Claude wrote a test harness for a bug no one wanted to chase
A rabbitmq connector occasionally got stuck after rare network drops, too minor to spend days fixing. Claude built a test harness that reproduced it, and the actual fix wasn't too hard.
Done withClaudeSpotted· by HN user perlgeek· Oct 21, 2026
Result Automatically runnable scenarios, not a one-off check
“I asked Claude to write me a test harness that reproduced the issue, and it did. Having a bunch of automatically runnable scenarios made the actual fix not too hard.”
Spotted: found in the wild. Details are as reported by the source above and have not been independently verified.
What they did
A rabbitmq connector at the writer’s company occasionally got stuck without reconnecting during rare patterns of network interruptions. It was low priority, easy to work around by restarting the service, so they didn’t want to spend days of engineering on it. They asked Claude to write a test harness that reproduced the issue.
How it went
Claude’s test harness did reproduce the issue. Having a bunch of automatically runnable scenarios made the actual fix not too hard.
Try it yourself with Claude
Write a test harness that reliably reproduces [the intermittent bug], covering [the rare conditions that trigger it], so I can create automatically runnable scenarios before attempting a fix.
A starting prompt written by Agents in the Wild. Fill in the [brackets], and check what the agent does before it sends, pays for or deletes anything.
After $45 in GitHub Actions overage in one month, a solo founder put an idle homelab to work as CI runners, with Claude making it easy to set up. Daily spend dropped from $2-4 a day to under $0.25.
A first homemade synth has 36 hall-effect keys and buttons and 7 rotary encoders. The firmware started by hand, then gentle prodding at Claude got everything needed much faster. Rev 2 of the PCB is nearly done.
Working on a Quake project, Claude decided on its own to build a test suite: demo playbacks with snapshots compared pixel by pixel, plus recorded demos whose screenshots it checked for each element.
After building a minimal proof assistant, the writer asked Claude how they knew the prover was actually sound. Claude checked, found five different ways it could prove false theorems, and fixed them.
Four years after shelving a homemade RSS reader and selling off its $500 domain, the writer built it this year with Codex and Claude. They use it daily, along with 30 other strangers who found it public.
Chasing a childhood itch for the exact 1996 After Dark Flying Toasters screensaver, the writer turned to Claude. It did a lot of good reverse-engineering work, but kept inventing details that needed pushback.