app-dev-team
A team of AI agents for building iOS and Android apps from a plain idea, covering planning, design, development, code review, QA, and release. Suits developers who want a structured studio workflow inside Claude Code.

A team of AI agents for building iOS and Android apps from a plain idea, covering planning, design, development, code review, QA, and release. Suits developers who want a structured studio workflow inside Claude Code.
Use as a pass/fail gate on any diff with a user-facing surface — by code-reviewer during review, by qa-engineer during the test…
Use before spawning any agent that writes files, and by every developer/fixer agent as its first and last action. Gives each…
Use to produce the technical architecture doc and engineering principles for a mobile app. Used primarily by the CTO agent.…
Use to validate docs/31-board.md before spawning any agent, and to verify a developer's "DONE" claim before moving a row to…
Use when pointing the team at an EXISTING, already-built app instead of a blank project — detects the stack, reverse-engineers…
Use when deciding or revisiting how the product makes money — pricing, tiers, trial shape, ad load, unit economics — by ceo when…
Use when writing or reviewing any string a user reads — labels, buttons, empty states, errors, permission prompts, onboarding,…
Run before changing a repository to verify branch, worktree, ticket, dependencies, source-of-truth documents, and unresolved…
Use before changing any persisted schema — by backend-developer on a server store, by web-developer on a client or server store,…
Use when reviewing code, auditing an app, writing a guard rule or test, or certifying any threshold/constant/formula. Finds the…
Audit declared dependencies, lockfiles, tool versions, compatibility, licenses, and upgrade evidence before implementation or…
Use when defining or extending design tokens and the shared component library — by product-designer when writing…
Use to implement Android features in Kotlin/Jetpack Compose from a ticket. Reads a ticket ID + impl spec, writes the code, writes…
Use to prepare the store presence — App Store / Play listing copy, keyword research, screenshots, and the store-readiness gate…
Use when a ticket needs API or backend work — endpoints, data models, auth, integrations, infra-as-code. Only spawned when…
Use as the top-level orchestrator at the start of any new app project, or when the user wants strategic direction, scope…
Use as the single founder interface — prepares decision briefs, tracks unresolved commitments, ensures every founder decision…
Use after a developer finishes a ticket and before tech-manager merges. Reviews a single branch / diff against the impl spec, the…
Use after the CEO has set vision, or whenever the project needs product depth — PRD, user stories, acceptance criteria,…
Use after the CEO sets vision, or whenever the project needs technical strategy — platform choice, architecture, build-vs-buy,…
Use to design the analytics event schema, ensure every P0 feature is instrumented, verify the consent gate, and after launch…
Use to set up and own the repository's plumbing — git branch model, commit/PR conventions, CI, signing, fastlane, build flavors,…
Use only when incident-ledger.mjs has an open sev1/sev2 record — a production incident, not a routine bug. Owns severity,…
Use to implement iOS features in Swift/SwiftUI from a ticket. Reads a ticket ID + impl spec, writes the code, writes the tests,…
Grade an existing app against the Mobify Studio House KB and Axiom standards — fan out the specialist auditors, produce a…
Run the sprint — launch developer agents in parallel, review each PR, gate to QA, surface bugs back into the loop
Check a role before granting an operation on a path:
Create a deterministic provenance manifest before an agent starts work:
Open the full control room — five screens (Mission Control, Communications, Board, Team, Founder Inbox) in the browser
Open the emergency/diagnostic dashboard — zero-dependency, single file, works when the build stack is broken
Evaluation manifests define reproducible cases with an executable command, expected exit code, and required evidence text:
Before merge, map every changed file to declared downstream consumers:
Use the incident ledger for production or release-health events, not a normal ticket completion:
Start a new mobile app project — runs requirements intake, then CEO vision, then PRD + architecture in parallel
Mine a shipped app's conventions into the living House Knowledge Base — adds net-new learnings to knowledge/*.md, harvests its…
Before respawning or replacing a manager, inspect its durable lease:
Is this you? Claim your profilePut a plugin at the top of Plugins, from $9