SupportFlow

Enforces architecture rules and reusable coding patterns for this Tauri + Next.js desktop app. Use when implementing Tauri commands or events, frontend pages/components, i18n copy, Redux logic, title bar behavior, modal windows, or main-window layout.

Instinct-based learning system that observes sessions via hooks, creates atomic instincts with confidence scoring, and evolves them into skills/commands/agents. v2.1 adds project-scoped instincts to prevent cross-project contamination.

Suggests manual context compaction at logical intervals to preserve context through task phases rather than arbitrary auto-compaction.

Cache expensive file processing results using SHA-256 content hashes — path-independent, auto-invalidating, with service layer separation.

Cost optimization patterns for LLM API usage — model routing by task complexity, budget tracking, retry logic, and prompt caching.

Frontend development patterns for React, Next.js, state management, performance optimization, and UI best practices.

Research-before-coding workflow. Search for existing tools, libraries, and patterns before writing custom code. Invokes the researcher agent.