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
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/grafana/gcxnpx agentmods add skills/grafana/gcx/synth-manage-checksWrote 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-manage-checks)<a href="https://agentmods.dev/skills/grafana/gcx/synth-manage-checks"><img src="https://agentmods.dev/badge/skills/grafana/gcx/synth-manage-checks/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-manage-checks"><img src="https://agentmods.dev/badge/skills/grafana/gcx/synth-manage-checks.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 141 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00057 | $0.02093 |
| Opus 5.5 | $0.00023 | $0.00837 |
| Sonnet 5.5 | $0.00011 | $0.00419 |
| Haiku 4.5 | $0.00006 | $0.00209 |
Grade A, and why
synth-manage-checks scanned grade A with 1 finding 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 6d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
1. Use gcx commands; never call Grafana APIs directly (no curl, no HTTP calls) How it starts
The opening of the file, as written. The whole thing — 215 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Synthetic Monitoring Check Manager
Manage Synthetic Monitoring checks using gcx.
Core Principles
- Use gcx commands; never call Grafana APIs directly (no curl, no HTTP calls)
- Trust the user's expertise — no explanations of what SM or gcx is
- Use
-o jsonfor agent processing; default table format for user display - gcx validates specs client-side before calling the API (probe names, check type, target format);
--dry-runonchecks create/checks updateadditionally validates against the SM API without writing anything - Probe names are case-sensitive — always copy-paste from
gcx synthetic-monitoring probes list
Workflow 1: Create New Check
Step 1: Determine Check Type
Pick the type from the target format (full decision tree and per-type templates: check-types.md):
| Target | Check Type |
|---|---|
URL (https://..., http://...) |
HTTP |
| Hostname or IP (no port) | Ping |
| Domain name (DNS lookup) | DNS |
host:port |
TCP |
| URL with routing path analysis | Traceroute |
If unsure, ask the user what they want to test (availability, DNS, port connectivity, routing).
Step 2: List and Select Probes
gcx synthetic-monitoring probes list
Recommend at least 3 geographically distributed probes. Copy names exactly as shown — case-sensitive. Suggest probes across different continents or regions to provide meaningful coverage (e.g., one each from North America, Europe, Asia-Pacific).
Step 3: Build YAML Definition
Use the template from check-types.md for the chosen type, filling the type-specific settings block. Common fields:
apiVersion: syntheticmonitoring.ext.grafana.app/v1alpha1
kind: Check
metadata:
name: <job-name> # gcx rewrites this to <job>-<id> after create
spec:
job: <job-name>
target: <target>
frequency: 60000 # milliseconds; 10000-120000 typical
timeout: 10000 # milliseconds; must be < frequency
enabled: true
labels:
- name: environment
value: production
- name: team
value: platform
probes:
- Atlanta
- Frankfurt
- Singapore
alertSensitivity: none # none unless the stack uses legacy sensitivity alerts
basicMetricsOnly: false # true = fewer metrics, lower cardinality
# folderUid: production-folder-uid # Optional: UID of an existing Grafana folder
settings:
http: {} # Replace with type-specific settings
What ships with it
1 file 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.
- 6d ago Changed · +10 lines c82df86a4f4f
- 14d ago Changed · +4 lines · -54 tokens per session 12329510a062
- 29d ago Changed · +8 lines c22548df73a7
- 1mo ago Changed · +9 lines 56e8ffdf0804
- 2mo ago First seen · 184 lines · 111 tokens per session scan A 8880651c94f8
synth-manage-checks is a skill published in the GitHub repository grafana/gcx (817 stars, last pushed today), licensed Apache-2.0. It adds 57 tokens to every session and 2,093 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
synth-manage-checks compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| synth-manage-checksgrafana/gcx | Skill | 817 | today | Apache-2.0 | A | 57 | Claude Code |
| imagegenopenai/codex | Skill | 133k | today | Apache-2.0 | A | 113 | Codex |
| playwright-climicrosoft/playwright | Skill | 99k | yesterday | Apache-2.0 | A | 19 | Claude Code |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 79k | 4d ago | MIT | A | 200 | Claude Code, Codex |
| systematic-debuggingobra/superpowers | Skill | 313k | 3d ago | MIT | A | 21 | Claude Code |
| next-cache-components-adoptionvercel/next.js | Skill | 143k | today | MIT | A | 95 | Claude Code |
| chat-pet-sprite-creationmicrosoft/vscode | Skill | 195k | today | MIT | A | 53 | Claude Code, Codex |