create-subagents

Design and manage Claude Code subagents with XML-structured prompts and tool access.

Updated Aug 23, 2026
One-click install
npx skills add https://github.com/voronerd/claude-orchestration-template --skill create-subagents-voronerd
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: create-subagents
Source: https://github.com/voronerd/claude-orchestration-template/tree/main/template_root/.claude/skills/create-subagents
Command: npx skills add https://github.com/voronerd/claude-orchestration-template --skill create-subagents-voronerd

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This Skill provides expert guidance for creating, building, and using Claude Code subagents and the Task tool. It helps teams structure agent configurations, set up tool access, and orchestrate multi-agent workflows with clear roles and constraints.

Core Features & Use Cases

  • Establish system prompts in pure XML with defined roles, constraints, focus areas, and workflows.
  • Configure tool access, memory strategies, evaluation, and prompt caching for reliable automation.
  • Generate repeatable, testable subagents that can be deployed across projects and cloned for reuse.
  • Apply multi-agent orchestration patterns (sequential, parallel, hierarchical, coordinator) to solve complex tasks.

Quick Start

Create and deploy a new subagent under the project root using the guided /agents workflow, then test it against representative tasks.

Frequently Asked Questions about create-subagents

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I design and deploy Claude Code subagents for multi-agent orchestration?

Claude Code subagents are configured using XML-structured prompts that define roles, constraints, tools, and models, enabling reliable multi-agent orchestration and task workflows across project boundaries.

What is the best way to structure prompts when building subagents?

Subagent prompts should be structured in pure XML to enforce strict prompt-caching practices, define clear focus areas, and maximize security and maintainability across multi-agent workflows.

Can I use multi-agent orchestration patterns like sequential or parallel workflows with Claude Code?

Yes, you can apply multi-agent orchestration patterns including sequential, parallel, hierarchical, and coordinator workflows to solve complex tasks reliably across project boundaries.

Do I need to configure tool access and memory management for each subagent individually?

Yes, you must configure tool access, memory strategies, and evaluation for each subagent individually to ensure safe tool access and reliable automation across different project boundaries.

How do I test and evaluate subagents before deploying them across projects?

You test subagents by running them against representative tasks using the guided agents workflow, applying evaluation and strict prompt-caching practices to ensure repeatable and testable deployments.

When should I not use a hierarchical or coordinator pattern for multi-agent tasks?

You should avoid hierarchical or coordinator orchestration patterns when tasks are simple enough to handle without cross-project boundaries, as strict XML prompts and tool access constraints add overhead.