ux-init

ux-init is a command for coding agents from ssheleg/super-ux. It costs 35 tokens per session (567 once invoked), scanned A, original, MIT.

A command that sets up a project's full user-experience design chain: product direction, user research, task flows, screens, and usage scenarios.

In plain words
What is it for?
Use it when starting or examining a product to define personas, jobs-to-be-done, journeys, stories, flows, screen states, and scenarios.
Why use it?
It creates a connected UX foundation so later screens and flows are based on agreed users, goals, and product scope.

Command

Part of the super-ux plugin — 7 skills, 15 commands 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/ssheleg/super-ux/ux-init
Clone the repo
git clone --depth 1 https://github.com/ssheleg/super-ux

Or install super-ux, the plugin that ships this one along with the rest of its 7 skills, 15 commands.

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-init

README.md
[![agentmods](https://agentmods.dev/badge/commands/ssheleg/super-ux/ux-init.svg)](https://agentmods.dev/commands/ssheleg/super-ux/ux-init)
Your own site
<a href="https://agentmods.dev/commands/ssheleg/super-ux/ux-init"><img src="https://agentmods.dev/badge/commands/ssheleg/super-ux/ux-init.svg" alt="Measured on agentmods" height="20"></a>
Per session 35 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 567 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 $0.00035 $0.00567
Opus 5 $0.00017 $0.00283
Sonnet 5 $0.00007 $0.00113
Haiku 4.5 $0.00003 $0.00057

Measured 3d ago against content hash 975e8b8c4326, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

ux-init 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 3d 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.

plugins/super-ux/commands/ux-init.md · 42 lines

What it actually says

Initialize the UX chain, WHAT-IT-IS → WHY → HOW → WHAT-IT-DOES:

  1. Vision (offer, never assume). If docs/ux/vision.md is missing, ask once whether the product's direction is settled. Settled → say so and go to 1. Not settled, or the answer is "we keep arguing about scope" → invoke the vision skill first: the anti-vision is what later stops a feature that every persona would happily use and the product should not have. Never seed an empty vision.md — a blank vision reads as a decided one, and every later check would pass over it.

  2. Foundation. If docs/ux/foundation.md is missing or empty, invoke the ux-foundation skill in Init mode — interview for greenfield, reverse-engineering for an existing product. Get the layers approved. (Tiny project and the user explicitly wants to skip? Note it and go v1 mode — scenarios without Traces.)

  3. Flows. Invoke the ux-flows skill: Design (greenfield — task analysis → mermaid flows → screen states per story) or Reverse (existing code — reconstruct actual flows with evidence, tag inferred).

  4. Scenarios. Invoke the ux-scenarios skill in Init mode: cover every flow node and edge (happy path, error edges, alt branches) with use-case scenarios, Traces: filled with story + flow IDs.

  5. Finish with the traceability check (Validate) and a status summary, then run python3 docs/ux/lint.py and report its counts. If a vision.md exists, confirm its alignment rule reached the project's instruction file — the linter warns when it did not.

  6. If the product has user-facing text, say that docs/brand/ is the layer that governs it and offer /brand-init. The chain decides what the product does; it does not decide how it speaks.

If foundation.md, flows.md, and scenarios.md already exist with entries, do NOT reinitialize — say so and suggest /ux for the action menu instead. If only some layers exist, initialize the missing ones and leave the rest untouched.

Additional context from the user: $ARGUMENTS

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. 3d ago First seen · 42 lines · 35 tokens per session scan A 975e8b8c4326

Subscribe to this mod's changes

ux-init is a command published in the GitHub repository ssheleg/super-ux (3 stars, last pushed today), licensed MIT. It adds 35 tokens to every session and 567 once invoked, about $0.0002 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.