<?xml version="1.0" encoding="UTF-8"?><rss xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:content="http://purl.org/rss/1.0/modules/content/" xmlns:atom="http://www.w3.org/2005/Atom" version="2.0" xmlns:cc="http://cyber.law.harvard.edu/rss/creativeCommonsRssModule.html">
    <channel>
        <title><![CDATA[Stories by Aman Singh on Medium]]></title>
        <description><![CDATA[Stories by Aman Singh on Medium]]></description>
        <link>https://medium.com/@monkscript?source=rss-277523a8e3db------2</link>
        <image>
            <url>https://cdn-images-1.medium.com/fit/c/150/150/1*St3pc5sClFklwrzZ8jgK0w.jpeg</url>
            <title>Stories by Aman Singh on Medium</title>
            <link>https://medium.com/@monkscript?source=rss-277523a8e3db------2</link>
        </image>
        <generator>Medium</generator>
        <lastBuildDate>Sat, 21 Nov 2026 03:38:30 GMT</lastBuildDate>
        <atom:link href="https://medium.com/@monkscript/feed" rel="self" type="application/rss+xml"/>
        <webMaster><![CDATA[yourfriends@medium.com]]></webMaster>
        <atom:link href="http://medium.superfeedr.com/" rel="hub"/>
        <item>
            <title><![CDATA[MAI Code 2 vs Claude Opus 5.5 in Copilot: Same 6 Tasks, a Sixth of the Bill]]></title>
            <description><![CDATA[<div class="medium-feed-item"><p class="medium-feed-image"><a href="https://medium.com/@monkscript/mai-code-2-vs-claude-opus-5-5-in-copilot-same-6-tasks-a-sixth-of-the-bill-398d166fb593?source=rss-277523a8e3db------2"><img src="https://cdn-images-1.medium.com/max/1672/1*WHGUKTXbZiBXCQeukBzazw.png" width="1672"></a></p><p class="medium-feed-snippet">It passed 5 of my 6 tasks against Opus&#x2019;s 6. The one it failed is the job I&#x2019;d still pay Opus for.</p><p class="medium-feed-link"><a href="https://medium.com/@monkscript/mai-code-2-vs-claude-opus-5-5-in-copilot-same-6-tasks-a-sixth-of-the-bill-398d166fb593?source=rss-277523a8e3db------2">Continue reading on Medium »</a></p></div>]]></description>
            <link>https://medium.com/@monkscript/mai-code-2-vs-claude-opus-5-5-in-copilot-same-6-tasks-a-sixth-of-the-bill-398d166fb593?source=rss-277523a8e3db------2</link>
            <guid isPermaLink="false">https://medium.com/p/398d166fb593</guid>
            <category><![CDATA[ai]]></category>
            <category><![CDATA[software-development]]></category>
            <category><![CDATA[developer-tools]]></category>
            <category><![CDATA[programming]]></category>
            <category><![CDATA[github-copilot]]></category>
            <dc:creator><![CDATA[Aman Singh]]></dc:creator>
            <pubDate>Wed, 18 Nov 2026 17:21:52 GMT</pubDate>
            <atom:updated>2026-11-18T17:21:52.575Z</atom:updated>
        </item>
        <item>
            <title><![CDATA[Your AI Coding Chat History Is a Credential Store. I Scanned Mine After the Cursor Breach]]></title>
            <description><![CDATA[<div class="medium-feed-item"><p class="medium-feed-image"><a href="https://medium.com/@monkscript/your-ai-coding-chat-history-is-a-credential-store-i-scanned-mine-after-the-cursor-breach-07db69947880?source=rss-277523a8e3db------2"><img src="https://cdn-images-1.medium.com/max/1672/1*PHqWhAlRe-zhPmktI0wWaA.png" width="1672"></a></p><p class="medium-feed-snippet">Cursor&#x2019;s breach spread through secrets left in old agent traces. My Claude Code and Codex history had two live ones.</p><p class="medium-feed-link"><a href="https://medium.com/@monkscript/your-ai-coding-chat-history-is-a-credential-store-i-scanned-mine-after-the-cursor-breach-07db69947880?source=rss-277523a8e3db------2">Continue reading on Medium »</a></p></div>]]></description>
