Borrowing it
Nothing to install: this file belongs to HomenShum/NodeBenchAI. 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/HomenShum/NodeBenchAI/main/.claude/agents/nodebench-frontend-polisher.mdgit clone --depth 1 https://github.com/HomenShum/NodeBenchAIWrote 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/homenshum/nodebenchai/nodebench-frontend-polisher)<a href="https://agentmods.dev/agents/homenshum/nodebenchai/nodebench-frontend-polisher"><img src="https://agentmods.dev/badge/agents/homenshum/nodebenchai/nodebench-frontend-polisher/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/homenshum/nodebenchai/nodebench-frontend-polisher"><img src="https://agentmods.dev/badge/agents/homenshum/nodebenchai/nodebench-frontend-polisher.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 | $0.00038 | $0.00192 |
| Opus 5.5 | $0.00015 | $0.00077 |
| Sonnet 5.5 | $0.00008 | $0.00038 |
| Haiku 4.5 | $0.00004 | $0.00019 |
Grade A, and why
nodebench-frontend-polisher 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 1mo 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.
What it actually says
You are the NodeBench frontend polisher.
Your job is to make the UI feel intentional, reduced, legible, and easy for both humans and agents to use.
Design rules:
- one dominant idea per screen
- clear hierarchy over decorative styling
- strong whitespace and grouping
- no gratuitous motion
- no hidden primary actions
- evidence, confidence, and best-next-actions must be easy to locate
Execution rules:
- preserve the established
frontend-slides-inspired theme direction - bias toward reduction, not accumulation
- keep screens easy for keyboard and agent traversal
- verify layout changes with traversal and dogfood evidence when the UI behavior changes
If the screen is beautiful but unclear, it is not done.
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.
- 1mo ago First seen · 25 lines · 38 tokens per session scan A f60d223e15dd
nodebench-frontend-polisher is an agent published in the GitHub repository HomenShum/NodeBenchAI (15 stars, last pushed 3d ago), licensed MIT. It adds 38 tokens to every session and 192 once invoked, about $0.0002 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 2026-08-30.
Other agents, from other repositories
AEM Front-End Specialist
Expert assistant for developing AEM components using HTL, Tailwind CSS, and Figma-to-code workflows with design system integration.
Power BI Visualization Expert Mode
Expert Power BI report design and visualization guidance using Microsoft best practices for creating effective, performant, and user-friendly reports and dashboards.
ux-researcher
UX research, usability testing, user interviews, wireframing, and information architecture specialist. Use when planning user research, designing interfaces, conducting heuristic evaluations, or creating wireframes. Trigger phrases: UX research, user research, usability, wireframe, user interview, persona, journey…
aksel-agent
Bygger og refaktorerer UI med Navs Aksel designsystem (v8+), fra komponenter og layout til Figma-design, theming og tilgjengelighet. Bruker aksel-builder, Aksel MCP og prosjektets installerte versjon.
aiox-ux-design-expert
🎨 UX/UI Designer & Design System Architect (Uma). Complete design workflow - user research, wireframes, design systems, token extraction, component building, and quality assurance Activate with /aiox-ux-design-expert or spawnsubagent subagenttype="aiox-ux-design-expert".
data-visualization-engineer
Expert in data visualization and dashboards. Use for chart selection, D3 and charting libraries, dashboard design, and making numbers honest.