#testing — Zakaria Bouazza

Testing a Claude Code plugin against no plugin at all

I built a small commit-message plugin and ran claude plugin eval on it. The no-plugin baseline showed what the plugin actually adds, and the one red case turned out to be the judge's mistake.

23 Oct 2026 · 6 min read ·82 views

Working with Claude Code

Java 8 to 21 on a batch full of traps I planted: the code-modernization plugin, end to end

I ran Anthropic's code-modernization plugin for Claude Code headless on a 2006-style billing batch I had booby-trapped. It caught every trap, found four problems I hadn't planted, and still only called its own proof "partly proven".

14 Oct 2026 · 8 min read ·570 views

Scala and the JVM · Part 15

Scala: Part 14: Testing Scala Results - Values, Errors and Exceptions

I unpack AnyFunSuite from a Java developer’s perspective, test returned Right and Left values, check thrown exceptions with intercept, and verify that independent expectations catch real mistakes.

29 Sep 2026 · 6 min read ·105 views

Building agents on the JVM with Embabel · Part 2

Stub the Model, Assert the Plan: Unit-Testing Embabel Agents

The non-deterministic part of an agent is the LLM. Box it out and the rest is ordinary, deterministic code you can test. Here's how I test Embabel agents on the JVM without spending a single token.

25 Jul 2026 · 5 min read ·178 views