What are the naming conventions for agent identifiers?

Identifiers must be between 3-50 characters, use only lowercase letters, numbers, and hyphens, and must start and end with an alphanumeric character.

How do I restrict the tools an agent can access?

You can define a 'tools' array in the agent's YAML frontmatter to limit access to only necessary functions like ['Read', 'Write'], following the principle of least privilege.

What model should I use for my Claude Code agent?

It is recommended to use 'inherit' as the model value, which allows the agent to use the same model as its parent process, maintaining consistency and cost-efficiency.

Why are triggering examples important in agent descriptions?

Examples help Claude understand the specific context and user requests that should activate an agent, ensuring the right specialized tool is used for the right task.

What is a Claude Code Agent?

An agent is an autonomous subprocess within a Claude Code plugin designed to handle complex, multi-step tasks independently using a specific persona and toolset.

Agent Development for Claude Code

Name: Agent Development for Claude Code
Author: nordeim

bynordeim

Developer Tools

Standardizes the creation of autonomous agents and subagents within Claude Code plugins using best practices for system prompts and triggering logic.

About

This skill provides a comprehensive framework for developing autonomous agents within the Claude Code ecosystem. It guides developers through the entire lifecycle of agent creation, from defining precise triggering conditions and YAML frontmatter to crafting robust system prompts and implementing validation rules. By utilizing this skill, developers can build specialized subprocesses that handle complex, multi-step tasks independently, ensuring consistent behavior, optimal tool usage, and seamless integration with Claude Code plugins. It covers critical concepts like namespacing, tool restriction, and visual identification through color coding.

Key Features

Standardized YAML frontmatter templates for agent metadata and configuration.
Comprehensive validation rules for identifiers, descriptions, and prompt length requirements.
Best practices for system prompt design focusing on core responsibilities and analysis processes.
Framework for AI-assisted agent generation and structured manual implementation workflows.
0 GitHub stars
Detailed guidance on creating effective triggering conditions with example blocks.

Use Cases

Building specialized autonomous subagents like code reviewers, test generators, or security analyzers.
Optimizing agent triggering logic to ensure high accuracy when Claude selects between different specialized tools.
Designing complex plugin architectures that require multi-step task handling without direct user intervention.

About

Key Features

Standardized YAML frontmatter templates for agent metadata and configuration.
Comprehensive validation rules for identifiers, descriptions, and prompt length requirements.
Best practices for system prompt design focusing on core responsibilities and analysis processes.
Framework for AI-assisted agent generation and structured manual implementation workflows.
0 GitHub stars
Detailed guidance on creating effective triggering conditions with example blocks.

Use Cases

Building specialized autonomous subagents like code reviewers, test generators, or security analyzers.
Optimizing agent triggering logic to ensure high accuracy when Claude selects between different specialized tools.
Designing complex plugin architectures that require multi-step task handling without direct user intervention.