Summary
This is post-deploy verification that actually runs checks instead of just hoping your release didn't break anything. Point it at a URL after you ship and it monitors HTTP status, console errors, network failures, Core Web Vitals, and whether critical page elements are still there. You can run it once as a quick smoke test or set it to watch continuously during a launch window. It diffs against a baseline so you catch regressions like LCP jumping 500ms or new console errors that weren't there before. The SSE stream monitoring is a nice touch since most tools ignore event-stream endpoints entirely. Pairs well with CI pipelines or just run it manually when you merge something scary.
Install to Claude Code
npx -y skills add affaan-m/ecc --skill canary-watch --agent claude-codeInstalls into .claude/skills of the current project.
Plug Mailtrap into your AI workflow and let it handle the email.
Connect Mailtrap MCP →
Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →
Make coding agent sessions - Searchable, Shareable, Vendor-neutral & Scored.
Try For Free →
Your agent targets a perfect 10 Code Health score. Deterministic. Every commit.
Try For Free →
Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →
belt cli automatically finds the best tools and skills for your agent. image, video, music, tts...
one prompt install →Files
SKILL.md
Select a file.
Featured
Plug Mailtrap into your AI workflow and let it handle the email.
Connect Mailtrap MCP →Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →Make coding agent sessions - Searchable, Shareable, Vendor-neutral & Scored.
Try For Free →Your agent targets a perfect 10 Code Health score. Deterministic. Every commit.
Try For Free →Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →belt cli automatically finds the best tools and skills for your agent. image, video, music, tts...
one prompt install →
