tunnel-mcp
Create, connect, list, and inspect MCP tunnel runtimes through the local tunnel-client plugin. Use when Codex needs to manage secure MCP tunnels with aliases and native tunnel-client runtime processes.
Browse reusable Agent Skills, each with a clear purpose and practical guidance.
Create, connect, list, and inspect MCP tunnel runtimes through the local tunnel-client plugin. Use when Codex needs to manage secure MCP tunnels with aliases and native tunnel-client runtime processes.
Add a new tool to the AI dispatch agent. Use when the user wants to give the agent a new capability (e.g., "add a tool that returns load board listings older than 24h"). Walks through the four files that must change and the silently load-bearing WriteTools step.
Add a new LLM provider or model to the AI dispatch system. Use when adding a new model from an existing provider (e.g., a new Claude version) or wiring up a new OpenAI-compatible endpoint. Walks through the seven places that must change to keep pricing, quotas, and UI dropdowns in sync.
TRIGGER when user asks to add a workflow step, agent step, agentic task, task endpoint, or workflow phase. "Agent step" and "workflow step" are interchangeable - a task is a single step of a workflow / agent, whether or not the surrounding workflow calls an LLM.
TRIGGER when user asks to define a workflow graph, create an agent or agentic workflow, orchestrate tasks, or build a multi-step process. "Agent", "agentic workflow", and "workflow" are interchangeable here - an LLM is not required for a workflow to be an agent (rule-based, deterministic, and LLM-driven workflows are all agents).
Turn a HardwareVisualizer maintainer correction, repeated failure, surprising invariant, or costly investigation into an evidence-backed learning record and the right durable guardrail. Use when asked to record learnings, prevent the same AI mistake, update AGENTS/rules/hooks/skills, or when completed work reveals a reusable repository-specific lesson.
Execute code in E2B sandboxes and integrate with LLMs for tool calling. Use when building AI agents that need to run Python/JS code, analyze data, generate charts, or use LLM function calling with E2B.
Add mcp-rubber-duck MCP server to an AI coding tool (Claude Desktop, Cursor, VS Code, Windsurf, etc.)
🎀 AgenticMail — Full email, SMS, phone call-control, Telegram, media, memory, storage & multi-agent coordination for AI agents. 89 tools.
Use when applying oh-my-claude workflow guidance, ultrawork modes, agent orchestration, plan execution, or plugin configuration.