ux-workshop

ux-workshop is a command for coding agents from Laith0003/ux-skill. It costs 113 tokens per session (2,496 once invoked), scanned A, original, MIT.

A guided design-thinking workshop for exploring a problem with stakeholders and ending with a concrete plan. Design thinking is a structured way to understand needs, generate options, and choose what to do next.

In plain words
What is it for?
Use it to facilitate project discovery, align product, design, engineering, and customer roles, or examine an opportunity when participants, a topic, and a time limit are available.
Why use it?
It gives a group a time-limited process for reaching decisions instead of ending with disconnected ideas or observations.

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-workshop
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-workshop

README.md
[![agentmods](https://agentmods.dev/badge/commands/laith0003/ux-skill/ux-workshop.svg)](https://agentmods.dev/commands/laith0003/ux-skill/ux-workshop)
Your own site
<a href="https://agentmods.dev/commands/laith0003/ux-skill/ux-workshop"><img src="https://agentmods.dev/badge/commands/laith0003/ux-skill/ux-workshop.svg" alt="Measured on agentmods" height="20"></a>
Per session 113 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,496 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 $0.00113 $0.02496
Opus 5 $0.00056 $0.01248
Sonnet 5 $0.00023 $0.00499
Haiku 4.5 $0.00011 $0.00250

Measured 4d ago against content hash 6c29b6f13ac3, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

ux-workshop 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 4d 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-workshop.md · 249 lines

How it starts

The opening of the file, as written. The whole thing — 249 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/ux-workshop

You are running the /ux-workshop command from the ux plugin. The job is to facilitate a discovery / design-thinking workshop end-to-end. Five sequential phases. Time-boxed. Concrete artifacts per phase. Decision at the end, not "interesting findings."

When to use

Triggers: "run a workshop", "facilitate a discovery", "let's do a design thinking session", "I have stakeholders for an hour, what do we do", "we need to align on this opportunity", "kick off the project". Use when there's a real question and real participants — not as a solo brainstorm (use /ux-design or /ux-frame for that).

Input

Required:

  • Topic: the question the workshop is converging on
  • Participants: roles (not names) — eg. "2 PMs, 1 designer, 1 eng lead, 1 customer rep"
  • Time budget: total minutes available

Ask once if missing: "Topic, participant roles, and total minutes?"

Process

1. Read the references

Read before starting:

  • references/process/design-thinking-apphaus.md — the canonical 5-phase structure
  • references/styles/anti-slop.md — for any visual artifacts produced

2. Compute the time-box

Default split (adapt to total budget):

  • Phase 1 — Exploration Exercise: 25%
  • Phase 2 — Heat Map: 15%
  • Phase 3 — Stakeholder Mapping: 15%
  • Phase 4 — Remember the Future: 20%
  • Phase 5 — Game Plan: 25%

State the schedule upfront so participants know the pace.

3. Run the phases sequentially

Phase 1 — Exploration Exercise

Goal: collect insights, identify barriers, find opportunities.

Facilitate:

  • Ask participants to silently brainstorm for 5 minutes: what's working, what's broken, who's stuck, who's underserved
  • Each person shares top 3 — one at a time, no debate
  • Cluster the raw output into themes
  • Tag each cluster: barrier / opportunity / insight / unknown

Artifact: clustered theme map with tags.

Phase 2 — Heat Map

Goal: prioritize opportunities by impact × feasibility × strategic fit.

Facilitate:

  • Pull the opportunities from Phase 1 onto a 2-axis grid: impact (y) × feasibility (x)
  • Each participant places dots on the 3 they care most about
  • Cluster dots reveal the heat
  • Strategic-fit overlay: kill anything that conflicts with stated company direction

Read the full file on GitHub · 249 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. 4d ago First seen · 249 lines · 113 tokens per session scan A 6c29b6f13ac3

Subscribe to this mod's changes

ux-workshop is a command published in the GitHub repository Laith0003/ux-skill (65 stars, last pushed 1mo ago), licensed MIT. It adds 113 tokens to every session and 2,496 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.