<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Npm Downloads on SoloSoft</title><link>https://www.solosoft.dev/tags/npm-downloads/</link><description>Recent content in Npm Downloads on SoloSoft</description><generator>Hugo</generator><language>en-us</language><lastBuildDate>Sat, 17 Oct 2026 00:00:00 +0000</lastBuildDate><atom:link href="https://www.solosoft.dev/tags/npm-downloads/index.xml" rel="self" type="application/rss+xml"/><item><title>Context Mode Has 30,231 Stars and a 98% Claim I Reproduced Two Different Ways: An npm Package Frozen Since June 29, a Badge That Counts Downloads as Users, and the $49/Month Gateway Behind It</title><link>https://www.solosoft.dev/post/context-mode-frozen-npm-98-percent-audit/</link><pubDate>Sat, 17 Oct 2026 00:00:00 +0000</pubDate><guid>https://www.solosoft.dev/post/context-mode-frozen-npm-98-percent-audit/</guid><description>&lt;p&gt;&lt;strong&gt;Context Mode&lt;/strong&gt; is the MCP plugin that promises to keep raw tool output out of your context window: 315 KB of tool output becomes 5.4 KB, a &lt;strong&gt;98% reduction&lt;/strong&gt;. It has 30,231 stars, it numbers its releases by the hundred, and its README states its philosophy in one blunt paragraph: &lt;em&gt;&amp;ldquo;Nothing leaves your machine. No telemetry, no cloud sync, no usage tracking, no account required&amp;hellip; Context optimization should happen at the source, not in a dashboard behind a per-seat subscription.&amp;rdquo;&lt;/em&gt;&lt;/p&gt;
&lt;p&gt;That is the README the 30,231 people starred. Here is the rest of the picture, all measured today rather than quoted:&lt;/p&gt;</description></item><item><title>REA Added 255,126 Stars in Eight Days: Re-Measuring GitHub's Fastest Star Curve, Where Forks Grew 43x Against Stars' 18x and 76% of the Git History Is 16 Days Old</title><link>https://www.solosoft.dev/post/rea-star-curve-eight-days-audit/</link><pubDate>Fri, 16 Oct 2026 00:00:00 +0000</pubDate><guid>https://www.solosoft.dev/post/rea-star-curve-eight-days-audit/</guid><description>&lt;p&gt;Eight days ago this site published a measured audit of REA — the MCP server that lets a coding agent reverse-engineer anything from an Electron app down to a native binary. The audit put the repository at &lt;strong&gt;15,095 stars, 44 watchers, 1,569 forks&lt;/strong&gt;, and priced a real analysis run at 209,619 tokens for eight files.&lt;/p&gt;
&lt;p&gt;On 2026-10-16, at 00:51 UTC, the same API endpoint returned &lt;strong&gt;270,221 stars, 915 watchers, 67,778 forks&lt;/strong&gt;.&lt;/p&gt;
&lt;p&gt;That is &lt;strong&gt;+255,126 stars, +871 watchers and +66,209 forks in eight days&lt;/strong&gt;. Nothing else on GitHub that I have measured moves like this, so this article does the only thing worth doing with a number like that: it measures the curve against a baseline, and separates the parts that are genuinely anomalous from the parts that are just what an agent-era repository looks like in 2026.&lt;/p&gt;</description></item></channel></rss>