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 prometheus/prometheus-mcp --skill check-system-healthgit clone --depth 1 https://github.com/prometheus/prometheus-mcpWrote 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/prometheus/prometheus-mcp/check-system-health)<a href="https://agentmods.dev/skills/prometheus/prometheus-mcp/check-system-health"><img src="https://agentmods.dev/badge/skills/prometheus/prometheus-mcp/check-system-health/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/prometheus/prometheus-mcp/check-system-health"><img src="https://agentmods.dev/badge/skills/prometheus/prometheus-mcp/check-system-health.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 | $0.00045 | $0.00494 |
| Opus 5 | $0.00023 | $0.00247 |
| Sonnet 5 | $0.00009 | $0.00099 |
| Haiku 4.5 | $0.00005 | $0.00049 |
Grade A, and why
check-system-health 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 — 36 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Understanding System Health
Build an overall picture of whether Prometheus itself is healthy and whether it is successfully monitoring what it should. A good health check covers the server, its targets, and the data being collected.
Getting oriented
- healthy and ready report whether the server is up and able to serve queries.
- build_info and runtime_info identify the version, storage retention, and runtime settings; flags exposes the full command line.
- list_targets shows every scrape target and its health; list_alerts shows what is actively firing.
- tsdb_stats summarizes series counts, cardinality, and ingestion (the load side of the picture).
- query Prometheus's self-monitoring metrics directly: rate(prometheus_tsdb_head_samples_appended_total[5m]) shows ingestion throughput, and counters like prometheus_rule_evaluation_failures_total or prometheus_notifications_dropped_total should sit at zero -- any steady rate on them is a problem in itself.
Topics worth exploring
Treat these as starting points and follow what the data shows:
- Firing alerts: anything already alerting is the fastest pointer to known problems; the labels identify the affected services.
- Target health: down or flapping targets in list_targets mean missing data, and their lastError usually says why.
- Scrape performance: how close scrapes run to their timeout, e.g. with query: topk(10, scrape_duration_seconds)
- TSDB pressure: series counts and per-metric cardinality from tsdb_stats; sudden growth is an early warning sign.
- Prometheus's own resources: if node_exporter or cadvisor metrics are available, check CPU, memory, and disk headroom, e.g.: process_resident_memory_bytes{job="prometheus"}
- Data freshness: confirm critical metrics are current, e.g. query up, or time() - timestamp() to spot staleness.
Reporting findings
Summarize server status, alert and target health, and TSDB load, and call out anything that needs attention together with the evidence that shows it.
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 · 36 lines · 45 tokens per session scan A b65d3c62b121
check-system-health is a skill published in the GitHub repository prometheus/prometheus-mcp (102 stars, last pushed 5d ago), licensed Apache-2.0. It adds 45 tokens to every session and 494 once invoked, about $0.0002 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…