ux-designer-mindset

ux-designer-mindset is a skill for Claude Code from Fergius-Engineering/instincts. It costs 27 tokens per session (443 once invoked), scanned A, original, MIT.

A user-experience checklist for building or changing screens, controls, and flows that people interact with.

In plain words
What is it for?
Use it before and after UI work to describe expected interactions and check states such as no results, large data sets, first use, and rapid clicks.
Why use it?
A feature can work technically yet still feel broken when feedback, empty states, repeated actions, or other edge cases are missing.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the instincts plugin — 20 skills, 2 hooks 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 skills/fergius-engineering/instincts/ux-designer-mindset
Any agent
npx skills add Fergius-Engineering/instincts --skill ux-designer-mindset
Clone the repo
git clone --depth 1 https://github.com/Fergius-Engineering/instincts

Made for: Claude Code.

Or install instincts, the plugin that ships this one along with the rest of its 20 skills, 2 hooks.

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-designer-mindset

README.md
[![agentmods](https://agentmods.dev/badge/skills/fergius-engineering/instincts/ux-designer-mindset.svg)](https://agentmods.dev/skills/fergius-engineering/instincts/ux-designer-mindset)
Your own site
<a href="https://agentmods.dev/skills/fergius-engineering/instincts/ux-designer-mindset"><img src="https://agentmods.dev/badge/skills/fergius-engineering/instincts/ux-designer-mindset.svg" alt="Measured on agentmods" height="20"></a>
Per session 27 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 443 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 5.1 $0.00027 $0.00443
Opus 5 $0.00014 $0.00221
Sonnet 5 $0.00005 $0.00089
Haiku 4.5 $0.00003 $0.00044

Measured 6d ago against content hash af062c6228fc, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

ux-designer-mindset 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 6d 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.

skills/ux-designer-mindset/SKILL.md · 30 lines

What it actually says

The rule

A feature that compiles and returns the right value can still feel broken. Before you implement, walk the interaction the way the user lives it; after, check the states you didn't design for. A green build tells you the code runs — it tells you nothing about how the thing feels under a real hand.

Fires when

Building or changing any control, screen, or flow a user interacts with.

How to apply

Before coding, narrate the interaction: "user does X, sees Y, expects Z" — and flag every gap where Y or Z is missing. After coding, walk the edge states you didn't design for: empty, zero results, a hundred thousand results, rapid repeated clicks, first run versus returning, panel closed versus open. Every clickable control must give feedback (a hover state, a cursor change), and you verify that in the running app — in many UI frameworks a bad style name silently falls back to a default and the build stays green either way. Offer the small touches that show care, like a count on hover or a brief fade.

Worked example

A toolbar icon is wired to its action and compiles cleanly, but it's drawn with a borderless style — no hover highlight, no cursor change. It works when clicked, yet it reads as dead, and users stop trusting that it does anything. Switching to a real button style and checking the hover and cursor live in the running app fixes the feel. The green build had nothing to say about it, because nothing about feel shows up at compile time.

Red flags

Thought Reality
"It compiles and returns the right value" Correct and broken-feeling are not exclusive.
"The button's wired up" Wired up but dead-looking reads as broken.
"I'll just check it built" A build proves the code runs, not how it feels.
"Nobody clicks twice" Someone always clicks twice. Handle it.
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. 6d ago First seen · 30 lines · 27 tokens per session scan A af062c6228fc

Subscribe to this mod's changes

ux-designer-mindset is a skill published in the GitHub repository Fergius-Engineering/instincts (2 stars, last pushed 11d ago), licensed MIT. It adds 27 tokens to every session and 443 once invoked, about $0.0001 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.

Related

Other skills, from other repositories

go-testing

Trigger: Go tests, go test coverage, Bubbletea teatest, golden files. Apply focused Go testing patterns.

Gentleman-Programming/gentle-ai · 26 tokens

rulesync

Generates and syncs AI rule configuration files (.cursorrules, CLAUDE.md, copilot-instructions.md) across 20+ coding tools from a single source. Use when syncing AI rules, running rulesync commands, importing or generating rule files, or managing shared AI coding configurations.

dyoshikawa/rulesync · 64 tokens

autoprompt

Explicit-only useful-first orchestration. Invoke /autoprompt to turn a mission into one executable roadmap, build dependency-safe lanes, and verify the result with independent reviewers. Never infer invocation from ordinary requests. Never resume from leftover artifacts without an explicit resume instruction.

Spielewoy/autoprompt-skill · 56 tokens

establishing-project-context

Use when the user asks to establish shared project language, or project work exposes a conflicting, renamed, or deprecated domain term that needs active semantic modeling. Routine small tasks stay on the fast path.

GanyuanRan/Aegis · 45 tokens

gitnexus

将 GitNexus 作为受控可选代码智能能力接入,用于 brownfield MCP 查询、影响面分析、 detectchanges、多仓分析和更深代码图谱证据。输出必须回落到 /team- 主链和 artifacts。.

hashgraph-online/awesome-codex-plugins · 58 tokens

loop

Full execution protocol for MODE: LOOP — the compound-engineering loop: brainstorm → plan → build → review → improve, iterating under defense-in-depth stop conditions with generator/critic separation, durable resumable state, and mandatory compounding learning capture. Loaded on demand by the architect when the loop…

ZaxbyHub/opencode-swarm · 72 tokens