A required intake command that collects ten project details before an interface is generated. It asks about the project, audience, goal, tone, constraints, references, technology, region, and success measure, then saves the answers for later commands.

Use it before generating a landing page, dashboard, admin panel, documentation site, mobile app, or email to define its audience, purpose, style, technology, locale, and success criteria.

It prevents design work from being based on guesses or vague requirements. The saved answers give later design commands concrete constraints to follow.

ux-discover — Command for Claude Code by Laith0003

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.

Clone the repo

git clone --depth 1 https://github.com/Laith0003/ux-skill

Made for: Claude Code.

Or install ux, the plugin that ships this one along with the rest of its 25 commands, 5 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/commands/laith0003/ux-skill/ux-discover.svg)](https://agentmods.dev/commands/laith0003/ux-skill/ux-discover)

Your own site

<a href="https://agentmods.dev/commands/laith0003/ux-skill/ux-discover"><img src="https://agentmods.dev/badge/commands/laith0003/ux-skill/ux-discover.svg" alt="Measured on agentmods" height="20"></a>

Per session 58 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 943 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	$0.00058	$0.00943
Opus 5	$0.00029	$0.00472
Sonnet 5	$0.00012	$0.00189
Haiku 4.5	$0.00006	$0.00094

Measured 7d ago against content hash 90dffe0b7d8f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

ux-discover 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 7d 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.

commands/ux-discover.md · 91 lines

How it starts

The opening of the file, as written. The whole thing — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/ux-discover — the forcing function

No generation without discovery.

This is the discipline gate. The 10-field intake every project goes through before /ux-design, /ux-component, /ux-recommend, or any other generation command runs. The plugin asks; you answer; the engine has constraints to work with instead of guessing.

The 10 fields:

Project type — landing / marketing-site / dashboard / admin-panel / docs / mobile-app / email
Audience — who specifically. Concrete. "B2B finance ops in MENA", not "business users."
Primary goal — ONE job for this surface. Trial signup. Pricing comprehension. At-a-glance dashboard status.
Tone — 3-5 words. warm / editorial / precise / playful / clinical / confident / calm / bold / technical.
Must-have — hard constraints. dark-mode / RTL / AA accessibility / mobile-first / print-fidelity.
Forbidden — what NOT to do. "No purple-to-blue gradient. No three-card hero. No Inter as display."
Reference brands — 3-5 real brands whose design language fits. Pulled into the recommender as exemplars.
Stack — react / nextjs / vue / svelte / blade-alpine / astro / vanilla-html.
Region / locale — mena / us / eu / apac / global. Affects RTL, typography, color norms, copy style.
Success metric — how will you know it worked? Signup CR > 4%. TTI < 2s. Lighthouse > 95.

When to use

Starting a new project, surface, or marketing page from zero.
Before any /ux-design, /ux-component, or /ux-recommend.
When picking up a stalled project and you need to re-anchor on the brief.

When to skip

You're fixing a bug in existing code → use /ux-fix.
You're auditing → use /ux-audit or /ux-lint.
You already have a .ux/last-discovery.json for this project and the brief hasn't changed.

How it runs

Inside Claude Code:

python3 -m engine.cli.main discover

The CLI walks the 10 questions interactively, then writes the answers to .ux/last-discovery.json. Subsequent commands (/ux-recommend, /ux-design, /ux-component) auto-load that file if present.

Read the full file on GitHub · 91 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.

7d ago First seen · 91 lines · 58 tokens per session scan A 90dffe0b7d8f

Subscribe to this mod's changes

ux-discover is a command published in the GitHub repository Laith0003/ux-skill (66 stars, last pushed yesterday), licensed MIT. It adds 58 tokens to every session and 943 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 2026-08-30.

Claude Code Design and UX Frontend Planning anti-ai-slop cursor design-system ux

accessibility-audit

You are an accessibility expert specializing in WCAG compliance, inclusive design, and assistive technology compatibility. Conduct comprehensive audits, identify barriers, provide remediation guidance, and ensure digital products are accessible to all users.

wshobson/agents · 0 tokens

cinematic-scroll

Build cinematic, scroll-driven websites with the cinematic-scroll skill — pinned chapter reveals, hero/multi-depth parallax, scroll-linked 3D tilt and camera moves, and environment-morphing backgrounds. From a single self-contained .html scroll section (Mode A) to a full Next.js release site with optional AI-generated…

MustBeSimo/cinematic-scroll-skill · 0 tokens

ux-discover