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 find-top-resource-consumersgit 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/find-top-resource-consumers)<a href="https://agentmods.dev/skills/prometheus/prometheus-mcp/find-top-resource-consumers"><img src="https://agentmods.dev/badge/skills/prometheus/prometheus-mcp/find-top-resource-consumers/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/find-top-resource-consumers"><img src="https://agentmods.dev/badge/skills/prometheus/prometheus-mcp/find-top-resource-consumers.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 | $0.00058 | $0.00494 |
| Opus 5 | $0.00029 | $0.00247 |
| Sonnet 5 | $0.00012 | $0.00099 |
| Haiku 4.5 | $0.00006 | $0.00049 |
Grade A, and why
find-top-resource-consumers 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.
What it actually says
Finding Top Resource Consumers
Identify which services, pods, or instances consume the most CPU, memory, or disk -- or drive the most TSDB growth. Resource metrics vary by environment (node_exporter, cadvisor, kubelet, ...), so discover what exists before querying.
Getting oriented
- label_values on name (or series with regex matchers) reveals which resource metrics exist: node_cpu_seconds_total, container_memory_working_set_bytes, process_resident_memory_bytes, and so on.
- metric_metadata confirms the type and meaning of whatever discovery turns up.
- tsdb_stats answers the "who produces the most metrics" version of the question via seriesCountByMetricName.
- Prometheus's own metrics exposes monitoring cost per target: query topk(10, scrape_samples_scraped) to find the heaviest targets, and a persistently high scrape_series_added means a target keeps minting new series.
Topics worth exploring
Treat these as starting points, adapting metric names to what discovery found:
- Top CPU: CPU counters need rate() before ranking, e.g. with query: topk(10, sum by (pod) (rate(container_cpu_usage_seconds_total[5m])))
- Top memory: gauges rank directly: topk(10, sum by (instance) (container_memory_working_set_bytes))
- Top disk: node_filesystem_avail_bytes vs node_filesystem_size_bytes for fullness; rate(node_disk_written_bytes_total[5m]) for write churn.
- Trend vs snapshot: range_query the same expressions to see whether a top consumer is growing, cyclic, or stable; a stable hog and a leak need different responses.
- TSDB growth: the top metric and label names from tsdb_stats show what is inflating storage, often more actionable than any single consumer.
Reporting findings
Rank the top consumers with numbers and units, note whether each is growing or stable, and flag anything disproportionate to its peers as a candidate for follow-up.
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 · 34 lines · 58 tokens per session scan A a5576e28700f
find-top-resource-consumers is a skill published in the GitHub repository prometheus/prometheus-mcp (100 stars, last pushed 4d ago), licensed Apache-2.0. It adds 58 tokens to every session and 494 once invoked, about $0.0003 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…