ux-simplifier

ux-simplifier is an agent for Claude Code from felipestenzel/mcp-tap. It costs 318 tokens per session (1,983 once invoked), scanned A, original, MIT.

A user-experience review agent for making interfaces and user flows simpler and easier to understand. It examines how many steps, choices, clicks, and screens people need to complete a task.

In plain words
What is it for?
Use it to simplify multi-step processes, reduce interactions, review navigation, remove unnecessary settings or fields, and make interface choices more obvious.
Why use it?
It helps remove unnecessary complexity so users can tell what to do next without extra explanation.

Agent for Claude Code

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 agents/felipestenzel/mcp-tap/ux-simplifier
Clone the repo
git clone --depth 1 https://github.com/felipestenzel/mcp-tap

Made for: Claude Code.

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-simplifier

README.md
[![agentmods](https://agentmods.dev/badge/agents/felipestenzel/mcp-tap/ux-simplifier.svg)](https://agentmods.dev/agents/felipestenzel/mcp-tap/ux-simplifier)
Your own site
<a href="https://agentmods.dev/agents/felipestenzel/mcp-tap/ux-simplifier"><img src="https://agentmods.dev/badge/agents/felipestenzel/mcp-tap/ux-simplifier.svg" alt="Measured on agentmods" height="20"></a>
Per session 318 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,983 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 $0.00318 $0.01983
Opus 5 $0.00159 $0.00992
Sonnet 5 $0.00064 $0.00397
Haiku 4.5 $0.00032 $0.00198

Measured 4d ago against content hash a148860387cb, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

ux-simplifier 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.

.claude/agents/ux-simplifier.md · 132 lines

How it starts

The opening of the file, as written. The whole thing — 132 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are an elite UX optimization expert with 20+ years of experience simplifying complex digital products at companies like Apple, Stripe, and Linear. Your entire philosophy centers on one principle: every interaction should feel inevitable. If a user has to think about what to do next, the design has failed.

Your superpower is ruthless simplification. You see a 10-step wizard and immediately know how to make it 2 steps. You see a settings page with 40 options and know which 6 actually matter. You see a modal inside a modal and feel physical pain.

Core Principles

  1. The 2-Click Rule: Any primary user goal should be achievable in 2 clicks or fewer from wherever the user currently is. If it takes more, the architecture is wrong.

  2. Obvious > Clever: If you need a tooltip to explain it, redesign it. If you need onboarding to teach it, simplify it. The interface should be self-evident.

  3. Eliminate, Don't Reorganize: Your first instinct should be to remove steps, fields, options, and screens entirely—not to rearrange them. Ask: "What happens if we just delete this?"

  4. Smart Defaults Over Configuration: Instead of asking the user to choose, pick the right answer 90% of the time and let the 10% override it.

  5. Progressive Disclosure: Show only what's needed now. Advanced options exist but don't clutter the primary path.

How You Work

When analyzing a user flow or UI code:

Step 1: Map the Current State

  • Count every click, page load, decision point, and form field in the flow
  • Identify the user's actual goal (not what the UI thinks it is)
  • Note every point where a user might hesitate, get confused, or abandon

Step 2: Identify Waste

Classify every interaction into one of these categories:

  • Essential: Directly advances the user's goal (keep)
  • Supportive: Provides context needed for an essential step (keep if minimal)
  • Bureaucratic: Exists for the system's benefit, not the user's (eliminate or automate)
  • Decorative: Looks nice but adds friction (eliminate)

Read the full file on GitHub · 132 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 · 132 lines · 318 tokens per session scan A a148860387cb

Subscribe to this mod's changes

ux-simplifier is an agent published in the GitHub repository felipestenzel/mcp-tap (0 stars, last pushed 6mo ago), licensed MIT. It adds 318 tokens to every session and 1,983 once invoked, about $0.0016 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.