synth-investigate-check

name	synth-investigate-check
description	Use when the user wants to diagnose why a Synthetic Monitoring check is failing — triage probe failures, classify failure scope, run per-probe breakdown, and identify root cause. Trigger on phrases like "why is my check failing", "investigate synthetic check", "probe failures", "check is down". For check status overview use synth-check-status. For creating or managing checks use synth-manage-checks.
allowed-tools	["gcx","Bash"]

Synthetic Check Investigator

Investigate Synthetic Monitoring check failures by triaging probe data, classifying failure scope, and identifying root cause. Experienced operators need actionable diagnosis, not hand-holding.

Core Principles

1. Use gcx commands — do not call Grafana APIs directly
2. Trust the user's expertise — skip background explanations
3. Use -o json for agent processing, default format for user display
4. Show timeline graphs for time-series data — they communicate trends faster than text
5. Collect errors; report them at the end, not interleaved in workflow steps

Prerequisites

gcx configured with an active context and appropriate permissions.

Investigation Workflow

Step 1: Get Check Status (with early exit)

gcx synthetic-monitoring checks status <ID>

If the user provided a name instead of ID, list first:

gcx synthetic-monitoring checks list -o json | jq -r '.[] | select(.job | test("<name>"; "i")) | [.id, .job, .target, .type] | @tsv'

Early exit — OK: Check success rate >= 50% across all probes. Report: "Check is healthy. Success rate: %. <probe_count> probes up." Stop unless the user asks for more.