            <link>https://medium.com/@monkscript/your-ai-coding-chat-history-is-a-credential-store-i-scanned-mine-after-the-cursor-breach-07db69947880?source=rss-277523a8e3db------2</link>
            <guid isPermaLink="false">https://medium.com/p/07db69947880</guid>
            <category><![CDATA[cursor]]></category>
            <category><![CDATA[programming]]></category>
            <category><![CDATA[ai]]></category>
            <category><![CDATA[ai-agent]]></category>
            <category><![CDATA[claude-code]]></category>
            <dc:creator><![CDATA[Aman Singh]]></dc:creator>
            <pubDate>Mon, 16 Nov 2026 15:13:35 GMT</pubDate>
            <atom:updated>2026-11-16T15:13:35.030Z</atom:updated>
        </item>
        <item>
            <title><![CDATA[Same Local Model, Three Harnesses: Qwen in Aider, OpenCode and Claude Code on My 32GB Mac]]></title>
            <description><![CDATA[<div class="medium-feed-item"><p class="medium-feed-image"><a href="https://medium.com/@monkscript/same-local-model-three-harnesses-qwen-in-aider-opencode-and-claude-code-on-my-32gb-mac-2b44290ba15d?source=rss-277523a8e3db------2"><img src="https://cdn-images-1.medium.com/max/1672/1*XNVygVsIO9czI3T_2D5Vzg.png" width="1672"></a></p><p class="medium-feed-snippet">Qwen3.8 never changed between runs. The harness did, and two settings turned four failed tasks into passes.</p><p class="medium-feed-link"><a href="https://medium.com/@monkscript/same-local-model-three-harnesses-qwen-in-aider-opencode-and-claude-code-on-my-32gb-mac-2b44290ba15d?source=rss-277523a8e3db------2">Continue reading on Medium »</a></p></div>]]></description>
            <link>https://medium.com/@monkscript/same-local-model-three-harnesses-qwen-in-aider-opencode-and-claude-code-on-my-32gb-mac-2b44290ba15d?source=rss-277523a8e3db------2</link>
            <guid isPermaLink="false">https://medium.com/p/2b44290ba15d</guid>
            <category><![CDATA[ollama]]></category>
            <category><![CDATA[programming]]></category>
            <category><![CDATA[llm]]></category>
            <category><![CDATA[claude-code]]></category>
            <category><![CDATA[ai-agent]]></category>
            <dc:creator><![CDATA[Aman Singh]]></dc:creator>
            <pubDate>Sun, 15 Nov 2026 05:34:32 GMT</pubDate>
            <atom:updated>2026-11-15T05:34:32.024Z</atom:updated>
        </item>
        <item>
            <title><![CDATA[Free AI Coding Agents in November 2026: I Ran One Feature Through 5 Free Tiers]]></title>
            <description><![CDATA[<div class="medium-feed-item"><p class="medium-feed-image"><a href="https://medium.com/@monkscript/free-ai-coding-agents-in-november-2026-i-ran-one-feature-through-5-free-tiers-9b5aa8224ba4?source=rss-277523a8e3db------2"><img src="https://cdn-images-1.medium.com/max/1672/1*dP62JDt5fXNJPyexosQoFQ.png" width="1672"></a></p><p class="medium-feed-snippet">Only one of them put its free agent limit in writing as a number. Here&#x2019;s how far one feature got on each.</p><p class="medium-feed-link"><a href="https://medium.com/@monkscript/free-ai-coding-agents-in-november-2026-i-ran-one-feature-through-5-free-tiers-9b5aa8224ba4?source=rss-277523a8e3db------2">Continue reading on Medium »</a></p></div>]]></description>
