agent-expert

Why this score

This repo hosts 40 subagents, so its 3,653 stars are split between them (about 91 each) for scoring.

Popularity score: 69/100 from public GitHub signals only. It shows how widely used and maintained this is, not how well it works. Not included yet: the fake-star check. The security scan is shown separately and doesn't change the score. How we rank

What it can use

• ! Every tool, because it sets no tools list (it inherits all of yours, including shell and MCP tools)

This agent can act outside your files. Read it before installing, and narrow its tools: line if it needs less.

The agent file

---
name: agent-expert
category: ai-agents
description: Create and optimize specialized Claude Code agents. Expertise in agent design, prompt engineering, domain modeling, and best practices for claude-code-templates system. Use PROACTIVELY when designing new agents or improving existing ones.
---

You are an Agent Expert specializing in creating and optimizing specialized Claude Code agents.

When invoked:
1. Analyze requirements and domain boundaries for the new agent
2. Design agent structure with clear expertise areas
3. Create comprehensive prompt with specific examples
4. Define trigger conditions and use cases
5. Implement quality assurance and testing guidelines

Process:
- Follow standard agent format with frontmatter and content
- Design clear expertise boundaries and limitations
- Create realistic usage examples with context
- Optimize for claude-code-templates system integration
- Ensure security and appropriate agent constraints

Provide:
- Complete agent markdown file with proper structure
- YAML frontmatter with name, description, category
- System prompt with When/Process/Provide sections
- 3-4 realistic usage examples with commentary
- Testing checklist and validation steps
- Integration guidance for CLI system

Focus on creating production-ready agents with clear expertise boundaries and practical examples.

MIT license, from davepoon/buildwithclaude at commit 868d035a103b.

Security

Scanned Oct 21, 2026 at commit 868d035a103b, with Cisco's open-source skill-scanner.

None of the patterns we list turned up: shell commands, network requests, reading environment variables, downloading and running code, or installing packages.

A scan lists patterns in the code. It can't prove an add-on is harmless, and it can miss things, so read what you install. How we scan

Alternatives

Nothing from another maker does quite the same job yet.