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.
Borrowing it
Nothing to install: this file belongs to grafana/gcx. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/grafana/gcx/main/.agents/skills/contribute/SKILL.mdgit 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/contribute)<a href="https://agentmods.dev/skills/grafana/gcx/contribute"><img src="https://agentmods.dev/badge/skills/grafana/gcx/contribute/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/contribute"><img src="https://agentmods.dev/badge/skills/grafana/gcx/contribute.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00059 | $0.01022 |
| Opus 5.5 | $0.00024 | $0.00409 |
| Sonnet 5.5 | $0.00012 | $0.00204 |
| Haiku 4.5 | $0.00006 | $0.00102 |
Grade A, and why
contribute 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 8d 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 — 54 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Contribute to gcx
Read AGENTS.md and the authoritative contribution workflow. Use its route and ownership guidance; the contributor does not need to choose a provider, datasource or RFC workflow upfront.
1. Establish the current step
Identify the requested outcome and the existing issue, accepted decisions, RFC or implementation branch. Inspect those records and relevant code before asking questions. State the applicable route, current step and missing maintainer decision. Reuse settled scope and design at each handoff.
Work within the request and existing authorization. A draft-only or review-only request ends with that artifact. An implementation request continues through authorized work once applicable maintainer decisions are settled. Prepare the concrete result before requesting publication permission; reuse authorization already given for the same destination and scope.
2. Prepare the issue when the route needs one
Documentation changes and bug fixes can go directly to a PR. Other code contributions need an accepted issue; comment on it to coordinate the work. Follow the product-team exception for changes within an existing owned area.
Search the repository’s open and closed issues for existing reports and proposals before creating an issue or starting implementation. Reuse a relevant issue; check its outcome and maintainer decisions before proceeding. When its maintainer decision is settled, continue to the needed planning or implementation rather than drafting another proposal.
- Bugfixes: can go directly to a PR without a separate issue or prior maintainer acknowledgement. When reporting a bug, search for an existing report first and add relevant evidence there. If no report matches, use the Bug report form. Establish actual and expected behavior, reproduction or evidence, and relevant version/environment. Link the existing report from the fix PR when available. Record verified findings separately from assumptions.
- Feature: use propose-feature to research and draft the common proposal. Show a concrete problem, proposed UX and checkable acceptance criteria; scale examples to the work and identify unresolved facts.
What ships with it
9 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.
- references/capability-implementation.md 7.7 KB
- references/contract-and-tests.md 7.3 KB
- references/datasource-implementation.md 24 KB
- references/distribution-and-gates.md 10 KB
- references/placement-and-readiness.md 13 KB
- references/provider-implementation.md 8.0 KB
- references/provider-placement.md 7.2 KB
- references/raw-sql.md 6.5 KB
- references/self-review.md 24 KB
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.
- 8d ago First seen · 54 lines · 59 tokens per session scan A a6677e494a85
contribute is a skill published in the GitHub repository grafana/gcx (805 stars, last pushed yesterday), licensed Apache-2.0. It adds 59 tokens to every session and 1,022 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-10-21.
Other skills, from other repositories
story-readiness
Checks whether a story is ready to implement: clear acceptance criteria, no open questions, valid ADR and dependencies. Use when the user asks if a story, or the sprint's stories, are ready to start or build.
recipe-create-meet-space
Create a Google Meet meeting space and share the join link.
workthreads
SpecStory Workthreads - a weekly work-thread rollup across a team's repos from SpecStory coding histories (any agent - Claude Code, Codex, Cursor, Gemini, and more). It groups the window's sessions into threads of work per project and labels each new / open / recently closed, so a lead sees what shipped, what is still…
atmos-config
Atmos root configuration: atmos.yaml discovery, precedence, deep merging, basepath, imports, minimal bootstrap, and routing to narrower Atmos skills.
qa-project-bootstrap
Onboard a new QA engineer to an existing codebase, or audit an existing test architecture. Produces a 30-day ramp plan: codebase orientation, framework walkthrough, test architecture audit, mentorship pairing, and first-test guidance. Use when: "QA onboarding," "new tester," "ramp up," "test architecture audit,"…
remove
Remove a deployed framework or addon from the current workspace.