<?xml version="1.0" encoding="utf-8" standalone="yes"?>
<rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom" xmlns:content="http://purl.org/rss/1.0/modules/content/">
  <channel>
    <title>rollbrains</title>
    <link>https://rollbrains.github.io/</link>
    <description>Recent content on rollbrains</description>
    <generator>Hugo</generator>
    <language>en</language>
    <lastBuildDate>Thu, 21 May 2026 00:00:00 +0000</lastBuildDate>
    <atom:link href="https://rollbrains.github.io/index.xml" rel="self" type="application/rss+xml" />
    <item>
      <title>About</title>
      <link>https://rollbrains.github.io/about/</link>
      <pubDate>Thu, 21 May 2026 00:00:00 +0000</pubDate>
      <guid>https://rollbrains.github.io/about/</guid>
      <description>About Steve and the rollbrains blog — Tested, practical writeups on AI tools for traders and builders.</description>
    </item>
    <item>
      <title>AI Coding Tools Are All Going Metered in 2026 — What Actually Burns Your Quota</title>
      <link>https://rollbrains.github.io/coding/ai-coding-usage-billing-decoded/</link>
      <pubDate>Thu, 21 May 2026 00:00:00 +0000</pubDate>
      <guid>https://rollbrains.github.io/coding/ai-coding-usage-billing-decoded/</guid>
      <description>Every major AI coding tool moved to metered billing in 2026 — Cursor in June 2025, Codex in April, Copilot on June 1. Here&amp;#39;s what actually consumes your usage, why a low-usage dashboard can still block you, and how to pick a plan without a surprise bill.</description>
    </item>
    <item>
      <title>WebMCP and the Citation Paradox — What Agent-Ready Websites Actually Mean for GEO</title>
      <link>https://rollbrains.github.io/mcp/webmcp-citation-paradox/</link>
      <pubDate>Thu, 21 May 2026 00:00:00 +0000</pubDate>
      <guid>https://rollbrains.github.io/mcp/webmcp-citation-paradox/</guid>
      <description>WebMCP lets a website expose tools that AI agents call directly, and Chrome 149&amp;#39;s origin trial (Google I/O 2026) makes it testable on real traffic. But the popular claim that WebMCP forces agents to cite your URL is wrong. Here&amp;#39;s what the W3C draft actually says, and what it really changes for citations and referral traffic.</description>
    </item>
    <item>
      <title>Why Claude Code Says You&#39;re Out of Usage — and When It Actually Resets</title>
      <link>https://rollbrains.github.io/coding/claude-code-usage-limits/</link>
      <pubDate>Thu, 21 May 2026 00:00:00 +0000</pubDate>
      <guid>https://rollbrains.github.io/coding/claude-code-usage-limits/</guid>
      <description>Claude Code stops you with a usage-limit message, but there isn&amp;#39;t one limit — there are three: a 5-hour session window, a 7-day weekly cap, and optional usage credits. Here&amp;#39;s how each works, which one you&amp;#39;re hitting, and when it resets, sourced from Anthropic&amp;#39;s official docs.</description>
    </item>
    <item>
      <title>TradingView Remix Complete Guide (2026)</title>
      <link>https://rollbrains.github.io/tradingview/remix/complete-guide/</link>
      <pubDate>Wed, 20 May 2026 00:00:00 +0000</pubDate>
      <guid>https://rollbrains.github.io/tradingview/remix/complete-guide/</guid>
      <description>The complete TradingView Remix guide for 2026 — installation, settings walkthrough, plan-by-plan capabilities, and the prompts that actually work. Updated for the new weekly usage model.</description>
    </item>
    <item>
      <title>Master Prompt vs Split Questions on TradingView Remix</title>
      <link>https://rollbrains.github.io/tradingview/remix/prompt-strategy/</link>
      <pubDate>Tue, 19 May 2026 00:00:00 +0000</pubDate>
      <guid>https://rollbrains.github.io/tradingview/remix/prompt-strategy/</guid>
      <description>I tested whether splitting Remix questions wastes usage versus a single master prompt. Four split queries cost 10 tools; the master prompt cost 19 tools. Both burned 1% on Premium. The 5× savings claim circulating online is exaggerated.</description>
    </item>
    <item>
      <title>TradingView Remix Weekly Limits, Tested by Plan</title>
      <link>https://rollbrains.github.io/tradingview/remix/weekly-limits-explained/</link>
      <pubDate>Tue, 19 May 2026 00:00:00 +0000</pubDate>
      <guid>https://rollbrains.github.io/tradingview/remix/weekly-limits-explained/</guid>
      <description>I tested 5 different request types on TradingView Remix with Premium (5× weekly limit). Result: 3% usage. Here&amp;#39;s the full breakdown for every plan.</description>
    </item>
  </channel>
</rss>
