<?xml version="1.0" encoding="utf-8" standalone="yes"?>
<rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom">
  <channel>
    <title>coding agents on Abbreviatory.com</title>
    <link>https://abbreviatory.com/tags/coding-agents/</link>
    <description>Recent content in coding agents on Abbreviatory.com</description>
    <generator>Hugo -- gohugo.io</generator>
    <language>en-us</language>
    <lastBuildDate>Mon, 19 Oct 2026 00:00:00 +0000</lastBuildDate><atom:link href="https://abbreviatory.com/tags/coding-agents/index.xml" rel="self" type="application/rss+xml" />
    <item>
      <title>Abbreviatory 0.3 Gives Coding Agents an MCP Server and Opens a Browser Demo</title>
      <link>https://abbreviatory.com/abbreviatory-0.3-gives-coding-agents-an-mcp-server-and-opens-a-browser-demo/</link>
      <pubDate>Mon, 19 Oct 2026 00:00:00 +0000</pubDate>
      
      <guid>https://abbreviatory.com/abbreviatory-0.3-gives-coding-agents-an-mcp-server-and-opens-a-browser-demo/</guid>
      <description>Coding agents run tests all day. Every run prints thousands of lines, and the agent reads all of them, pays for all of them, and then often reads them again after a one-line change. Abbreviatory v0.3.0 lets the agent skip that. It&amp;rsquo;s now an MCP server, so an agent can ask it to run the tests and get back the short report instead: the failures with their messages, what changed since the last run, and one line when nothing did.</description>
    </item>
    
    <item>
      <title>How to Give a Coding Agent Short Test Reports Through the Abbreviatory MCP Server</title>
      <link>https://abbreviatory.com/how-to-give-a-coding-agent-short-test-reports-through-the-abbreviatory-mcp-server/</link>
      <pubDate>Mon, 19 Oct 2026 00:00:00 +0000</pubDate>
      
      <guid>https://abbreviatory.com/how-to-give-a-coding-agent-short-test-reports-through-the-abbreviatory-mcp-server/</guid>
      <description>A coding agent fixing a bug runs the tests again and again. Change a line, run go test ./..., read the output, change another line. Each run of our sample suite prints 4,882 lines of go test -json events, 808 kB, and almost all of it says a test passed. The agent reads every line, every time, and pays for every line in its context window. By the tenth run most of its context is old test output.</description>
    </item>
    
    <item>
      <title>How to Map an Unfamiliar Repository With find and Abbreviatory</title>
      <link>https://abbreviatory.com/how-to-map-an-unfamiliar-repository-with-find-and-abbreviatory/</link>
      <pubDate>Mon, 19 Oct 2026 00:00:00 +0000</pubDate>
      
      <guid>https://abbreviatory.com/how-to-map-an-unfamiliar-repository-with-find-and-abbreviatory/</guid>
      <description>The first thing anyone does in a new repository is look around. A person runs tree and gives up after a few screens. A coding agent runs find . -type f and gets every path, and on a large project that&amp;rsquo;s thousands of lines spent before it has read a single file. Most of them say the same thing: another test fixture, another Go file in the same package.
The listing in this example is find src -type f over Go&amp;rsquo;s own source tree, which is big enough to make the point: 10,703 paths in 1,097 directories, 454.</description>
    </item>
    
    <item>
      <title>What Context Reduction Is and Why Abbreviatory Does It Without a Language Model</title>
      <link>https://abbreviatory.com/what-context-reduction-is-and-why-abbreviatory-does-it-without-a-language-model/</link>
      <pubDate>Sun, 18 Oct 2026 00:00:00 +0000</pubDate>
      
      <guid>https://abbreviatory.com/what-context-reduction-is-and-why-abbreviatory-does-it-without-a-language-model/</guid>
      <description>Context is whatever a reader has in front of them when they decide what to do next. For a person, it&amp;rsquo;s the terminal. For a coding agent, it&amp;rsquo;s the text that goes into the model on its next turn. Either way it&amp;rsquo;s limited, and most of what tools print is filler.
Context reduction is cutting that down before it reaches the reader, without losing anything they need. A test run of 5,000 lines, of which 4,950 say &amp;ldquo;ok&amp;rdquo;, becomes the 50 that don&amp;rsquo;t, plus a count of the rest.</description>
    </item>
    
  </channel>
</rss>
