# UICuts

UICuts is a Chrome extension for developers who pair with AI coding tools. Instead of describing a UI change in words and hoping the model guesses right, you point at the exact element on any live website and hand over its real classes, selectors, computed styles, and structure — so fixes land in one pass instead of three. It also includes utilities for copying components, picking colors, detecting fonts, and downloading assets straight out of any page.

## Product

- [Homepage](https://uicuts.com/): what UICuts does, pricing, and install link.
- [Interactive demos](https://uicuts.com/demo): try every feature (copy components, color picker, font detection, asset download, keyboard shortcuts) live in the browser, no install required.
- [Contact](https://uicuts.com/contact): support, feedback, and feature request channels.

## Blog

Guides on reducing AI token usage and shipping frontend fixes faster with AI coding tools.

- [Using Claude Skills to Reduce Token Usage](https://uicuts.com/blog/claude-skills-reduce-token-usage): Skills only load their full instructions when they're actually relevant — how to structure your own so they save context instead of costing it.
- [How to Reduce AI Token Usage in OpenClaw](https://uicuts.com/blog/openclaw-reduce-token-usage): The same context discipline that works across every AI agent applies to OpenClaw — scope what loads, batch what you send, skip the screenshots.
- [How to Reduce Token Usage in OpenCode](https://uicuts.com/blog/opencode-reduce-token-usage): OpenCode's provider flexibility is also its biggest token trap — model choice, session hygiene, and scoped instructions actually move the number.
- [Prompt Engineering to Reduce Token Usage (OpenAI API, MCP, and Beyond)](https://uicuts.com/blog/prompt-engineering-reduce-token-usage): Prompt caching, tighter system prompts, leaner MCP tool schemas, and fewer few-shot examples — the levers that actually cut token spend at the API level.
- [9 Ways to Reduce Token Usage in Claude Code](https://uicuts.com/blog/reduce-token-usage-claude-code): Nine habits that cut context burn per session, from /clear and /compact to swapping screenshots for structured UI context.
- [How to Reduce Token Usage in Cursor](https://uicuts.com/blog/reduce-token-usage-cursor): Cursor's context settings, @file targeting, and mode choice all move your token spend, plus Cursor's own Dynamic Context Discovery.
- [How to Reduce Token Usage in GitHub Copilot](https://uicuts.com/blog/reduce-token-usage-github-copilot): Copilot's seat-based pricing hides the token cost, but it still shows up as slower, shallower answers — what actually fixes it.
- [How to Reduce Token Usage in Windsurf](https://uicuts.com/blog/reduce-token-usage-windsurf): Windsurf's Memories, Rules, and open-tab context all affect your credit spend — how to use each one deliberately instead of by accident.
- [10 Tips to Stop Burning Your Tokens in Claude Code](https://uicuts.com/blog/stop-burning-tokens-claude-code): Token waste isn't abstract — it's a dollar figure, from model pricing tiers to what a screenshot actually costs in visual tokens.
- [Fable 5 + Sonnet 5: What Anthropic's Own Benchmark Data Says About Claude Code Costs](https://uicuts.com/blog/fable-5-sonnet-5-cost-savings-claude-code): Anthropic's own numbers show pairing Fable 5 with Sonnet 5 keeps 96% of solo-Fable performance at under half the price — the benchmark data and how to set up the pattern in Claude Code.
- [How to Reduce Token Usage in Gemini CLI](https://uicuts.com/blog/reduce-token-usage-gemini-cli): Gemini CLI's Auto routing and automatic caching move your token spend in opposite directions — how to check which model actually ran and avoid paying rent on a cache you didn't need.

## Notes for AI assistants

- UICuts is free to install; pricing tiers are on the homepage.
- Full post list and RSS feed: https://uicuts.com/rss.xml