synth-investigate-check

synth-investigate-check is a skill for Claude Code from grafana/gcx. It costs 95 tokens per session (1,868 once invoked), scanned A, original, Apache-2.0.

A diagnostic workflow for finding why a Grafana Synthetic Monitoring check is failing. Synthetic Monitoring tests websites and services from probe locations, such as by making HTTP requests or checking network connectivity.

In plain words
What is it for?
Use it to investigate failing website, DNS, ping, TCP, or traceroute checks and identify which locations are affected and what errors they report.
Why use it?
It separates a single probe problem from a wider outage and uses probe-level results to narrow down the likely cause.

Skill for Claude Code ✓ vendor

Written for Claude Code: allowed-tools in frontmatter.

Part of the gcx plugin — 24 skills, 1 agent shipped together

Good fit Use it to investigate failing website, DNS, ping, TCP, or traceroute checks and identify which locations are affected and what errors they report.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/grafana/gcx/synth-investigate-check
About the project

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.

grafana/gcx · 597 stars · on GitHub · grafana.com

Install

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.

Any agent
npx skills add grafana/gcx --skill synth-investigate-check
Clone the repo
git clone --depth 1 https://github.com/grafana/gcx

Made for: Claude Code.

Or install gcx, the plugin that ships this one along with the rest of its 24 skills, 1 agent.

Wrote 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.

agentmods badge for synth-investigate-check

README.md
[![agentmods](https://agentmods.dev/badge/skills/grafana/gcx/synth-investigate-check/github.svg)](https://agentmods.dev/skills/grafana/gcx/synth-investigate-check)
Your own site
<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.

agentmods 80×15 button for synth-investigate-check

Your own site · 80×15
<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>
Per session 95 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,868 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce 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

Measured 11d ago against content hash 04b705af2887, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

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.

claude-plugin/skills/synth-investigate-check/SKILL.md · 192 lines

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

  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

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.

  1. Get check config to verify enabled: true (gcx synthetic-monitoring checks get <ID> -o json | jq .spec.enabled)
  2. If disabled: report "Check is disabled — no metrics will appear until it is re-enabled."
  3. 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:

Read the full file on GitHub · 192 lines

Files

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.

Changes

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.

  1. 11d ago First seen · 192 lines · 95 tokens per session scan A 04b705af2887

Subscribe to this mod's changes

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.

Related

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…

google/skills · 112 tokens

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…

google/skills · 83 tokens

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.

google/skills · 69 tokens

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…

google/skills · 117 tokens

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.

awslabs/mcp · 52 tokens

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.

opensandbox-group/OpenSandbox · 48 tokens