C
Create Claude Code Agent
Complete guide for creating Claude Code agents with YAML frontmatter structure, agent file format, trigger condition design, and system prompt writing
byNeoLabHQ
What is it?
Agents are autonomous subprocesses spawned via the Task tool that:
- Handle complex, multi-step tasks independently
- Have their own isolated context window
- Return results to the parent conversation
- Can be specialized for specific domains
| Concept | Agent | Command |
|---|---|---|
| Trigger | Claude decides based on description | User invokes with /name |
| Purpose | Autonomous work | User-initiated actions |
| Context | Isolated subprocess | Shared conversation |
| File format | agents/.md | commands/.md |
How to use it?
Agent triggers based on prior tool usage.
<example>
Context: User made multiple edits to test files
user: "I've updated all the tests"
assistant: "Great! Let me verify test quality."
<commentary>
Multiple Edit tools used on test files. Proactively trigger test-quality-analyzer
to ensure tests follow best practices.
</commentary>
assistant: "I'll use the test-quality-analyzer agent to review the tests."
</example>
Key Features
- Complete guide for creating Claude Code agents with YAML frontmatter structure, agent file format, trigger condition design, and system prompt writing
- Seamless integration with Claude's development workflow
- Comprehensive guidelines and best practices for create claude code agent
Related Skills
More from AI & MLContext Engineering Guide
Comprehensive context engineering tutorial covering attention mechanics, progressive disclosure, context budget management, and quality vs quantity trade-offs for AI agent development
433NeoLabHQ
AI & ML
Developer Tools
Agent Evaluation Framework
Comprehensive Claude Code agent evaluation framework with multi-dimensional scoring, LLM-as-Judge mode, and research-backed performance variance analysis
433NeoLabHQ
AI & ML
Developer Tools
Create Skill (TDD Method)
TDD methodology for skill creation — test with subagents first, write skill to address failures, iterate until bulletproof against rationalization
433NeoLabHQ
AI & ML
Developer Tools