<?xml version="1.0" encoding="UTF-8"?><rss version="2.0"><channel><title>UICuts Blog</title><description>Guides on reducing AI token usage and shipping frontend fixes faster with AI coding tools.</description><link>https://uicuts.com/</link><item><title>Using Claude Skills to Reduce Token Usage</title><link>https://uicuts.com/blog/claude-skills-reduce-token-usage/</link><guid isPermaLink="true">https://uicuts.com/blog/claude-skills-reduce-token-usage/</guid><description>Skills only load their full instructions when they&apos;re actually relevant. Here&apos;s how to structure your own so they save context instead of costing it.</description><pubDate>Sat, 04 Jul 2026 00:00:00 GMT</pubDate></item><item><title>How to Reduce AI Token Usage in OpenClaw</title><link>https://uicuts.com/blog/openclaw-reduce-token-usage/</link><guid isPermaLink="true">https://uicuts.com/blog/openclaw-reduce-token-usage/</guid><description>The same context discipline that works across every AI agent applies to OpenClaw: scope what loads, batch what you send, and skip the screenshots.</description><pubDate>Sat, 04 Jul 2026 00:00:00 GMT</pubDate></item><item><title>How to Reduce Token Usage in OpenCode</title><link>https://uicuts.com/blog/opencode-reduce-token-usage/</link><guid isPermaLink="true">https://uicuts.com/blog/opencode-reduce-token-usage/</guid><description>OpenCode&apos;s provider flexibility is also its biggest token trap. Model choice, session hygiene, and scoped instructions actually move the number.</description><pubDate>Sat, 04 Jul 2026 00:00:00 GMT</pubDate></item><item><title>Prompt Engineering to Reduce Token Usage (OpenAI API, MCP, and Beyond)</title><link>https://uicuts.com/blog/prompt-engineering-reduce-token-usage/</link><guid isPermaLink="true">https://uicuts.com/blog/prompt-engineering-reduce-token-usage/</guid><description>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.</description><pubDate>Sat, 04 Jul 2026 00:00:00 GMT</pubDate></item><item><title>9 Ways to Reduce Token Usage in Claude Code</title><link>https://uicuts.com/blog/reduce-token-usage-claude-code/</link><guid isPermaLink="true">https://uicuts.com/blog/reduce-token-usage-claude-code/</guid><description>I burn less context per session since fixing these nine habits in Claude Code — from /clear and /compact to swapping screenshots for structured UI context.</description><pubDate>Sat, 04 Jul 2026 00:00:00 GMT</pubDate></item><item><title>How to Reduce Token Usage in Cursor</title><link>https://uicuts.com/blog/reduce-token-usage-cursor/</link><guid isPermaLink="true">https://uicuts.com/blog/reduce-token-usage-cursor/</guid><description>Cursor&apos;s context settings, @file targeting, and mode choice all move your token spend. Here&apos;s what actually works, plus Cursor&apos;s own Dynamic Context Discovery.</description><pubDate>Sat, 04 Jul 2026 00:00:00 GMT</pubDate></item><item><title>How to Reduce Token Usage in GitHub Copilot</title><link>https://uicuts.com/blog/reduce-token-usage-github-copilot/</link><guid isPermaLink="true">https://uicuts.com/blog/reduce-token-usage-github-copilot/</guid><description>Copilot&apos;s seat-based pricing hides the token cost, but it still shows up as slower, shallower answers. Here&apos;s what actually fixes it.</description><pubDate>Sat, 04 Jul 2026 00:00:00 GMT</pubDate></item><item><title>How to Reduce Token Usage in Windsurf</title><link>https://uicuts.com/blog/reduce-token-usage-windsurf/</link><guid isPermaLink="true">https://uicuts.com/blog/reduce-token-usage-windsurf/</guid><description>Windsurf&apos;s Memories, Rules, and open-tab context all affect your credit spend. Here&apos;s how to use each one deliberately instead of by accident.</description><pubDate>Sat, 04 Jul 2026 00:00:00 GMT</pubDate></item></channel></rss>