Agent Development
Author Claude Code plugin subagents with correct YAML frontmatter, triggering examples, and system prompts when you add autonomous capabilities to your setup.
Overview
Agent Development is an agent skill for the Build phase that teaches solo builders how to structure Claude Code plugin subagents with frontmatter, triggering examples, system prompts, and tool scopes.
Install
npx skills add https://github.com/anthropics/claude-code --skill agent-developmentWhat is this skill?
- Separates agents (autonomous multi-step work) from commands (user-initiated actions) so you pick the right Claude Code p
- Defines complete agent file format: name, description with XML-style examples, model, color, and tools list in YAML fron
- Explains triggering via rich description fields with contextual user/assistant/commentary examples agents match at runti
- Covers system-prompt structure with role, core responsibilities, and behavior expectations for subprocess agents.
- Documents model inheritance, color customization, and tool allowlists for scoped autonomous runs.
- Four key concepts in the overview: autonomous vs commands, markdown frontmatter, description triggers, and system prompt
- Complete agent template includes name, description with examples, model, color, and tools in YAML frontmatter
Adoption & trust: 13.5k installs on skills.sh; 131k GitHub stars; 3/3 security scanners passed (skills.sh audits).
What problem does it solve?
You want autonomous Claude Code subprocesses but lack a consistent file format, trigger examples, and system-prompt pattern agents actually match in production.
Who is it for?
Indie builders authoring or extending Claude Code plugins who need documented subagent files with explicit trigger examples and tool allowlists.
Skip if: Teams only wiring MCP servers, one-shot slash commands, or products outside Claude Code’s agent file convention.
When should I use this skill?
User asks to create an agent, add an agent, write a subagent, agent frontmatter, when-to-use description, agent examples, agent tools, agent colors, autonomous agent, or needs guidance on agent structure, system prompts,
What do I get? / Deliverables
You ship plugin agent markdown with valid frontmatter, example-driven descriptions, and role-focused system prompts ready to invoke as scoped autonomous workers.
- Claude Code agent markdown file with YAML frontmatter and XML-style triggering examples
- System prompt section defining agent role and numbered core responsibilities
- Configured model, color, and tools allowlist for the subprocess
Recommended Skills
Journey fit
Agent files are product artifacts you create while extending Claude Code with plugin subprocesses, which is core agent-tooling work in the build phase. The skill documents markdown-plus-frontmatter structure, description triggers, tools, and prompts specifically for Claude Code agents—not generic app features or MCP wiring.
How it compares
Teaches native Claude Code agent markdown packages—not MCP servers or ad-hoc chat personas without frontmatter contracts.
Common Questions / FAQ
Who is agent development for?
Solo and indie builders shipping Claude Code plugins who create or refactor subagents, frontmatter, and autonomous routing descriptions—not casual chat-only users.
When should I use agent development?
Use it in Build → agent-tooling when you add an agent, write subagent YAML, design when-to-use examples, or need structure for model, color, and tools on Claude Code subprocesses.
Is agent development safe to install?
Treat it as documentation guidance; review the Security Audits panel on this Prism page and inspect the skill package before enabling it in your agent environment.
SKILL.md
READMESKILL.md - Agent Development
# 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 ```markdown --- 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] **Output Format:** [What to return] ``` ## Frontmatter Fields ### name (required) Agent identifier used for namespacing and invocation. **Format:** lowercase, numbers, hyphens only **Length:** 3-50 characters **Pattern:** Must start and end with alphanumeric **Good examples:** - `code-reviewer` - `test-generator` - `api-docs-writer` - `security-analyzer` **Bad examples:** - `helper` (too generic) - `-agent-` (starts/ends with hyphen) - `my_agent` (underscores not allowed) - `ag` (too short, < 3 chars) ### description (required) Defines when Claude should trigger this agent. **This is the most critical field.** **Must include:** 1. Triggering conditions ("Use this agent when...") 2. Multiple `<example>` blocks showing usage 3. Context, user request, and assistant response in each example 4. `<commentary>` explaining why agent triggers **Format:** ``` Use this agent when [conditions]. Examples: <example> Context: [Scenario description] user: "[What user says]" assistant: "[How Claude should respond]" <commentary> [Why this agent is appropriate] </commentary> </example> [More examples...] ``` **Best practices:** - Include 2-4 concrete examples - Show proactive and reactive triggering - Cover different phrasings of same intent - Explain reasoning in commentary - Be specific about when NOT to use the agent ### model (required) Which model the agent should use. **Options:** - `inherit` - Use same model as parent (recommended) - `sonnet` - Claude Sonnet (balanced) - `opus` - Claude Opus (most capable, expensive) - `haiku` - Claude Haiku (fast, cheap) **Recommendation:** Use `inherit` unless agent needs specific model capabilities. ### color (required) Visual identifier for agent in UI. **Options:** `blue`, `cyan`, `green`, `yellow`, `magenta`, `red` **Guidelines:** - Choose distinct colors for different agents in same plugin - Use consistent colors for similar agent types - Blue/cyan: Analysis, review - Green: Success-oriented tasks - Yellow: Caution, validation - Red: Critical, security - Magenta: Creative, generation ### tools (optional) Restrict agent to specific tools. **Format:** Array of tool names ```yaml tools: ["Read", "Write", "Grep", "Bash"] ``` **Default:** If omitted, agent has access to all tools **Best practice:** Limit tools to minimum needed (principle of least privilege) **Common tool sets:** - Read-only analysis: `["Read", "Grep", "G