Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.
Operating procedures for AI agents in destino-binacional. Use when unsure how to approach a task, how to save tokens, or how this repo expects agents to work. Read AGENTS.md first.
Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.
Laravel 11 + Inertia (React, TypeScript) app with Vite, Tailwind, Ziggy, and Sanctum. Use when editing PHP backend, Inertia pages, dashboard/site UI, routes, or when the user mentions destino-binacional, this repo, or its stack.
Spec-driven development for destino-binacional. Use when starting a new feature, behavior change, multi-file refactor, or when the user mentions spec, specification, SDD, or acceptance criteria. Requires a spec in specs/ before non-trivial implementation.