gcx is a command-line tool that lets people and AI coding agents manage and inspect Grafana Cloud, Enterprise, and open-source instances. It provides access to dashboards, alerts, SLOs, metrics, logs, and traces, with workflows for alert investigation, dashboard management, GitOps, and observability setup. Its catalogue entries provide agent instructions and extensions for using gcx.
Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add grafana/gcx --skill synth-investigate-checkgit clone --depth 1 https://github.com/grafana/gcxWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/grafana/gcx/synth-investigate-check)<a href="https://agentmods.dev/skills/grafana/gcx/synth-investigate-check"><img src="https://agentmods.dev/badge/skills/grafana/gcx/synth-investigate-check/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/grafana/gcx/synth-investigate-check"><img src="https://agentmods.dev/badge/skills/grafana/gcx/synth-investigate-check.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00095 | $0.01868 |
| Opus 5 | $0.00048 | $0.00934 |
| Sonnet 5 | $0.00019 | $0.00374 |
| Haiku 4.5 | $0.00010 | $0.00187 |
Grade A, and why
synth-investigate-check scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 11d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 192 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Synthetic Check Investigator
Investigate Synthetic Monitoring check failures by triaging probe data, classifying failure scope, and identifying root cause.
Core Principles
- Use gcx commands — do not call Grafana APIs directly
- Trust the user's expertise — skip background explanations
- Use
-o jsonfor agent processing, default format for user display - Show timeline graphs for time-series data — they communicate trends faster than text
- Collect errors; report them at the end, not interleaved in workflow steps
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 with a job glob (the numeric ID is the NAME suffix, e.g. web-check-1001 is ID 1001):
gcx synthetic-monitoring checks list --job '*<name>*'
Early exit — OK: Status command reports OK (success rate at or above the check's alertSensitivity threshold: high = 95%, medium/default = 90%, low = 75%).
Report: "Check <job> is healthy. Success rate: %. <probe_count> probes up."
Stop unless the user asks for more.
Early exit — NODATA: No Prometheus metrics available.
- Get check config to verify
enabled: true(gcx synthetic-monitoring checks get <ID> -o json | jq .spec.enabled) - If disabled: report "Check is disabled — no metrics will appear until it is re-enabled."
- If enabled: report "No metrics found. Check datasource config or whether the SM stack is healthy." Stop after reporting.
Step 2: Get Check Configuration
gcx synthetic-monitoring checks get <ID> -o json
Extract: job name, target, check type (http/ping/dns/tcp/traceroute), probe list, frequency, timeout, alertSensitivity, enabled flag.
For HTTP checks also note: any assertion settings, TLS config, expected status codes.
Step 3: Timeline Triage
gcx synthetic-monitoring checks timeline <ID> --from now-1h --to now
Show the graph output to the user. Then analyze the pattern:
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 11d ago First seen · 192 lines · 95 tokens per session scan A 04b705af2887
synth-investigate-check is a skill published in the GitHub repository grafana/gcx (597 stars, last pushed today), licensed Apache-2.0. It adds 95 tokens to every session and 1,868 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
gke-node-notready
Diagnoses GKE nodes reporting NotReady or Unknown status by inspecting node conditions, events, kubelet/containerd logs, and node metrics, then proposing safe remediations. Use when nodes show NotReady, when the kubelet stops posting node status, or when workloads are evicted or stuck Pending due to node health. Don't…
gke-ai-troubleshooting-jobset-interruption
Diagnoses GKE JobSet interruptions, restarts, and preemptions for AI/ML training workloads autonomously. Use when troubleshooting JobSet restart loops, spot VM preemptions, node readiness failures, host VM issues, or coordinator worker crashes. Don't use for general GKE cluster creation, basic workload deployment, or…
gke-workload-troubleshooting
Diagnoses GKE workload failures (CrashLoopBackOff, OOMKilled, ImagePullBackOff, Pending, etc.) via logs and events. Use when pods fail to start or crash repeatedly. Don't use for GKE cluster infrastructure provisioning, node pool creation, or non-Kubernetes Google Cloud services.
gke-ai-troubleshooting-handle-disruption-gpu-tpu
Diagnoses, predicts, and mitigates node disruptions during Compute Engine host maintenance and hardware or software maintenance events for GPU and TPU workloads on GKE. Use when diagnosing node disruptions, predicting host maintenance events on GPU/TPU nodepools, inspecting node interruption PromQL metrics, auditing…
agentcore-investigation
Investigate Bedrock AgentCore runtime sessions via CloudWatch Logs Insights — resolve session/trace IDs, query OTEL spans, filter noise, build timelines. Use when debugging AgentCore agent sessions, tracing tool calls, or analyzing latency.
troubleshoot-sandbox
Troubleshoot OpenSandbox issues by running diagnostics (logs, inspect, events, summary) via CLI or HTTP API to diagnose sandbox failures like OOM, crash, image pull errors, network problems, etc.