A botched deploy can shove a hero image off-screen or break a pricing table, and nobody notices until a customer does. This tester screenshots your pages on a schedule.
sonnet4 daysApifyPlaywrightGPT-4 VisionSlack
Claude
63ROI
63Scale
$1.6k81Saved
ROI for
README.md
Why this subagent
A botched deploy can shove a hero image off-screen or break a pricing table, and nobody notices until a customer does. This tester screenshots your pages on a schedule.
It diffs each capture against an approved baseline, then asks a vision model whether a change is real breakage or expected content. You get a Slack alert with the diff image and a verdict, and ignorable shifts are filtered out so the channel stays trustworthy.
How it runs
Used at step 01 to kick off the pipeline.
Write
Used at step 01 to kick off the pipeline.
WebFetch
Used at step 01 to kick off the pipeline.
WebSearch
Used at step 01 to kick off the pipeline.
Compare each new shot against the approved baseline at the pixel and layout level.
pending
Send real differences to a vision model to judge whether they are breakage or expected.
pending
Alert Slack with the diff image and a verdict, and skip ignorable changes.
pending
Sample output
json
// Sample output
// (generated when the pipeline finishes)
Compare the new screenshot to baseline and return {changed: bool, severity, region, likely_cause}; ignore dynamic content zones marked in config.
Unlock the rest
The full agent definition, install snippet, and starter task are gated for community members.
Members get the full `.md` agent file, the npm / pnpm install one-liners, a starter prompt that we've tuned against real runs, and the open-source repo when this automation ships there. One email, magic link, done.