<?xml version="1.0" encoding="UTF-8"?>


<feed xmlns="http://www.w3.org/2005/Atom">
    <id>https://www.julianwyngaard.com/tags/jesse-vincent/feed.xml</id>
    <title>Loosely Coupled Thoughts &#x2014; tagged jesse-vincent</title>
    <subtitle>A blog about software engineering, AI, and development.</subtitle>
    <link rel="self" type="application/atom+xml" href="https://www.julianwyngaard.com/tags/jesse-vincent/feed.xml"/>
    <link rel="alternate" type="text/html" href="https://www.julianwyngaard.com/tags/jesse-vincent"/>
    <updated>2026-06-18T20:34:51.383726+12:00</updated>
    <author>
        <name>Julian Wyngaard</name>
    </author>
    <entry>
        <id>urn:uuid:019ed9de-4f74-7c95-9b43-4dd3d2d9bbed</id>
        <title>Superpowers 6</title>
        <link rel="alternate" type="text/html" href="https://www.julianwyngaard.com/2026/06/18/superpowers-6"/>
        <published>2026-06-18T20:34:51.383726+12:00</published>
        <updated>2026-06-18T20:34:51.383726+12:00</updated>
        <category term="ai" label="ai"/>
        <category term="superpowers" label="superpowers"/>
        <category term="agent-skills" label="agent-skills"/>
        <category term="claude-code" label="claude-code"/>
        <category term="jesse-vincent" label="jesse-vincent"/>
        <category term="agentic-workflows" label="agentic-workflows"/>
        <category term="engineering-with-ai" label="engineering-with-ai"/>
        <content type="html">&lt;p&gt;&lt;a href=&quot;https://blog.fsck.com/2026/06/15/Superpowers-6/&quot;&gt;Superpowers 6&lt;/a&gt;&lt;/p&gt;&lt;p&gt;Jesse Vincent &lt;a href=&quot;https://blog.fsck.com/2026/06/15/Superpowers-6/&quot;&gt;just released&lt;/a&gt; version 6 of his &lt;a href=&quot;https://github.com/obra/superpowers&quot;&gt;Superpowers plugin&lt;/a&gt; for coding agents, and has made it a &lt;strong&gt;lot&lt;/strong&gt; faster and a token hungry.&lt;/p&gt;
&lt;p&gt;One thing that can be frustrating is planning and building with the plugin skills can be slow and use large amounts of tokens. It&apos;s no surprise though considering what it does.&lt;/p&gt;
&lt;blockquote&gt;
&lt;p&gt;A bunch of the reasons that Superpowers builds have taken longer and cost more are the same reasons that it delivers good outcomes for so many users. It does a ton of up-front planning work to make sure your implementations can be hands-off, forces strict red-green TDD while implementing, and then the orchestrator inside Superpowers reviews every single change on two axes:&lt;/p&gt;
&lt;ol&gt;
&lt;li&gt;did the agent implement exactly what was asked, no more and no less.&lt;/li&gt;
&lt;li&gt;is the quality of the work up to snuff.&lt;/li&gt;
&lt;/ol&gt;
&lt;p&gt;Just by the nature of what it&apos;s doing, it&apos;s going to be slower than yoloing an untested implementation and calling it a day.&lt;/p&gt;
&lt;/blockquote&gt;
&lt;p&gt;However, it seems he also managed to take advantage of the few short days that Fable 5 was available and used it deeply analyse thousands of Subagent Driven Development sessions and effectively have it create an autoresearch harness that ran 25 experiments to make it more efficient.&lt;/p&gt;
&lt;pre&gt;&lt;code&gt;/goal once this is done, run an autoresearch loop to improve cost-efficiency of the superpowers build loop. test with opus as the coordinator. make an hypothesis log. run experiments. run at least 25 experiments.
&lt;/code&gt;&lt;/pre&gt;
&lt;p&gt;Resulting in a whopping 50% speed up and 60% reduction in token usage.&lt;/p&gt;
&lt;blockquote&gt;
&lt;p&gt;The long and the short of it it is that across about 36 hours of work and what would have been $650 of unsubsidized token spend, our Anthropic eval benchmarks were looking like we&apos;d reduced wall-clock runtime for Superpowers builds by 50% and token spend by 60%.&lt;/p&gt;
&lt;/blockquote&gt;
&lt;p&gt;I use this plugin a lot and has served me well. Speed has never been a major problem as it runs in the background and can do other things. But the context switching while waiting can be tiring and this will probably take the edge off of that a bit. And probably means less watching that 5 hourly rate limit when kicking of large builds. And with stronger and more costly models becoming available the token usage reduction is welcome.&lt;/p&gt;</content>
    </entry>
</feed>
