From agent-core
Orchestrates multi-file tasks by delegating to parallel sub-agents. Use when a task spans multiple files or components and can benefit from parallel execution to save context and time.
How this skill is triggered — by the user, by Claude, or both
Slash command
/agent-core:complex-orchestratorThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Distribute multi-file work across parallel sub-agents to save context and time.
Distribute multi-file work across parallel sub-agents to save context and time.
Task spans multiple files?
│
├─ Independent? ──────► Full Parallel
├─ Some dependencies? ─► Staged Parallel (waves)
└─ Tightly coupled? ──► Sequential or single agent
Break into file-scoped units. Identify dependencies.
Launch multiple Tasks in single message:
Task({ subagent_type: "general-purpose", description: "Edit file A", prompt: "..." })
Task({ subagent_type: "general-purpose", description: "Edit file B", prompt: "..." })
## Scope
File: [path] | Task: [what to do in THIS file only]
## Context
Pattern: [consistent approach across all units]
## Constraints
- Only modify [path]
- Follow existing style
| Sub-task | Agent |
|---|---|
| Simple edit | general-purpose |
| Exploration needed | Explore → general-purpose |
| Complex logic | advanced-general-purpose |
For detailed examples and troubleshooting, see examples.md
npx claudepluginhub xmgrex/ccx-arsenal --plugin agent-coreCoordinates multi-agent work across plan/implement/test/review phases, fanning out 3+ independent workstreams in parallel. Includes a GO/NO-GO gate to assess whether parallelization is appropriate.
Launches parallel subagents via the Task tool with run_in_background: true to concurrently implement features, analyze directories, or run independent tasks.
Dispatches parallel subagents for 2+ independent tasks with no shared state. Use when tasks are well-defined and have no sequential dependency.