ux-frame

ux-frame is a command for coding agents from Laith0003/ux-skill. It costs 119 tokens per session (2,070 once invoked), scanned A, original, MIT.

A lightweight project-intake command that turns a vague idea into a short brief covering the target users, desired outcome, hypothesis, and success signal. A hypothesis is an assumption about what will help, and a success signal is how you will know it worked.

In plain words
What is it for?
Use it at the start of a project, sprint, or design task with anything from a one-line idea to a meeting transcript, or with no prepared material.
Why use it?
It prevents design work from starting without agreement about who the project serves and what should change. It also gives later reviews a shared point of reference.

Command

Part of the ux-skill plugin — 25 commands, 5 agents shipped together

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 commands/laith0003/ux-skill/ux-frame
Clone the repo
git clone --depth 1 https://github.com/Laith0003/ux-skill

Or install ux-skill, 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.

agentmods badge for ux-frame

README.md
[![agentmods](https://agentmods.dev/badge/commands/laith0003/ux-skill/ux-frame.svg)](https://agentmods.dev/commands/laith0003/ux-skill/ux-frame)
Your own site
<a href="https://agentmods.dev/commands/laith0003/ux-skill/ux-frame"><img src="https://agentmods.dev/badge/commands/laith0003/ux-skill/ux-frame.svg" alt="Measured on agentmods" height="20"></a>
Per session 119 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,070 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 $0.00119 $0.02070
Opus 5 $0.00060 $0.01035
Sonnet 5 $0.00024 $0.00414
Haiku 4.5 $0.00012 $0.00207

Measured 5d ago against content hash 0f8dedb8a176, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

ux-frame 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 5d 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-frame.md · 183 lines

How it starts

The opening of the file, as written. The whole thing — 183 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/ux-frame

You are running the /ux-frame command from the ux plugin. The job is to produce a tight, structured framing block that every downstream command can read. No design work happens here. No critique. Just the four-field intake that turns a vague request into a working brief.

When to use

Triggers: "frame this", "what's the brief", "set up the project", "framing", "what are we actually building", "frame the work", "scope this".

Use at the start of any project, sprint, or one-off engagement. Also use mid-stream if a conversation has drifted and nobody can answer "who is this for and what changes when we ship?"

Input

Anything the user has: a Slack paste, a Figma URL, a one-line idea, a ticket, a meeting transcript, or nothing. If the input already contains the four framing fields, extract them — do not re-ask.

Process

1. Extract or ask — never both

Read what the user provided. If you can confidently pull audience, outcome, hypothesis, and success_signal out of the input, skip ahead to step 3.

If any field is missing, ask ONCE with a single combined question that surfaces all gaps. Example:

"Quick framing — who specifically is this for (not 'users'), what changes for them when we ship, what's your bet on why this will work, and how will we know it worked? One paragraph is fine."

Do not ask the four questions in four separate messages. That is the failure mode this command exists to prevent.

2. Sharpen the answers

Apply these tests before accepting any field:

  • Audience — must name a real person/role/segment. Reject "everyone," "users," "people," "customers" without further qualifier. Push back specifically: "Which customers? Returning ones? First-time? A specific tier?"
  • Outcome — must describe a behavior or state change for the audience, not a feature. Reject "make it better," "improve UX," "modernize." Push back: "What does the audience do differently after we ship that they don't do today?"
  • Hypothesis — must include a causal "because" or "if-then." Reject "we think it'll be good." Push back: "What's the bet? If we change X, then Y will happen because Z."
  • Success signal — must name a measurable thing or an observable behavior. Reject "users will love it." Push back: "What metric, behavior, or signal would prove this worked? How would you know in two weeks?"

Read the full file on GitHub · 183 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. 5d ago First seen · 183 lines · 119 tokens per session scan A 0f8dedb8a176

Subscribe to this mod's changes

ux-frame is a command published in the GitHub repository Laith0003/ux-skill (65 stars, last pushed 1mo ago), licensed MIT. It adds 119 tokens to every session and 2,070 once invoked, about $0.0006 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.