Use when an agent must open, drive, dogfood, or test the real Nevermind Electron app through its visible UI. Covers palette search, keyboard navigation, commands, action panels, extension views, AI chats, independent windows, screenshots, and multi-step user…
Use when changing or reviewing performance-sensitive Nevermind paths: command palette search, keyboard input, AI chat streaming, extension views, cache invalidation, IPC, Electron window behavior, file/icon/thumbnail/clipboard work, or any request mentioning…
Use when changing or reviewing Nevermind desktop/backend contracts - Astro API routes used by desktop, Electron backend fetches, auth/device login, token revoke, active-model descriptors, AI proxy routes, billing/rate-limit/error shapes, compatibility…
Use when changing or reviewing Nevermind Electron behavior - BrowserWindow/webPreferences, preload and IPC contracts, custom protocols, permissions, shell/file/URL actions, extension iframes, updater/packaging, platform integration, or any request mentioning…
Use when testing, reviewing, or polishing Nevermind extension API UI fixtures, host-rendered extension views, or any UI-facing extension API endpoint. Trigger on requests mentioning extension fixtures, Fixtures root item, extension UI tests, dev-only UI…
Use when improving Nevermind's extension API or builder workflow from recent local AI builder conversations. Review persisted aiChats and generated extension code, then draft actionable GitHub issues for API, host, or builder improvements.
Use for Nevermind production incidents, external configuration, or deployed-flow verification — Sentry alerts, Vercel/Axiom logs, backend 5xx, auth failures, Neon/Upstash incidents, upstream AI provider failures, GitHub release failures, desktop prod logs, or…
Use when reviewing Nevermind for security risk, threat modeling, secure-code review, dependency/config exposure, secrets, OWASP-style web/API issues, Electron attack surface, auth/session/token/billing abuse, or any request for a penetration-test/security…