gcx: Skill for Claude Code

.agents/skills/generate-slide/SKILL.md

generate-slide is a skill for Claude Code, Codex from grafana/gcx. It costs 61 tokens per session (2,018 once invoked), scanned A, original, Apache-2.0.

A procedure for regenerating gcx's 1440×900 marketing slide from the current command-line tool. It builds the program and checks the live command tree so the slide reflects available commands and counts.

In plain words
What is it for?
Use it to refresh the bento-style marketing slide, rebuild gcx, extract its command catalogue, and update the displayed command, resource, and provider information.
Why use it?
It prevents documentation and marketing material from showing commands or statistics that no longer match the software. The workflow verifies the data before updating the slide.

Skill for Claude CodeCodex ✓ vendor

Written for no agent in particular: nothing here depends on one. Also seen: installed under .agents/ (shared by several agents).

This is grafana/gcx's own configuration. It tells Claude Code and Codex how to work on gcx itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything gcx configures →

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is go build -buildvcs=false -o bin/gcx ./cmd/gcx/.

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 · 805 stars · on GitHub · grafana.com

Reuse

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.

Copy the file
curl -O https://raw.githubusercontent.com/grafana/gcx/main/.agents/skills/generate-slide/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/grafana/gcx

Made for: Claude Code, Codex.

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 generate-slide

README.md
[![agentmods](https://agentmods.dev/badge/skills/grafana/gcx/generate-slide/github.svg)](https://agentmods.dev/skills/grafana/gcx/generate-slide)
Your own site
<a href="https://agentmods.dev/skills/grafana/gcx/generate-slide"><img src="https://agentmods.dev/badge/skills/grafana/gcx/generate-slide/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 generate-slide

Your own site · 80×15
<a href="https://agentmods.dev/skills/grafana/gcx/generate-slide"><img src="https://agentmods.dev/badge/skills/grafana/gcx/generate-slide.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 61 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,018 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 $0.00061 $0.02018
Opus 5.5 $0.00024 $0.00807
Sonnet 5.5 $0.00012 $0.00404
Haiku 4.5 $0.00006 $0.00202

Measured 2mo ago against content hash e9043e31775e, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

generate-slide 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 2mo 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.

.agents/skills/generate-slide/SKILL.md · 164 lines

How it starts

The opening of the file, as written. The whole thing — 164 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Generate gcx Marketing Slide

Regenerate docs/bento_marketing_slide.html — a 1440x900 "bento box" marketing slide — so that every command shown is verified against the live binary and all stats are accurate.

Prerequisites

  • Go toolchain available
  • docs/bento_marketing_slide.html must exist

Workflow

Stage 1: Build & Reflect

Build a fresh gcx binary and extract the full command catalog and stats.

# 1. Build
go build -buildvcs=false -o bin/gcx ./cmd/gcx/

# 2. Extract the full flat command catalog (commands + resource_types)
./bin/gcx commands --flat -o json > /tmp/gcx-catalog.json

# 3. Extract counts from the catalog
python3 -c "
import json, sys
d = json.load(open('/tmp/gcx-catalog.json'))
cmds = d.get('commands', [])
rt = d.get('resource_types', [])
leaves = [c for c in cmds if c.get('token_cost')]
print(f'Total commands: {len(cmds)}')
print(f'Leaf commands (with token_cost): {len(leaves)}')
print(f'Resource types: {len(rt)}')
"

# 4. Get provider count
./bin/gcx providers list -o json | python3 -c "
import json, sys
d = json.load(sys.stdin)
print(f'Providers: {len(d)}')
for p in d: print(f'  - {p[\"name\"]}')
"

# 5. Get the human-readable command tree (for selecting showcase commands)
./bin/gcx help-tree --depth 3 -o text

Stage 2: Verify Card Commands

For each card topic, extract the relevant subtree from the binary and confirm every command shown on the slide actually exists.

# Per-card verification — run one per card topic:
./bin/gcx help-tree kg --depth 3 -o text           # Card 1: Knowledge Graph
./bin/gcx help-tree assistant --depth 3 -o text     # Card 2: Grafana Assistant
./bin/gcx help-tree fleet --depth 3 -o text         # Card 3: Fleet Management
./bin/gcx help-tree frontend --depth 3 -o text      # Card 4a: App O11y (frontend/faro)
./bin/gcx help-tree appo11y --depth 3 -o text       # Card 4b: App O11y (appo11y)
./bin/gcx help-tree incidents --depth 3 -o text     # Card 5a: Incident Response
./bin/gcx help-tree oncall --depth 3 -o text        # Card 5b: Incident Response (OnCall)
./bin/gcx help-tree synth --depth 3 -o text         # Card 5c: Incident Response (Synth)
./bin/gcx help-tree setup --depth 3 -o text         # Card 6: K8s Observability
./bin/gcx help-tree metrics adaptive --depth 3 -o text  # Card 7a: Adaptive Telemetry
./bin/gcx help-tree logs adaptive --depth 3 -o text     # Card 7b: Adaptive Telemetry
./bin/gcx help-tree traces adaptive --depth 3 -o text   # Card 7c: Adaptive Telemetry
./bin/gcx help-tree slo --depth 3 -o text           # Card 8: Agent-Ready Platform
./bin/gcx help-tree profiles --depth 3 -o text      # Card 8: Agent-Ready Platform

Read the full file on GitHub · 164 lines

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. 2mo ago First seen · 164 lines · 61 tokens per session scan A e9043e31775e

Subscribe to this mod's changes

generate-slide is a skill published in the GitHub repository grafana/gcx (805 stars, last pushed yesterday), licensed Apache-2.0. It adds 61 tokens to every session and 2,018 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 2026-08-30.

Related

Other skills, from other repositories

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…

microsoft/ai-agents-for-beginners · 200 tokens

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

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…

vercel/next.js · 95 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

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…

vercel/next.js · 83 tokens