Instructions file CodexOpenCode
AGENTS.md instructions for prometheus/prometheus-mcp, covering agent guide for prometheus mcp server, build, test, lint, architecture in brief, adding a new tool and gotchas.
Instructions file
Claude Code instructions for prometheus/prometheus-mcp, a project described as: MCP server for LLMs to interact with Prometheus.
Skill Claude CodeCodex
Health-check the Prometheus server and its targets. Use for status, uptime, or is-monitoring-OK questions; reviews readiness, active alerts, target health, TSDB stats, and runtime info.
Skill Claude CodeCodex
Find the top CPU, memory, or disk consumers. Use for capacity reviews, noisy-neighbor hunts, and top-N questions about which jobs, pods, or instances use the most resources or drive TSDB growth; builds topk() queries over discovered metrics.
Skill Claude CodeCodex
Investigate elevated error rates and failing requests. Use when errors or 5xx/gRPC failures spike, SLOs burn, or an error alert fires; quantifies error ratios with rate(), compares to baseline, and isolates affected jobs and instances.
Skill Claude CodeCodex
Find and reduce high-cardinality metrics and labels. Use when series counts or memory grow, queries slow down, or tsdbstats shows label explosions; pinpoints offending labels and proposes relabeling, dropping, and aggregation fixes.
Skill Claude CodeCodex
Audit and improve recording and alerting rules. Use when reviewing alert coverage or rule health, drafting new alerts or recording rules, investigating flapping or noisy alerts, or speeding up slow dashboards with pre-computed expressions; produces complete rule-group YAML.
Skill Claude CodeCodex
Diagnose missing metrics, absent series, or scrape gaps. Use when queries unexpectedly return empty, a metric stopped reporting, a target is down or unscraped, or dashboards show no data; walks target health, metadata, and config checks.
Skill Claude CodeCodex
Review and tune Prometheus configuration and performance. Use for scrape interval, retention, storage, relabeling, flag, and capacity questions, or when Prometheus itself is slow or resource-hungry; recommends concrete config changes.