            <link>https://medium.com/@monkscript/free-ai-coding-agents-in-november-2026-i-ran-one-feature-through-5-free-tiers-9b5aa8224ba4?source=rss-277523a8e3db------2</link>
            <guid isPermaLink="false">https://medium.com/p/9b5aa8224ba4</guid>
            <category><![CDATA[software-development]]></category>
            <category><![CDATA[vibe-coding]]></category>
            <category><![CDATA[ai-agent]]></category>
            <category><![CDATA[artificial-intelligence]]></category>
            <category><![CDATA[programming]]></category>
            <dc:creator><![CDATA[Aman Singh]]></dc:creator>
            <pubDate>Wed, 11 Nov 2026 04:56:48 GMT</pubDate>
            <atom:updated>2026-11-11T04:56:48.911Z</atom:updated>
        </item>
        <item>
            <title><![CDATA[Claude Code Hooks for the 5 CLAUDE.md Rules It Kept Breaking]]></title>
            <description><![CDATA[<div class="medium-feed-item"><p class="medium-feed-image"><a href="https://medium.com/@monkscript/claude-code-hooks-for-the-5-claude-md-rules-it-kept-breaking-46033a182344?source=rss-277523a8e3db------2"><img src="https://cdn-images-1.medium.com/max/1672/1*KdP6F8CrWEqeuQ_CPOR_Lg.png" width="1672"></a></p><p class="medium-feed-snippet">A follow-up to my CLAUDE.md rewrite: a two-question test for every line, and the config that made five rules stick.</p><p class="medium-feed-link"><a href="https://medium.com/@monkscript/claude-code-hooks-for-the-5-claude-md-rules-it-kept-breaking-46033a182344?source=rss-277523a8e3db------2">Continue reading on Medium »</a></p></div>]]></description>
            <link>https://medium.com/@monkscript/claude-code-hooks-for-the-5-claude-md-rules-it-kept-breaking-46033a182344?source=rss-277523a8e3db------2</link>
            <guid isPermaLink="false">https://medium.com/p/46033a182344</guid>
            <category><![CDATA[developer-tools]]></category>
            <category><![CDATA[software-development]]></category>
            <category><![CDATA[claude-code]]></category>
            <category><![CDATA[programming]]></category>
            <category><![CDATA[artificial-intelligence]]></category>
            <dc:creator><![CDATA[Aman Singh]]></dc:creator>
            <pubDate>Mon, 09 Nov 2026 13:50:22 GMT</pubDate>
            <atom:updated>2026-11-09T13:50:22.801Z</atom:updated>
        </item>
        <item>
            <title><![CDATA[Local Coding Models That Actually Fit a 32GB Mac: The 5 I’d Keep]]></title>
            <description><![CDATA[<div class="medium-feed-item"><p class="medium-feed-image"><a href="https://medium.com/@monkscript/local-coding-models-that-actually-fit-a-32gb-mac-the-5-id-keep-def7899d6df8?source=rss-277523a8e3db------2"><img src="https://cdn-images-1.medium.com/max/1672/1*2cOPagzQnZaz9MDDtv1tdA.png" width="1672"></a></p><p class="medium-feed-snippet">Qwen3.8 just changed the list. Plus the famous coding model I&#x2019;d skip, and one command that puts any of them in Claude Code.</p><p class="medium-feed-link"><a href="https://medium.com/@monkscript/local-coding-models-that-actually-fit-a-32gb-mac-the-5-id-keep-def7899d6df8?source=rss-277523a8e3db------2">Continue reading on Medium »</a></p></div>]]></description>
            <link>https://medium.com/@monkscript/local-coding-models-that-actually-fit-a-32gb-mac-the-5-id-keep-def7899d6df8?source=rss-277523a8e3db------2</link>
            <guid isPermaLink="false">https://medium.com/p/def7899d6df8</guid>
            <category><![CDATA[mac]]></category>
