My macOS development environment: agterm + Claude Code workflow, fish, zellij bridge for a second Mac, yashiki tiling WM, karabiner layout generator - all dotbot-managed
Agent
Use this agent when you need expert guidance on designing, implementing, or optimizing AI agent systems for production environments. Examples include: when you're architecting a multi-agent system and need advice on agent coordination patterns; when you're struggling with context management across agent interactions…
Agent
Use this agent when you need an external expert opinion from OpenAI Codex on code-related questions, best practices, or technical insights. This agent provides read-only consultation by querying the Codex CLI tool.
Agent
Use this agent when you need to optimize prompts specifically for GPT-5's unique capabilities and characteristics. Examples include: when you need to control "agentic eagerness" in GPT-5 workflows, when you want to leverage GPT-5's reasoningeffort parameter, when you're designing prompts for GPT-5's enhanced…
Agent
Use this agent when you need to improve the performance of AI prompts, system instructions, or agent configurations. Examples include: when an existing agent is producing inconsistent results, when you want to optimize a prompt for better accuracy or efficiency, when you need to redesign system instructions for…
Agent
Audits a single Claude Code skill candidate (URL + author) for topic relevance and author quality. Spawned in parallel by the skill-finder skill - one subagent per candidate - and returns a structured JSON verdict. Do not invoke directly; use the skill-finder skill, which orchestrates gathering, fan-out, and…