30 scrapers in 5 languages break weekly. Claude opens the fix PRs.
Which bike races are on TV today, and where? The data is messy and the sites break every week. Each day Claude reads the unmatched-race report and proposes fixes, so one person can keep it running.
Done withClaude CodeSpotted· by HN user dbrabyn· Oct 15, 2026
Result Legal TV listings for every race, every day
“So AI does the upkeep: scrapers are dumb fetchers, and Claude reads the daily "unmatched race" report and opens PRs proposing fixes.”
Spotted: found in the wild. Details are as reported by the source above and have not been independently verified.
What they did
Built Course du Jour with Claude Code to answer one daily question: which bike races are on TV today, and where can I watch them legally. The data comes from about 30 sources in 5 languages, with inconsistent naming and sites that break weekly. The scrapers are simple fetchers, and Claude reads the daily “unmatched race” report and opens pull requests proposing fixes.
How it went
The AI handles the upkeep, which is what makes a messy, ever-breaking data problem manageable for one person.
Try it yourself with Claude Code
Every morning, read today's scraper report in [file]. For each item that didn't match (a renamed event, a changed page layout, a new source format), find the cause in the scraper code, write the smallest fix with a test using the saved page, and open a pull request explaining what changed on the source site. Don't merge anything yourself.
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.
Markdown files should just open, so they asked Claude Code for a viewer. It opens instantly: faster, they say, than any other macOS app, and faster than Bitwarden's Chrome extension shows its fill menu.
Migrating a password reset flow, Claude Code and Opus produced code on par with a mid level developer. It needed close supervision throughout, and cost roughly 2 months of Pro subscription for about half a day's work.
A URL shortener side project ran on AWS. Claude Code wrote the GitHub Actions workflows for the move and fixed each failure as it came up. The writer reports zero downtime.
A 7-app monorepo needed an 8 GB memory setting and 25 seconds to typecheck. Claude Code made the changes for the move to oxlint, oxfmt and tsgo, and the team validated each step.
Turning plan files into Claude Code workflows took 5-6 hours each. A script that converts them deterministically, and flags what can move out of the LLM, cut that to 20-30 minutes at about 20% of the tokens.
An inherited app on Azure, an error, and a hunt that could easily take 1-2 days by hand. With CLI access to Azure and the repo, Claude Code ran the config and network checks and found the root cause in about 45 minutes.