            <category><![CDATA[llm]]></category>
            <category><![CDATA[programming]]></category>
            <category><![CDATA[ollama]]></category>
            <category><![CDATA[claude-code]]></category>
            <dc:creator><![CDATA[Aman Singh]]></dc:creator>
            <pubDate>Thu, 05 Nov 2026 04:12:23 GMT</pubDate>
            <atom:updated>2026-11-05T04:12:23.417Z</atom:updated>
        </item>
        <item>
            <title><![CDATA[AI Agents vs SaaS: Thin SaaS Dies First. Here’s the 3-Part Test I’d Use]]></title>
            <description><![CDATA[<div class="medium-feed-item"><p class="medium-feed-image"><a href="https://medium.com/@monkscript/ai-agents-vs-saas-thin-saas-dies-first-heres-the-3-part-test-i-d-use-084b8a1be02a?source=rss-277523a8e3db------2"><img src="https://cdn-images-1.medium.com/max/1672/1*Jl8_0hCK5YOspuDkkbUREg.png" width="1672"></a></p><p class="medium-feed-snippet">Gartner puts $234 billion of software spend in agents&#x2019; path. Before I build anything for 2027, I&#x2019;d check context, outcome and opinion.</p><p class="medium-feed-link"><a href="https://medium.com/@monkscript/ai-agents-vs-saas-thin-saas-dies-first-heres-the-3-part-test-i-d-use-084b8a1be02a?source=rss-277523a8e3db------2">Continue reading on Medium »</a></p></div>]]></description>
            <link>https://medium.com/@monkscript/ai-agents-vs-saas-thin-saas-dies-first-heres-the-3-part-test-i-d-use-084b8a1be02a?source=rss-277523a8e3db------2</link>
            <guid isPermaLink="false">https://medium.com/p/084b8a1be02a</guid>
            <category><![CDATA[saas]]></category>
            <category><![CDATA[artificial-intelligence]]></category>
            <category><![CDATA[agentic-ai]]></category>
            <category><![CDATA[ai-agent]]></category>
            <category><![CDATA[startup]]></category>
            <dc:creator><![CDATA[Aman Singh]]></dc:creator>
            <pubDate>Wed, 04 Nov 2026 11:45:38 GMT</pubDate>
            <atom:updated>2026-11-04T11:45:38.352Z</atom:updated>
        </item>
        <item>
            <title><![CDATA[Reviewing Every Line of AI Code Is the Wrong Job. Here’s What I’d Check Instead]]></title>
            <description><![CDATA[<div class="medium-feed-item"><p class="medium-feed-image"><a href="https://medium.com/activated-thinker/reviewing-every-line-of-ai-code-is-the-wrong-job-heres-what-i-d-check-instead-ea58a13ec338?source=rss-277523a8e3db------2"><img src="https://cdn-images-1.medium.com/max/1672/1*LRaYqLGL0T_0MyU9eJHUTQ.png" width="1672"></a></p><p class="medium-feed-snippet">Agent code looks equally sure of every line. Here are the six checks I&#x2019;d run on every AI pull request, in order.</p><p class="medium-feed-link"><a href="https://medium.com/activated-thinker/reviewing-every-line-of-ai-code-is-the-wrong-job-heres-what-i-d-check-instead-ea58a13ec338?source=rss-277523a8e3db------2">Continue reading on Activated Thinker »</a></p></div>]]></description>
            <link>https://medium.com/activated-thinker/reviewing-every-line-of-ai-code-is-the-wrong-job-heres-what-i-d-check-instead-ea58a13ec338?source=rss-277523a8e3db------2</link>
            <guid isPermaLink="false">https://medium.com/p/ea58a13ec338</guid>
            <category><![CDATA[software-development]]></category>
            <category><![CDATA[code-review]]></category>
            <category><![CDATA[claude-code]]></category>
            <category><![CDATA[ai]]></category>
            <category><![CDATA[programming]]></category>
