Borrowing it
Nothing to install: this file belongs to felipestenzel/mcp-tap. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/felipestenzel/mcp-tap/main/.claude/agents/ux-simplifier.mdgit clone --depth 1 https://github.com/felipestenzel/mcp-tapWrote 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.
[](https://agentmods.dev/agents/felipestenzel/mcp-tap/ux-simplifier)<a href="https://agentmods.dev/agents/felipestenzel/mcp-tap/ux-simplifier"><img src="https://agentmods.dev/badge/agents/felipestenzel/mcp-tap/ux-simplifier/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<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="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00318 | $0.01983 |
| Opus 5.5 | $0.00127 | $0.00793 |
| Sonnet 5.5 | $0.00064 | $0.00397 |
| Haiku 4.5 | $0.00032 | $0.00198 |
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 2mo 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.
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
-
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.
-
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.
-
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?"
-
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.
-
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)
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.
- 2mo ago First seen · 132 lines · 318 tokens per session scan A a148860387cb
ux-simplifier is an agent published in the GitHub repository felipestenzel/mcp-tap (0 stars, last pushed 8mo ago), licensed MIT. It adds 318 tokens to every session and 1,983 once invoked, about $0.0013 per session on Opus 5.5. 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.
ux-simplifier compared with agents from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| ux-simplifierfelipestenzel/mcp-tap | Agent | 0 | 8mo ago | MIT | A | 318 | Claude Code |
| ux-flow-auditorCharlesWiltgen/Axiom | Agent | 1.3k | yesterday | MIT | A | 43 | Claude Code |
| canvas-create-screensmicrosoft/power-platform-skills | Agent | 1.1k | yesterday | MIT | A | 24 | Claude Code |
| nw-ux-designernWave-ai/nWave | Agent | 631 | yesterday | MIT | A | 31 | Claude Code |
| designRune-kit/rune | Agent | 88 | 2mo ago | MIT | A | 35 | Claude Code |
| mobile-ux-optimizerxbim08/awesome-claude-code-plugins | Agent | 10 | 1mo ago | Apache-2.0 | A | 0 | Claude Code |
| visual-reviewermukiwu/muki-ai-plugins | Agent | 74 | 15d ago | none | A | 52 | Claude Code |