How do I install the Prometheus skill?

Run npx skillmds@latest add modbender/prometheus-3 in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Prometheus safe to use?

This skill has not completed SkillMD's automated safety review yet. Independent scanners report: SkillSpector: PASS, Skill Scanner: PASS. Capability flags: executes scripts, makes network calls, reads secrets. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Prometheus?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Prometheus free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Prometheus?

modbender (@modbender) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Prometheus by modbender — Agent Skill

Name: Prometheus
Rating: 4.2 (5 reviews)
Author: modbender

Prometheus

Query Prometheus monitoring data to check server metrics, resource usage, and system health. Use when the user asks about server status, disk space, CPU/memory usage, network stats, or any metrics collected by Prometheus. Supports HTTP Basic Auth via environment variables.

modbender Updated Sep 22, 2026 12 repo stars

File contents

Prometheus Skill

Query Prometheus monitoring data to get insights about your infrastructure.

Environment Variables

Set in .env file:

PROMETHEUS_URL - Prometheus server URL (e.g., http://localhost:9090)
PROMETHEUS_USER - HTTP Basic Auth username (optional)
PROMETHEUS_PASSWORD - HTTP Basic Auth password (optional)

Usage

Query Metrics

Use the CLI to run PromQL queries:

source .env && node scripts/cli.js query '<promql_query>'

Common Examples

Disk space usage:

node scripts/cli.js query '100 - (node_filesystem_avail_bytes / node_filesystem_size_bytes * 100)'

CPU usage:

node scripts/cli.js query '100 - (avg by (instance) (irate(node_cpu_seconds_total{mode="idle"}[5m])) * 100)'

Memory usage:

node scripts/cli.js query '(node_memory_MemTotal_bytes - node_memory_MemAvailable_bytes) / node_memory_MemTotal_bytes * 100'

Load average:

node scripts/cli.js query 'node_load1'

List Metrics

Find available metrics matching a pattern:

node scripts/cli.js metrics 'node_memory_*'

Series Discovery

Find time series by label selectors:

node scripts/cli.js series '{__name__=~"node_cpu_.*", instance=~".*:9100"}'

Get Labels

List label names:

node scripts/cli.js labels

List values for a specific label:

node scripts/cli.js label-values instance

Output Format

All commands output JSON for easy parsing. Use jq for pretty printing:

node scripts/cli.js query 'up' | jq .

Common Queries Reference

Metric	PromQL Query
Disk free %	`node_filesystem_avail_bytes / node_filesystem_size_bytes * 100`
Disk used %	`100 - (node_filesystem_avail_bytes / node_filesystem_size_bytes * 100)`
CPU idle %	`avg by (instance) (irate(node_cpu_seconds_total{mode="idle"}[5m])) * 100`
Memory used %	`(node_memory_MemTotal_bytes - node_memory_MemAvailable_bytes) / node_memory_MemTotal_bytes * 100`
Network RX	`rate(node_network_receive_bytes_total[5m])`
Network TX	`rate(node_network_transmit_bytes_total[5m])`
Uptime	`node_time_seconds - node_boot_time_seconds`
Service up	`up`

Notes

Time range defaults to last 1 hour for instant queries
Use range queries [5m] for rate calculations
All queries return JSON with data.result containing the results
Instance labels typically show host:port format

---name: prometheus-3description: Query Prometheus monitoring data to check server metrics, resource usage, and system health. Use when the user asks about server status, disk space, CPU/memory usage, network stats, or any metrics collected by Prometheus. Supports HTTP Basic Auth via environment variables.---# Prometheus SkillQuery Prometheus monitoring data to get insights about your infrastructure.## Environment VariablesSet in `.env` file:- `PROMETHEUS_URL` - Prometheus server URL (e.g., `http://localhost:9090`)- `PROMETHEUS_USER` - HTTP Basic Auth username (optional)- `PROMETHEUS_PASSWORD` - HTTP Basic Auth password (optional)## Usage### Query MetricsUse the CLI to run PromQL queries:```bashsource .env && node scripts/cli.js query '<promql_query>'```### Common Examples**Disk space usage:**```bashnode scripts/cli.js query '100 - (node_filesystem_avail_bytes / node_filesystem_size_bytes * 100)'```**CPU usage:**```bashnode scripts/cli.js query '100 - (avg by (instance) (irate(node_cpu_seconds_total{mode="idle"}[5m])) * 100)'```**Memory usage:**```bashnode scripts/cli.js query '(node_memory_MemTotal_bytes - node_memory_MemAvailable_bytes) / node_memory_MemTotal_bytes * 100'```**Load average:**```bashnode scripts/cli.js query 'node_load1'```### List MetricsFind available metrics matching a pattern:```bashnode scripts/cli.js metrics 'node_memory_*'```### Series DiscoveryFind time series by label selectors:```bashnode scripts/cli.js series '{__name__=~"node_cpu_.*", instance=~".*:9100"}'```### Get LabelsList label names:```bashnode scripts/cli.js labels```List values for a specific label:```bashnode scripts/cli.js label-values instance```## Output FormatAll commands output JSON for easy parsing. Use `jq` for pretty printing:```bashnode scripts/cli.js query 'up' | jq .```## Common Queries Reference| Metric | PromQL Query ||--------|--------------|| Disk free % | `node_filesystem_avail_bytes / node_filesystem_size_bytes * 100` || Disk used % | `100 - (node_filesystem_avail_bytes / node_filesystem_size_bytes * 100)` || CPU idle % | `avg by (instance) (irate(node_cpu_seconds_total{mode="idle"}[5m])) * 100` || Memory used % | `(node_memory_MemTotal_bytes - node_memory_MemAvailable_bytes) / node_memory_MemTotal_bytes * 100` || Network RX | `rate(node_network_receive_bytes_total[5m])` || Network TX | `rate(node_network_transmit_bytes_total[5m])` || Uptime | `node_time_seconds - node_boot_time_seconds` || Service up | `up` |## Notes- Time range defaults to last 1 hour for instant queries- Use range queries `[5m]` for rate calculations- All queries return JSON with `data.result` containing the results- Instance labels typically show `host:port` format

Frequently asked questions