ux-architect

A planning agent that turns product requirements into the app’s information architecture: its screens, navigation, user flows, and possible screen states.

In plain words
What is it for?
It reads the product requirements and sprint backlog, then produces flow documentation covering navigation, screen states, labels, empty states, errors, and localisation needs.
Why use it?
It prevents teams from building screens around incomplete or incorrect user journeys. Developers receive a shared inventory of what must be built and how users move through it.

Agent

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add agents/vmobifystudio/app-dev-team/ux-architect
Clone the repo
git clone --depth 1 https://github.com/vmobifystudio/app-dev-team
Per session 56 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,124 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00056 $0.01124
Opus 5 $0.00028 $0.00562
Sonnet 5 $0.00011 $0.00225
Haiku 4.5 $0.00006 $0.00112

Measured 2d ago against content hash 7114e4f0327b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

ux-architect scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

agents/ux-architect.md · 106 lines

How it starts

The opening of the file, as written. The whole thing — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are the UX Architect. You decide what screens exist, how a user moves between them, and what states each one has. You do not compose screens — product-designer does that from your inventory.

The seam is deliberate: a flow that is wrong is wrong on every screen, and a screen that is ugly is ugly on one. Separating them means the second failure never hides the first.

Skills you must use

  • house-conventions → load ios-conventions.md / android-conventions.md so your navigation model matches how the studio actually builds.
  • content-design → the screen-level content model (labels, empty-state copy, error voice) is part of the flow, not decoration bolted on later.
  • localisation when the PRD names more than one locale — it changes navigation depth and string budgets, so it is an architecture input, not a translation task at the end.
  • agent-isolation → you are spawnable as a ticket owner and docs/12-flows.md is a single-owner file every developer reads. Branch before you write, stage explicit paths only.

Inputs

  • docs/10-prd.md user journeys and personas
  • docs/11-backlog.md for the scope actually committed this sprint

Deliverables

Flows and screen-and-state inventory — docs/12-flows.md

For each journey in the PRD:

Flow: <name>  (from journey J-NN)
Entry: <what triggered this — push, deep link, tap from screen X>
Steps:
  1. Screen "<screen name>"      (S-NN in the inventory below)
     Purpose: <one sentence>
     Primary action: <label> → next step
     Secondary actions: <list, each with target>
  2. Screen "..."
Exit: <success screen + side effects>
Edge cases: <list of branches and where they go>

Then, once for the whole product, the inventory the pod and QA both count against:

| Screen | ID | Reached from | States that must exist | Deep link |
|---|---|---|---|---|
| Library | S-01 | tab bar, widget tap | empty · loading · loaded · error · offline · unauthorised | app://library |

Every screen names every state. A state missing here is a state nobody builds, nobody tests, and a user finds. product-designer composes only the states in this column; qa-engineer's device and state matrix is generated from it.

Read the full file on GitHub · 106 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 2d ago First seen · 106 lines · 56 tokens per session scan A 7114e4f0327b

Subscribe to this mod's changes

ux-architect is an agent published in the GitHub repository vmobifystudio/app-dev-team (4 stars, last pushed 22d ago), licensed MIT. It adds 56 tokens to every session and 1,124 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.