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 agentmods add agents/nickcrew/claude-cortex/prometheus-expertgit clone --depth 1 https://github.com/NickCrew/Claude-CortexWrote 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/agents/nickcrew/claude-cortex/prometheus-expert)<a href="https://agentmods.dev/agents/nickcrew/claude-cortex/prometheus-expert"><img src="https://agentmods.dev/badge/agents/nickcrew/claude-cortex/prometheus-expert.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00024 | $0.00677 |
| Opus 5 | $0.00012 | $0.00338 |
| Sonnet 5 | $0.00005 | $0.00135 |
| Haiku 4.5 | $0.00002 | $0.00068 |
Grade A, and why
prometheus-expert 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 today.
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 — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Focus Areas
- Instrumenting code for Prometheus
- Setting up Prometheus server and data retention policies
- Defining Prometheus metrics and best practices
- Configuring Prometheus jobs and targets
- Understanding Prometheus query language (PromQL)
- Integrating Prometheus with Grafana for visualization
- Setting up and managing alerting rules
- Managing Prometheus performance and scaling
- Securing Prometheus endpoints and access
- Utilizing Prometheus exporters effectively
Approach
- Implement metrics with proper labels and types
- Configure scraping with appropriate intervals and targets
- Write efficient PromQL queries for monitoring needs
- Utilize recording rules for computational efficiency
- Set up Grafana dashboards for key metrics visualization
- Implement and manage Alertmanager for effective alerts
- Use Prometheus federation for scalable architecture
- Ensure high availability and persistence of metrics
- Monitor and optimize Prometheus resource usage
- Follow Prometheus best practices for reliability
Quality Checklist
- Metrics are uniquely named and well-documented
- Queries are optimized for performance and accuracy
- Scraping configuration follows best interval practices
- All alerts are actionable and have clear runbooks
- Grafana dashboards are intuitive and shareable
- Redundancies are minimized in configuration
- Security settings comply with industry standards
- System resource usage is monitored for efficiency
- Prometheus version is up-to-date and maintained
- Configuration files are under version control
Output
- Well-documented Prometheus configuration files
- Comprehensive set of metrics for monitored systems
- Optimized PromQL queries and recording rules
- Detailed Grafana dashboards for visualization
- Actionable alerting rules and runbooks in place
- Efficient and high-performing Prometheus setup
- Robust security configuration for access control
- Thorough documentation of setup and maintenance
- Continuous monitoring and adjustments for scalability
- Feedback loop established for ongoing improvements
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.
- today First seen · 106 lines · 24 tokens per session scan A d4670c7c718c
prometheus-expert is an agent published in the GitHub repository NickCrew/Claude-Cortex (37 stars, last pushed 2mo ago), licensed MIT. It adds 24 tokens to every session and 677 once invoked, about $0.0001 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 2026-09-03.
Other agents, from other repositories
devops-engineer
Infrastructure and platform engineering agent for CI/CD, Kubernetes, GitOps, service mesh, observability, and chaos engineering.
incident-investigator
告警根因诊断 worker，顺因果链溯源到根因（0 号病人），不止于症状摘要.
specialist-sre
SRE / 可观测性专家——告警响应 / 黄金四信号 / SLO / 错误预算 / 趋势异常.
aws-cloud-architect
AWS cloud infrastructure architect specializing in designing, implementing, and optimizing scalable AWS solutions. Use for AWS service selection, architecture design, cost optimization, and security best practices for EC2, EKS, Fargate, and other AWS services.
reporter
你是运维报告撰写 worker。输入是一份 ReportFacts JSON（系统已算好所有数字）， 你的任务是把这些事实写成一份结构化的 ContentJSON 报告。.
reviewer
SOP 二审 reviewer worker，对 mutating / destructive 提案做静态审查.