            <dc:creator><![CDATA[Aman Singh]]></dc:creator>
            <pubDate>Tue, 03 Nov 2026 13:24:03 GMT</pubDate>
            <atom:updated>2026-11-03T13:24:03.128Z</atom:updated>
        </item>
        <item>
            <title><![CDATA[AI Coding Isn’t Overhyped. The Way Most Teams Use It Is.]]></title>
            <description><![CDATA[<div class="medium-feed-item"><p class="medium-feed-image"><a href="https://medium.com/@monkscript/ai-coding-isnt-overhyped-the-way-most-teams-use-it-is-1b6e288f7787?source=rss-277523a8e3db------2"><img src="https://cdn-images-1.medium.com/max/1672/1*ihPCquNIBpv4N1m6d8T7pw.png" width="1672"></a></p><p class="medium-feed-snippet">Technical workers report 3x the speed and at most 2x the value. The gap isn&#x2019;t the tools, and here are the three habits I&#x2019;d change.</p><p class="medium-feed-link"><a href="https://medium.com/@monkscript/ai-coding-isnt-overhyped-the-way-most-teams-use-it-is-1b6e288f7787?source=rss-277523a8e3db------2">Continue reading on Medium »</a></p></div>]]></description>
            <link>https://medium.com/@monkscript/ai-coding-isnt-overhyped-the-way-most-teams-use-it-is-1b6e288f7787?source=rss-277523a8e3db------2</link>
            <guid isPermaLink="false">https://medium.com/p/1b6e288f7787</guid>
            <category><![CDATA[programming]]></category>
            <category><![CDATA[developer-tools]]></category>
            <category><![CDATA[agentic-ai]]></category>
            <category><![CDATA[ai]]></category>
            <category><![CDATA[software-development]]></category>
            <dc:creator><![CDATA[Aman Singh]]></dc:creator>
            <pubDate>Tue, 03 Nov 2026 06:31:44 GMT</pubDate>
            <atom:updated>2026-11-03T06:31:44.841Z</atom:updated>
        </item>
        <item>
            <title><![CDATA[Claude Opus 5.5 Prompting: How I’d Rewrite a CLAUDE.md From Anthropic’s Guide, Line by Line]]></title>
            <description><![CDATA[<div class="medium-feed-item"><p class="medium-feed-image"><a href="https://medium.com/@monkscript/claude-opus-5-5-prompting-how-id-rewrite-a-claude-md-from-anthropic-s-guide-line-by-line-99804b1ad685?source=rss-277523a8e3db------2"><img src="https://cdn-images-1.medium.com/max/1672/1*P6GMSqUYOG0ooOz4Mo-yxw.png" width="1672"></a></p><p class="medium-feed-snippet">Two kinds of lines to delete, one to rewrite, one to add, two jobs to move into settings, and the new rules I&#x2019;d leave out.</p><p class="medium-feed-link"><a href="https://medium.com/@monkscript/claude-opus-5-5-prompting-how-id-rewrite-a-claude-md-from-anthropic-s-guide-line-by-line-99804b1ad685?source=rss-277523a8e3db------2">Continue reading on Medium »</a></p></div>]]></description>
            <link>https://medium.com/@monkscript/claude-opus-5-5-prompting-how-id-rewrite-a-claude-md-from-anthropic-s-guide-line-by-line-99804b1ad685?source=rss-277523a8e3db------2</link>
            <guid isPermaLink="false">https://medium.com/p/99804b1ad685</guid>
            <category><![CDATA[claude]]></category>
            <category><![CDATA[programming]]></category>
            <category><![CDATA[artificial-intelligence]]></category>
            <category><![CDATA[prompt-engineering]]></category>
            <category><![CDATA[claude-code]]></category>
            <dc:creator><![CDATA[Aman Singh]]></dc:creator>
            <pubDate>Mon, 02 Nov 2026 10:57:39 GMT</pubDate>
            <atom:updated>2026-11-02T10:57:39.654Z</atom:updated>
        </item>
    </channel>
</rss>