DEDUPED Hot AI repos, turned into use cases Get the Monday 5

How to catch broken controls in a page an agent just wrote with Assay

Run Assay after an agent finishes a page and get a one-line pass or fail result.

  • Top pick
  • Software and DevOps
  • Intermediate
  • 15 minutes
  • From the README
  • Claude Code
  • Codex
  • Cursor
  • Gemini CLI

Who it is forA developer using a coding agent to build a small web app, who needs to know the page works before accepting the agent's reply.

The problemA page can look right in the code and still throw errors, ignore clicks, or show wrong counts once someone uses it.

The outcomeThe developer gets a short summary listing the page checked, the number of checks run, and anything flagged.

What you need first

  • Python 3.10+, or uv or pipx to install the tool
  • A folder containing built web page output, with index.html or another page to check
  • Internet access for the first run, when Chromium may be downloaded

Steps

  1. Run pip install assay-ui to install the tool.
  2. Run assay ./my-app --one-line against the folder that holds the page, replacing ./my-app with your folder.
  3. Read the summary line, which reports the page checked, the number of checks, and anything flagged.
  4. If anything is flagged, have the agent fix the listed problem and run the same command again.

Prompt for your agent

Use the assay CLI from the assay-ui package on the page in <folder path>. Run assay <folder path> --one-line, then report the one-line summary in your reply. Verify that the exit code is zero before you tell the user the page passed.

Caveat. Assay checks whether the page responds and contradicts itself, so it cannot confirm that the page does the wrong or right job for its purpose.

Share: X LinkedIn Hacker News Email Copy link

Disclaimer

Deduped lists open-source repositories that belong to other people. We do not own, maintain, audit, or vouch for any of them, and a repo appearing here is not an endorsement or a safety check. The use cases, steps, and prompts are written by AI and may be incomplete, outdated, or just wrong. Where a use case is marked "Seen in the wild", we link to public posts where someone described something similar, but we have not verified those posts and the use case itself is still our AI's own write-up. Use all of this at your own risk. Only run code, commands, or agents on systems and accounts you are authorized to use, and read the code and every command before you run it, especially anything that touches credentials, files, or the network. Nothing here is professional, security, legal, or financial advice. All trademarks and project names belong to their respective owners, and their use here does not imply affiliation. Content is provided as is, without warranties of any kind. Found a mistake, a safety problem, or something you want removed? Email [email protected] and we will look at it promptly. Full disclaimer page