This is a learning resource for building autonomous agents in Claude Code, covering the fundamentals of agent structure and behavior design. It walks through the markdown file format with YAML frontmatter, how to write triggering conditions that fire agents automatically, and system prompt patterns that define agent behavior. Use this if you're trying to understand when to build an agent versus a command, or if you need a reference for the agent file format. The skill itself is documentation and templates rather than executable code, so think of it as onboarding material for the agent development model. It comes from a broader template repository with 27K GitHub stars.

GitHub stars
30.2K
last updated
Aug 21, 2026

Install

$ npx -y skills add davila7/claude-code-templates --skill 'Agent Development' --agent claude-code

Installs into .claude/skills of the current project.

Files

Agent Development for Claude Code Plugins

Overview

Agents are autonomous subprocesses that handle complex, multi-step tasks independently. Understanding agent structure, triggering conditions, and system prompt design enables creating powerful autonomous capabilities.

Key concepts:

  • Agents are FOR autonomous work, commands are FOR user-initiated actions
  • Markdown file format with YAML frontmatter
  • Triggering via description field with examples
  • System prompt defines agent behavior
  • Model and color customization

Agent File Structure

Complete Format

---
name: agent-identifier
description: Use this agent when [triggering conditions]. Examples:

<example>
Context: [Situation description]
user: "[User request]"
assistant: "[How assistant should respond and use this agent]"
<commentary>
[Why this agent should be triggered]
</commentary>
</example>

<example>
[Additional example...]
</example>

model: inherit
color: blue
tools: ["Read", "Write", "Grep"]
---

You are [agent role description]...

**Your Core Responsibilities:**
1. [Responsibility 1]
2. [Responsibility 2]

**Analysis Process:**
[Step-by-step workflow]

Sponsors

Details

Repository
github.com/davila7/claude-code-templates
Category
AI & Agent Building
First seen
Jun 3, 2026

More from davila7/claude-code-templates

All 618
1PostHog avatarimplementing-agent-modesPostHog/posthog-fossGuidelines to create/update a new mode for PostHog AI agent. Modes are a way to limit what tools, prompts, and prompt injections are applied and under what cond0skills.sh installs
2ruvnet avatarAgentDB Vector Searchruvnet/rufloImplement semantic vector search with AgentDB for intelligent document retrieval, similarity matching, and context-aware querying. Use when building RAG systems0skills.sh installs
3spencermarx avatarAgentDB Vector Searchspencermarx/open-code-reviewImplement semantic vector search with AgentDB for intelligent document retrieval, similarity matching, and context-aware querying. Use when building RAG systems0skills.sh installs
4sunflowermm avatarxrk-mcpsunflowermm/XRK-AGT当你需要理解或扩展 MCP 工具(Model Context Protocol)、工具注册/分组/远程 MCP 连接与 LLM tool calling 的关系时使用。0skills.sh installs
5inference-sh avatarai-image-generationinference-sh/skillsGenerate AI images with GPT-Image-2, FLUX, Gemini, Grok, Seedream, Reve and 50+ models via inference.sh CLI. Models: GPT-Image-2, FLUX Dev LoRA, FLUX.2 Klein Lo1.7Mskills.sh installs
6xixu-me avatarrunning-claude-code-via-litellm-copilotxixu-me/skillsUse when routing Claude Code through a local LiteLLM proxy to GitHub Copilot, reducing direct Anthropic spend, configuring ANTHROPIC_BASE_URL or ANTHROPIC_MODEL520.2Kskills.sh installs