Autonomous 17-role mobile-app development team for Claude Code — idea to shipped iOS/Android app, parallel agents, self-reviewing, wired to Axiom/Material3/ASO skills, with a living House Knowledge Base.
Agent
Use to translate architecture into per-platform implementation specs, to design module boundaries, to set patterns the dev pod will reuse, and to make hands-on technical calls during execution. Hands-on senior engineer. Pairs with the dev pod, unblocks them on design questions, and owns the impl specs.
Agent
Use to stand up the dev pod, plan sprints, assign work in parallel, run standups, unblock ICs, and track progress. The orchestration layer between executives and ICs. Owns the sprint plan, the kanban board, and the daily report. Spawns parallel dev agents and the code-reviewer; escalates blockers to tech-lead or CTO.
Agent
Use on flagship work to build and own test infrastructure — the harness, the device and state matrix, CI test execution, evidence-bundle capture, and flake detection. Conditional role, distinct from qa-engineer's exploratory and acceptance passes. Writes code, so it runs the IC workflow.
Agent
Use to turn PRD user journeys into information architecture, navigation model, flows, and the screen-and-state inventory the dev pod builds against. Owns docs/12-flows.md. Hands the screen inventory to product-designer, who composes each screen.
Agent
Use to certify anything the team asserts but nobody executed — a threshold or constant that makes a real-world claim, a new guard rule/lint rule/architecture test, a "swept every instance" claim, or a batch of agent reports. Runs the thing instead of reading it. Triggered before /app-ship, at the end of /app-audit…
Agent
Use to implement web features from a ticket — TypeScript, a React/Next-shaped stack, and the browser platform. Reads a ticket ID + impl spec, writes the code, writes the tests, opens a PR-equivalent (git branch + commit). Multiple instances run in parallel on independent tickets. This is the IC that makes product type…