# monitoring-specialist

This subagent helps plan metrics, logs, tracing, alerts, and SLA monitoring. Use it while building observability for an infrastructure project.

- subagent · `type=agent` · Claude Code · 1677 installs
- Author: davila7
- License: not stated · policy=link-only · description only; the file stays with the author
- Source: https://github.com/davila7/claude-code-templates/tree/HEAD/cli-tool/components/agents/devops-infrastructure/monitoring-specialist.md
- Updated: 2026-10-24
- HTML: https://affpapa.org/en/nevibecode/agents/monitoring-specialist

## What it does

The subagent works on infrastructure monitoring tasks, from collecting metrics and examining logs to tracing requests across services and setting up alerts. Its available tools cover file reading and editing as well as shell commands. The listed systems include Prometheus, Grafana, Loki, and OpenTelemetry.

It considers latency, traffic, errors, and resource saturation when shaping monitoring, and recommends alerting on symptoms. Possible outputs include Prometheus rules, Grafana dashboards, OpenTelemetry instrumentation, SLA reports, and runbooks for recurring alert scenarios. It needs project configuration files and a command-running environment to make changes; without those, it cannot apply configuration in the project. Retention and monitoring costs are also part of its stated focus.

## Install

### Claude Code (native platform)

1. **claude-code-templates**
```bash
npx claude-code-templates@latest --agent devops-infrastructure/monitoring-specialist
```

2. **Manually: put the files in place**
- File: `.claude/agents/monitoring-specialist.md` — For all projects use ~/.claude/agents/. Claude delegates by the description field or an @-mention

### Codex

**Manually: put the files in place**
- File: `.codex/agents/monitoring-specialist.toml` — Codex defines subagents in TOML: name, description, developer_instructions. Move the Markdown text into developer_instructions by hand. For all projects use ~/.codex/agents/

### Cursor

**Manually: put the files in place**
- File: `.cursor/agents/monitoring-specialist.md` — Cursor also reads .claude/agents/

Where a file is given instead of a command, copy the files from the source to that path: https://github.com/davila7/claude-code-templates/tree/HEAD/cli-tool/components/agents/devops-infrastructure/monitoring-specialist.md

## When to use it
- configure metric collection and Prometheus alert rules
- aggregate service logs and define alert conditions
- set up OpenTelemetry tracing across services
- build dashboards for SLA and performance checks
- write response steps for common alert scenarios

## Example prompts
- Set up Prometheus metrics and draft alert rules for this service.
- Plan infrastructure log aggregation and alerts for error patterns.
- Create Grafana dashboards and an SLA monitoring report.

## Similar
- [security-auditor](https://affpapa.org/en/nevibecode/agents/voltagent-community-security-auditor.md) — subagent · 10718 installs
- [error-detective](https://affpapa.org/en/nevibecode/agents/error-detective.md) — subagent · 7557 installs
- [devops-engineer](https://affpapa.org/en/nevibecode/agents/devops-engineer.md) — subagent · 7392 installs
- [deployment-engineer](https://affpapa.org/en/nevibecode/agents/deployment-engineer.md) — subagent · 6079 installs
- [security-engineer](https://affpapa.org/en/nevibecode/agents/security-engineer.md) — subagent · 3243 installs
- [data-engineer](https://affpapa.org/en/nevibecode/agents/voltagent-community-data-engineer.md) — subagent · 3194 installs

From the same set: [davila7/claude-code-templates](https://affpapa.org/en/nevibecode/by/davila7/claude-code-templates.md) — 238 cards

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md