debug-production
Investigate a production bug in a fixed order. Find the failing issue, read its stack and first-seen release, pull the logs and trace around the first event, check who is affected, state what is unknown, fix it, then check that new events stop. Use when someone asks why something broke in production, why checkout or login fails, what an error or stack trace means, or to debug a crash, exception, 500 error, or error spike. Reads LogBrew through its MCP server or the logbrew CLI, and works from a pasted stack trace and logs when no tool is connected.
instrument-app
Add error tracking, structured logs, and tracing to an app, then prove it works by reading a test event back. Use when someone asks to add error tracking, logging, monitoring, observability, or tracing, to set up LogBrew or install its SDK, or to check that events arrive. Detects the framework with logbrew setup --json, installs the matching SDK, sets service, environment, and release, sends one test event, and reads it back. Includes logging rules that help with any tool.
verify-release
Decide go or rollback after a deploy. Compare the new release's issues, error logs, and trace error rate with the previous release, then report the decision with evidence. Use when someone asks if a deploy is safe, whether a release broke anything, to check a canary or rollout, to compare 2 versions, or whether to roll back. Reads LogBrew release comparisons through the logbrew CLI or MCP server, and works from exported error and request counts when no tool is connected.