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 review-prometheus-rulesgit 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/review-prometheus-rules)<a href="https://agentmods.dev/skills/prometheus/prometheus-mcp/review-prometheus-rules"><img src="https://agentmods.dev/badge/skills/prometheus/prometheus-mcp/review-prometheus-rules/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/review-prometheus-rules"><img src="https://agentmods.dev/badge/skills/prometheus/prometheus-mcp/review-prometheus-rules.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high System Prompt Leakage · line 18 Skill contains instructions that could directly expose system prompts, internal rules, or hidden instructions to users or external parties.Fix: Remove any instructions that reveal, print, or output system prompts or internal rules. System instructions should never be exposed to end users.
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 | $0.00055 | $0.00607 |
| Opus 5.5 | $0.00022 | $0.00243 |
| Sonnet 5.5 | $0.00011 | $0.00121 |
| Haiku 4.5 | $0.00006 | $0.00061 |
Grade A, and why
review-prometheus-rules 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 1mo 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 — 34 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Reviewing and Improving Prometheus Rules
Recording rules pre-compute expensive or repeated expressions into new series; alerting rules turn expressions into notifications. They live together in rule groups and are best designed together -- good alerts are often built on top of good recording rules. This runbook covers auditing the rules that exist, finding gaps, and drafting improvements.
Getting oriented
- list_rules returns every rule group -- recording and alerting -- with expressions, labels, and per-rule evaluation health.
- list_alerts shows what is firing right now; useful for separating "badly tuned" from "correctly noisy".
- tsdb_stats reveals series counts and cardinality, which tells you whether a pre-aggregation would actually pay off.
- list_targets can surface scraped services that no rule covers at all.
- Prometheus's own metrics expose rule health at runtime: the ALERTS{} series records pending and firing alerts (range_query it to reconstruct an alert's history and spot flapping), rate(prometheus_rule_evaluation_failures_total[5m]) catches rules that fail to evaluate, and prometheus_rule_group_last_duration_seconds approaching the group's interval means evaluation is running out of budget.
Topics worth exploring
Treat these as starting points and follow what the data shows, not as a fixed checklist:
- Rule health: list_rules reports evaluation health and last error per rule; broken or always-empty rules are quick wins. Test a suspect expression directly by querying.
- Recording rule candidates: expressions repeated across alerts or dashboards, especially rate/sum/histogram_quantile combinations. Verify a candidate returns what you expect before proposing it, e.g. with range_query: sum by (job) (rate(http_requests_total{code=~"5.."}[5m])) / sum by (job) (rate(http_requests_total[5m]))
- Alert quality: alert on symptoms rather than causes, keep severity labels meaningful, balance
fordurations against detection speed, and fill in annotations (summary, description, runbook link). - Coverage gaps: SLOs without multi-window multi-burn-rate alerts, critical metrics without absent() protection, resource exhaustion without capacity alerting.
- Naming conventions: recording rules follow level:metric:operations (e.g. job:http_requests:rate5m); docs_search has the full convention and the rule config schema.
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.
- 1mo ago First seen · 34 lines · 55 tokens per session scan A 22701df1916a
review-prometheus-rules is a skill published in the GitHub repository prometheus/prometheus-mcp (127 stars, last pushed 3d ago), licensed Apache-2.0. It adds 55 tokens to every session and 607 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.
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…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…
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.
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…
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…