AI Engineering

Claude Code Extension Mechanisms compares subagents, commands, and skills in Claude Code to help you choose the right mechanism for autonomous tasks, user-triggered workflows, or reusable procedures.

Vibe to Agentic Framework teaches the conceptual model behind moving from unstructured vibe coding to structured agentic engineering with Claude Code. Use it to understand the four-level journey and how each Claude Code feature—CLAUDE.md, rules, skills, agents, commands, hooks, MCP—fits into a presentation or learning plan.

CLI Models queries available AI models, lists model aliases, and browses the full model catalog from the CLI. Use it to filter by provider, search by capability, and resolve model name variants.

CLI Plugins Skills manages Omni Skills (list, install, test, remove), plugins (create, configure), and persistent memory (search, add, clear) from the command line.

CLI Providers manages provider connections from the command line, including listing, adding, testing, rotating API keys, and viewing per-provider metrics.

CLI Routing creates, lists, updates, and deletes routing combos from the command line. Use it to test routing strategies, inspect combo metrics, and configure fallback chains interactively.

Configure Codex CLI walks an agent through configuring the OpenAI Codex CLI on Linux, macOS, or Windows to use OmniRoute as an OpenAI-compatible backend, writing config.toml, profiles, and environment variables.

OmniRoute A2A lets an agent interact with the OmniRoute LLM gateway over JSON-RPC 2.0, exposing six skills: smart-routing, quota-management, provider-discovery, cost-analysis, health-report, and list-capabilities. Use it to discover providers, check quotas, estimate costs, and route prompts to the best model.

CLI MCP inspects MCP server status, lists registered tools and scopes, runs tool invocations, and manages MCP audit logs from the command line. Use it to monitor, restart, and debug MCP servers without leaving the terminal.

CLI Compression configures and tests prompt compression from the command line. It manages RTK filters, Caveman rules, stacked compression modes, and previews compression output with real prompts.

CLI Contexts manages context engineering configurations, RTK filter sets, and conversation sessions from the command line. Use it to apply context-relay settings, inspect active context pipelines, and switch among configured contexts.

CLI Eval creates and runs LLM evaluation suites from the command line, with live benchmark progress, scorecards, model comparisons, and CI integration.