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 manage-dashboardsgit 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/manage-dashboards)<a href="https://agentmods.dev/skills/grafana/gcx/manage-dashboards"><img src="https://agentmods.dev/badge/skills/grafana/gcx/manage-dashboards/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/manage-dashboards"><img src="https://agentmods.dev/badge/skills/grafana/gcx/manage-dashboards.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 | $0.00186 | $0.01865 |
| Opus 5 | $0.00093 | $0.00932 |
| Sonnet 5 | $0.00037 | $0.00373 |
| Haiku 4.5 | $0.00019 | $0.00186 |
Grade A, and why
manage-dashboards 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 10d 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 — 160 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Manage Dashboards
Use gcx dedicated commands first. Only use gcx api when a dedicated command
cannot perform the requested operation.
Routing
| User intent | Use |
|---|---|
| Build a new dashboard from an idea, service, SLO, incident, or set of metrics | create-dashboard |
| Redesign layout, choose panels/queries, or visually iterate dashboard quality | create-dashboard |
| Generate a Go builder skeleton only | generate-resource-stubs |
| Convert an existing live dashboard to Go code | import-dashboards |
| List, search, inspect, delete, restore, pull, push, validate, promote, or snapshot existing dashboards | this skill |
| Configure gcx/auth first | setup-gcx |
Preflight for Mutations
Before any create/update/delete/push/restore operation:
gcx config current-context
gcx config check
Use --context <name> when the user named a target environment. Do not switch
the global context unless the user asked for it.
For writes, read current state first and preserve folder/manager intent:
gcx dashboards get <dashboard-name> -o json
gcx resources get folders -o json
Manager boundary: gcx protects resources managed by another tool. If a push
fails because of grafana.app/managed-by, stop and ask/confirm before using
--include-managed.
Typical Update Workflow
- Preflight —
gcx config check, then fetch current state withgcx dashboards get <name> -o json - Edit — write the modified YAML locally
- Validate and push —
gcx resources validate -p <path> -o json,gcx resources push -p <path> --dry-run,gcx resources push -p <path> - Verify —
gcx dashboards get <name> -o json
Operation Reference
Use JSON/YAML for programmatic work and table/wide output for human summaries.
| Operation | Command pattern |
|---|---|
| List datasources | gcx datasources list -o json |
| Prometheus metric names | gcx datasources prometheus labels -d <uid> --label __name__ |
| Prometheus label values | gcx datasources prometheus labels -d <uid> --label <label> |
| Prometheus metric metadata | gcx datasources prometheus metadata -d <uid> |
| Loki label names | gcx datasources loki labels -d <uid> |
| Loki label values | gcx datasources loki labels -d <uid> --label <label> |
| Tempo attribute names | gcx datasources tempo labels -d <uid> |
| Tempo attribute values | gcx datasources tempo labels -d <uid> -l resource.service.name --llm -o json |
| Pyroscope profile types | gcx datasources pyroscope list-profile-types -d <uid> |
| Pyroscope label values | gcx datasources pyroscope labels -d <uid> --label service_name |
| Other datasource types | Check gcx datasources <type> --help for dedicated subcommands before using gcx api |
| List dashboards | gcx dashboards list -o wide |
| Search by text/tag/folder | gcx dashboards search "<query>" --tag <tag> --folder <folder-name> -o json |
| Get one dashboard | gcx dashboards get <dashboard-name> -o json |
| Create from finished file | gcx dashboards create -f <dashboard.yaml> |
| Update from finished file | gcx dashboards update <dashboard-name> -f <dashboard.yaml> |
| Delete with confirmation | gcx dashboards delete <dashboard-name> |
| Delete non-interactively | gcx dashboards delete <dashboard-name> --force |
| Version history | gcx dashboards list-versions <dashboard-name> |
| Restore version | gcx dashboards versions restore <dashboard-name> <version> --message "<why>" |
| Pull dashboards/folders | gcx resources pull dashboards folders -p <dir> -o yaml |
| Pull one dashboard | gcx resources pull dashboards/<dashboard-name> -p <dir> -o yaml |
| Validate local files | gcx resources validate -p <path> -o json |
| Preview push | gcx resources push -p <path> --dry-run |
| Push local files | gcx resources push -p <path> |
| Delete by selector | gcx resources delete dashboards/<dashboard-name> |
Edit in $EDITOR |
gcx resources edit dashboards/<dashboard-name> -o yaml |
| List resource kinds | gcx resources list-types |
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.
- 10d ago First seen · 160 lines · 186 tokens per session scan A 338c2876d7f0
manage-dashboards is a skill published in the GitHub repository grafana/gcx (594 stars, last pushed today), licensed Apache-2.0. It adds 186 tokens to every session and 1,865 once invoked, about $0.0009 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…