Claude Code agent generation system that creates custom agents and sub-agents with enhanced YAML frontmatter, tool access patterns, and MCP integration support following proven production patterns
npxskills add alirezarezvani/claude-code-skill-factory--skill agent-factoryLoading…
A comprehensive system for generating production-ready Claude Code agents and sub-agents. This skill provides templates, standards, and generation tools to create custom agents that seamlessly integrate with Claude Code's agent system.
This skill helps you create custom Claude Code agents for any domain or workflow. It generates properly formatted agent files that Claude Code can automatically discover and invoke when relevant.
Every generated agent includes rich metadata:
---
name: agent-name-kebab-case
description: When to invoke this agent
tools: Read, Write, Edit # Comma-separated
model: sonnet # sonnet|opus|haiku|inherit
color: green # Visual categorization
field: frontend # Domain area
expertise: expert # beginner|intermediate|expert
mcp_tools: mcp__playwright # MCP integrations
---
Development: frontend, backend, fullstack, mobile, devops
Quality: testing, security, performance
Strategic: product, architecture, research, design
Domain: data, ai, content, finance, infrastructure
AGENT_NAME: my-custom-agent
DESCRIPTION: What this agent does and when to invoke it
DOMAIN_FIELD: frontend
TOOLS_NEEDED: Read, Write, Edit, Bash
.claude/agents/ or ~/.claude/agents/@agent-factory
Create a custom agent:
Name: api-integration-specialist
Type: Implementation
Domain: backend
Description: API integration expert for third-party services
Capabilities: OAuth, REST clients, error handling
Tools: Read, Write, Edit, Bash
MCP: mcp__github
Output: Complete .claude/agents/api-integration-specialist.md file
Each generated agent is a single Markdown file:
---
name: custom-agent
description: Triggers auto-invocation
tools: Read, Write, Edit
model: sonnet
color: green
field: backend
expertise: expert
mcp_tools: mcp__github
---
You are a [role] specializing in [domain].
When invoked:
1. [Step 1]
2. [Step 2]
3. [Step 3]
[Detailed instructions]
[Checklists]
[Best practices]
[Output format]
1. product-planner → Creates requirements
2. frontend-developer + backend-developer → Build (parallel)
3. test-runner → Validates (sequential)
4. code-reviewer → Reviews (sequential)
1. debugger → Analyzes issue
2. [appropriate-dev-agent] → Fixes
3. test-runner → Validates fix
1. code-reviewer → Quality review (can run solo)
2. security-auditor → Security scan (can run solo)
Common MCP servers to integrate:
Agents automatically reference MCP tools in their capabilities when configured.
Agents consume system resources. Monitor with:
ps aux | grep -E "mcp|npm|claude" | wc -l
Safe ranges:
Warnings:
30: Reduce parallelization
60: Critical - restart system
✅ Safe: 4-5 strategic agents in parallel ✅ Safe: 2-3 implementation agents coordinated ❌ Unsafe: Quality agents in parallel (crashes system)
Generated Agent Files:
Place in one of these locations:
Project agents (shared with team):
.claude/agents/custom-agent.md
Personal agents (available everywhere):
~/.claude/agents/custom-agent.md
Create custom agents for:
Use the AGENTS_FACTORY_PROMPT.md template when:
Version: 1.0.0 Last Updated: October 22, 2025 Compatibility: Claude Code (agents system) Template Location: documentation/templates/AGENTS_FACTORY_PROMPT.md
Create or update AgentSkills. Use when designing, structuring, or packaging skills with scripts, references, and assets.
Run Codex CLI, Claude Code, OpenCode, or Pi Coding Agent via background process for programmatic control.
Create or update AgentSkills. Use when designing, structuring, or packaging skills with scripts, references, and assets.
Set up and use 1Password CLI (op). Use when installing the CLI, enabling desktop app integration, signing in (single or multi-account), or reading/injecting/running secrets via op.
Create or update AgentSkills. Use when designing, structuring, or packaging skills with scripts, references, and assets.
Run Codex CLI, Claude Code, OpenCode, or Pi Coding Agent via background process for programmatic control.
Create or update AgentSkills. Use when designing, structuring, or packaging skills with scripts, references, and assets.
Set up and use 1Password CLI (op). Use when installing the CLI, enabling desktop app integration, signing in (single or multi-account), or reading/injecting/running secrets via op.