Back to Skills

agent-development

verified

This skill should be used when the user asks to "create an agent", "write an agent", "build an agent", or wants to add new agent capabilities to Claude Code.

View on GitHub

Marketplace

claude-toolkit

dwmkerr/claude-toolkit

Plugin

toolkit

Repository

dwmkerr/claude-toolkit
4stars

plugins/toolkit/skills/agent-development/SKILL.md

Last Verified

January 20, 2026

Install Skill

Select agents to install to:

Scope:
npx add-skill https://github.com/dwmkerr/claude-toolkit/blob/main/plugins/toolkit/skills/agent-development/SKILL.md -a claude-code --skill agent-development

Installation paths:

Claude
.claude/skills/agent-development/
Powered by add-skill CLI

Instructions

# Agent Development

Create effective Claude Code agents.

## Agent Colors

Agents support color assignments for visual distinction. Set in YAML frontmatter:

```yaml
---
name: explore
description: Explores codebases
color: purple
---
```

### Color Conventions

| Color | Agent Type | Purpose |
|-------|------------|---------|
| Purple | Explore | Codebase exploration, documentation |
| Blue | Plan | Analysis, planning, architecture |
| Green | Create | Testing, creation, validation |
| Orange | Debug | Debugging, refactoring |
| Yellow | Clean | Optimization, cleanup |
| Red | Reflect | Security, critical review |
| Pink | - | Available |
| Cyan | - | Orchestration, coordination |

## Agent Behavior

### Permission Denial Resilience

Subagents continue after permission denial rather than stopping entirely. When a subagent hits a permissions wall, it tries alternative approaches automatically. This makes autonomous workflows more resilient and reduces the need for human intervention.

## Important

After creating or modifying agents, inform the user:

> **No restart needed.** Agent changes take effect immediately - agents are hot-reloaded.

Validation Details

Front Matter
Required Fields
Valid Name Format
Valid Description
Has Sections
Allowed Tools
Instruction Length:
1145 chars