The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.
✅ Model Selection Matrix — 30+ task-specific recommendations with costs
✅ Agent Selection Guide — Find agents by role, task, or team size
✅ Cost Optimization — Save up to 82% on Claude API costs
✅ Time Savings Data — 40+ documented efficiency gains
What is This?
This is a curated library of 34 specialized Claude agent configurations organized into 7 professional categories. Each agent is a detailed markdown file containing:
Purpose — Who the agent is and what they excel at
Core Responsibilities — Specific tasks and behaviors
Key Skills — Tools, technologies, and expertise
Communication Style — How the agent interacts
Example Prompts — Ready-to-use prompts
Related Agents — Connections to other agents
Why Use Agents?
[!TIP]
Agents transform Claude from a general assistant into a domain expert with consistent behavior and specialized knowledge.
Instead of writing prompts from scratch every time, agents give Claude a persistent persona with domain expertise, consistent behavior, and task-specific knowledge.
Simple prompt:
Help me write a marketing email.
With an agent:
# Content Creator Agent
You are an expert content marketer with 10+ years of experience
creating high-converting copy for B2B SaaS companies...
The difference? Consistent quality, faster results, and expertise on demand.
Claude Code is an agentic coding tool that lives in your terminal, understands your codebase, and helps you code faster by executing routine tasks, explaining complex code, and handling git workflows - all through natural language commands.
A Claude Code plugin that automatically captures everything Claude does during your coding sessions, compresses it with AI (using Claude's agent-sdk), and injects relevant context back into future sessions.
