find files by pattern | Explore | general-purpose |
| Search code for keyword | Explore | gemini |
| Plan implementation | Plan | architect |
| Deep strategic analysis | strategy-analyzer | architect |
| Large codebase analysis | gemini | Explore |
| Web research | researcher | general-purpose |
| Multi-agent coordination | orchestrator | general-purpose |
| PRD implementation | engineer | general-purpose |
| Claude Code help | claude-code-guide | - |
When tasks are independent:
Task tool (agent1) + Task tool (agent2) in parallel
When tasks depend on each other:
Task tool (research) ā Task tool (implement)
For long-running tasks:
Task tool with run_in_background=true
ā TaskOutput to retrieve results
# Quick codebase search
agent: Explore
thoroughness: quick
# Deep implementation planning
agent: Plan
complexity: high
# Large codebase bug
agent: gemini
context: 2M tokens
# Professional implementation
agent: engineer
from: PRD
# Multi-domain coordination
agent: orchestrator
domains: [frontend, backend, database]