I Tested My Claude Code Plugin Across 1,260 Live Sessions. Four Sentences Nearly Matched It.

Description and use

<p>"All tests pass."</p> <p>If you use an AI coding agent, you've probably read that sentence several times today.</p> <p>It sounds like proof. But it's only a claim.</p> <p>So I built receipts, an open-source Claude Code plugin with one simple principle:</p> <p>No receipts, no "done."</p> <p>Then I tried to prove my own idea wrong.</p> <p>The results were surprising. And some of them weren't particularly flattering to my plugin.</p> <p>I'm publishing those too.</p> <p>The Problem: Confidence Isn't Evidence<br> An AI coding agent can confidently report "all tests pass" even when:</p> <p>It nev

Problem

<p>"All tests pass."</p> <p>If you use an AI coding agent, you've probably read that sentence several times today.</p> <p>It sounds like proof. But it's only a claim.</p> <p>So I built receipts, an open-source Claude Code plugin with one simple principle:</p> <p>No receipts, no "done."</p> <p>Then I tried to prove my own idea wrong.</p> <p>The results were surprising. And some of them weren't particularly flattering to my plugin.</p> <p>I'm publishing those too.</p> <p>The Problem: Confidence Isn't Evidence<br> An AI coding agent can confidently report "all tests pass" even when:</p> <p>It nev

Outcome

<p>"All tests pass."</p> <p>If you use an AI coding agent, you've probably read that sentence several times today.</p> <p>It sounds like proof. But it's only a claim.</p> <p>So I built receipts, an open-source Claude Code plugin with one simple principle:</p> <p>No receipts, no "done."</p> <p>Then I tried to prove my own idea wrong.</p> <p>The results were surprising. And some of them weren't particularly flattering to my plugin.</p> <p>I'm publishing those too.</p> <p>The Problem: Confidence Isn't Evidence<br> An AI coding agent can confidently report "all tests pass" even when:</p> <p>It nev

Evidence

I Tested My Claude Code Plugin Across 1,260 Live Sessions. Four Sentences Nearly Matched It.

Source