openzero

Use when working on Z's persona/identity system, crew YAML definitions, agent-rules.md, prompt engineering, multi-character architecture, crew routing keywords, or the agentic intelligence layer. Expert in Semantic Priming and LLM behaviour shaping.

Use when working on FastAPI endpoints, Python services, scheduled tasks, LLM routing, message bus, memory, voice/TTS, notifier, email rules, or any external API wrapper (Calendar, Gmail, SearXNG, Qdrant, weather). Covers the entire src/backend/ codebase.

Use when working on the board/list/card system: Planka integration, operator board priority abstraction, crew-to-Planka persistence, ACTION tag execution, shopping list management, or architecting the future native openZero board replacement.

Use when working on commercialisation strategy: BSL-1.1 licensing (Change Date, Additional Use Grant), pricing models, positioning openZero as a self-hosted AI OS, developer marketing, competitive landscape analysis, landing page strategy, launch planning, or open-source community building.

Use when orchestrating a full feature that spans multiple domains (frontend + backend + crews + infra). Assesses which specialist agents are needed, delegates appropriately, then audits BUILD.md and artifacts for staleness. User-invocable orchestrator.

Use when debugging runtime issues: container logs, Docker inspect, health endpoint checks (/health, /health/qdrant, /health/planka), LLM diagnostics, Qdrant/Redis state inspection, or crew execution health monitoring (timeouts, output quality, scheduling failures).

Use when working on the CSS design system: custom properties, HSLA token chains, shared style modules, glassmorphism, rem enforcement, forced-colors/reduced-motion media queries, or theme architecture. Reference docs/artifacts/DESIGN.md.

Single entry point for everything. Describe any task or question in plain language and this agent identifies the right specialist(s), summarises the intent, and delegates autonomously.

Use when working on Docker Compose services, Traefik routing, hardware profiles, deployment (sync.sh), firewall rules (UFW/iptables), DNS/Pi-hole, voice profile containers, LLM peer discovery, config.py env var management, or SearXNG configuration.

Use when optimising performance: Lighthouse scores, Core Web Vitals, bundle analysis, Vite chunk splitting, endpoint latency, Qdrant query tuning, LLM inference profiling, Redis caching, Docker resource limits, hardware profiles, or benchmarking.

Use when designing or refining your personal operating system: weekly/daily review rituals, PKM architecture (PARA, Zettelkasten, second brain), habit system design, energy management frameworks, crew scheduling strategy, and how all life domains wire together into a coherent whole. Expert in GTD, Atomic Habits, BASB, time blocking, and personal metrics. Advisory — never modifies files directly.

Use when running a pre-commit or pre-deploy audit. Orchestrates quality-gate checks (tsc, ruff, mypy, i18n, static analysis, security tests), then delegates to security (secrets/injection), repo (dead code/deps), and perf (if performance-sensitive changes detected).

Use when writing tests, running test suites, reviewing code quality, or checking coverage. Covers security tests (268 tests, 25 attack classes), axe-core Playwright a11y, live regression, static analysis, i18n coverage, ruff, mypy, ESLint, and bandit.

Use when auditing repository hygiene: dead code detection, unused imports, orphaned translation keys, unused CSS tokens, dependency health (pip-audit, npm audit), git discipline, semver/VERSION tracking, .example file parity, or artifact currency.

Use when exploring the codebase, analysing architecture, researching documentation, performing web lookups, or planning implementation approaches. Read-only -- never modifies files. Applies active injection filtering on all web-sourced content.

Use when auditing prompt injection defences, OWASP Top 10 compliance, secrets hygiene (.env/.example parity, Trufflehog), firewall posture assessment (audit port exposure, Tailscale perimeter), bandit SAST, CodeQL review, or attack class coverage analysis.

Use when building, modifying, or debugging dashboard Web Components. Covers Shadow DOM lifecycle, data fetching, lazy-load registration, accessibility (WCAG/a11y), and the full i18n workflow: tr() strings in TypeScript plus _EN/_DE dict updates in translations.py plus test_i18n_coverage.py gate.

Use when brainstorming ideas, exploring future directions, challenging assumptions, or getting cross-disciplinary advice. Expert in HCI futures (wearable tech, ambient computing, voice-first UI, spatial computing), emerging LLM architectures, edge inference, product paradigm shifts, and competitive foresight.

Scaffold a new FastAPI REST endpoint with Pydantic models, service function stub, and dashboard integration pattern.

Run the full openZero deploy pipeline: build dashboard, commit, push, sync to VPS, and optionally run live regression tests.

Scaffold a new openZero dashboard Web Component with Shadow DOM, i18n, accessibility, and lazy-load registration.

Scaffold a new openZero native crew entry in agent/crews.yaml with characters, keywords, scheduling, and Planka persistence.

Run all pre-commit quality checks in sequence: TypeScript, ruff, mypy, i18n coverage, static analysis, and security tests.

Scaffold a complete full-stack feature: FastAPI endpoint, dashboard Web Component, i18n keys, test stubs, and documentation checks.

Create a new HSLA theme for the openZero dashboard with full 4-token primitive chains and register it in the theme catalogue.