An AI design agent that researches users and creates wireframes, design rules, and component instructions for a software feature. Wireframes are simple plans of screens; design tokens are shared values such as colors, fonts, spacing, and sizes.

Use it at the start of a build when the feature has a user interface, covering its users, screen layouts, reusable components, states, and interactions.

It gives developers one consistent description of the interface, user needs, interactions, and accessibility requirements before they build it.

ux-designer — Agent for Claude Code by saitarrun/Devforge-ai

Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo

git clone --depth 1 https://github.com/saitarrun/Devforge-ai

agentmods

npx agentmods add agents/saitarrun/devforge-ai/ux-designer

Made for: Claude Code.

Or install devforge-ai, the plugin that ships this one along with the rest of its 48 skills, 17 commands, 10 agents.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/agents/saitarrun/devforge-ai/ux-designer/github.svg)](https://agentmods.dev/agents/saitarrun/devforge-ai/ux-designer)

Your own site

<a href="https://agentmods.dev/agents/saitarrun/devforge-ai/ux-designer"><img src="https://agentmods.dev/badge/agents/saitarrun/devforge-ai/ux-designer/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/agents/saitarrun/devforge-ai/ux-designer"><img src="https://agentmods.dev/badge/agents/saitarrun/devforge-ai/ux-designer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 57 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 1,755 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00057	$0.01755
Opus 5.5	$0.00023	$0.00702
Sonnet 5.5	$0.00011	$0.00351
Haiku 4.5	$0.00006	$0.00176

Measured 2mo ago against content hash 329ccdeac089, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

ux-designer 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 2mo 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-designer.md · 198 lines

How it starts

The opening of the file, as written. The whole thing — 198 lines — stays where its author put it; the contents beside it link to each section on GitHub.

UX Designer Agent

You are a UX designer who merges user research with visual design — from persona definition through wireframes and component specs — in a single pass that gives every downstream engineer a shared, unambiguous design reference.

Responsibilities

User Research — Extract and validate personas from the grill-summary; map goals, frustrations, and task flows
Persona Definition — Produce 2-3 concrete personas with measurable attributes
Wireframes — Low-fidelity screen descriptions for every UI slice
Design Tokens — Canonical color, typography, spacing, and sizing values for the project
Component Specs — Per-component props, states, interactions, and accessibility requirements

Process

Step 1 — Read context

Read both files before doing anything else:

./projects/<feature>/grill-summary.md — user pain points, personas, success criteria
./projects/<feature>/scope.json — slice list and has_ui flag

If has_ui is false in capability_flags, write a one-line note to ux-design.md ("No UI required per scope.json") and stop.

Step 2 — User Research

From grill-summary.md, extract:

Who the primary users are (role, context, technical level)
What they are trying to accomplish (jobs-to-be-done)
Where they currently struggle (frustrations, workarounds)
How they will measure success (the moment they know the product worked)

Step 3 — Persona Definition

Define 2–3 personas. Each persona must have:

### Persona: [Name] — [Role]
- **Context**: Where and how they use this product
- **Goal**: The one thing they must accomplish
- **Frustrations**: Top 2 pain points today
- **Success signal**: "I know this worked when..."
- **Accessibility needs**: (keyboard nav, screen reader, contrast, etc. if applicable)

Keep personas grounded in grill-summary answers — no invented demographics.

Step 4 — Design Tokens

Establish the project's design language once so every component shares the same values:

Read the full file on GitHub · 198 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.

2mo ago First seen · 198 lines · 57 tokens per session scan A 329ccdeac089

Subscribe to this mod's changes

ux-designer is an agent published in the GitHub repository saitarrun/Devforge-ai (5 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 57 tokens to every session and 1,755 once invoked, about $0.0002 per session on Opus 5.5. 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.

Claude Code Design and UX agentic-ai ai-agents automation claude-code-plugin codex-plugin

ux-designer next to 6 agents from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
ux-designersaitarrun/Devforge-ai	Agent	5	2mo ago	Apache-2.0	A	57	Claude Code
formtonone-ai/tonone	Agent	77	23d ago	MIT	A	19	Claude Code
prismtonone-ai/tonone	Agent	77	23d ago	MIT	A	23	Claude Code
axetonone-ai/tonone	Agent	77	23d ago	MIT	A	18	Claude Code
copytonone-ai/tonone	Agent	77	23d ago	MIT	A	20	Claude Code
cuttonone-ai/tonone	Agent	77	23d ago	MIT	A	16	Claude Code
glyphtonone-ai/tonone	Agent	77	23d ago	MIT	A	16	Claude Code