Toolkit in Action · Sep 5, 2026 · 0:42
Are Hotjar and Clarity loading correctly?
Watch OpenCode separate delivered HTML, the public GTM container, live browser requests, and PageSpeed into one concise analytics verdict.
The OpenCode clip loops continuously. The complete text transcript is below.
What this session proves
OpenCodeAnalytics and tagsPageSpeedConsent
Ask for a clear outcomeName the target, checks, evidence and output. The toolkit can then select the right repeatable process.
Review before anything shipsUse the returned evidence to verify the work. A report or email draft is a handoff for review, not permission to send.
Improve repeat workCapture missing fields, screenshots and approval steps. A repeated job is a candidate for a stronger shared skill.
Try the first prompt
This is the exact employee-facing request used for this lesson.
Review dsmcoachlight.com. Is Hotjar or Clarity installed, is either loading twice, and what is the current PageSpeed baseline? Read only.Results transcript
The complete text result is always available with the recording.
OpenCode · read-only client measurement
Question
Review dsmcoachlight.com.
Is Hotjar or Clarity installed, and is either loading twice?
Include the current PageSpeed baseline.
Measured result · dsmcoachlight.com
Clarity: PRESENT — loads twice
• delivered directly in page HTML
• loaded again by the public GTM container
• live collection requests observed
Hotjar: PRESENT — script loads once through GTM
• no Hotjar collector request observed in the capture window
Performance baseline · PageSpeed Insights
Mobile lab: 29 FAIL · LCP 19.1s · CLS 0.61
Mobile field: FAST · LCP 2.15s · INP 119ms · CLS 0.01
Desktop lab: 70 REVIEW · LCP 3.8s · TBT 177ms
Desktop field: FAST · LCP 1.98s · INP 85ms · CLS 0.01
Note: PageSpeed timed out once per device; the two successful legs are retained.
Consent: FAIL
Cookie banner appears, but GTM and Clarity fired before consent.
Evidence retained
Delivered HTML · public GTM payload · live request capture
PageSpeed mobile + desktop responses · HTML and text reports
Stopped here.
No client configuration changed. Nothing paused, approved, published, or written back.
Keep it safe and useful
Start a new task when the work changes, protect keys and .env files, and stop a run that is heading in the wrong direction. A person remains the final reviewer before a client-facing or live-system change. See API-key hygiene.
If this reveals a useful gap, submit an issue. The next recording and the next run should benefit from what this one taught.
