Spider Monitoring Claude Plugin

The Spider Monitoring Claude Plugin gives Claude Code the ability to autonomously read, compare, and troubleshoot Spider self-monitoring data. It wraps the Spider Mon CLI with purpose-built skills and agents for review, period comparison, alert decoding, and tuning advice.

The spider-mon plugin is one of two plugins in the spider-analyzer marketplace. See also spider-claude-plugin for the traffic-investigation counterpart.

Prerequisites

The Spider Mon CLI must be installed and a profile configured. spider-mon reuses the same profiles as the Spider CLI, at ~/.spider/profiles.json.

Install

Claude Code plugins come from marketplaces. The plugin repo is its own marketplace — add it first, then install the spider-mon plugin from it:

# Inside Claude Code
/plugin marketplace add https://gitlab.com/spider-analyzer/tools/spider-claude-plugin.git
/plugin install spider-mon@spider-analyzer

Skills

Skill	When to use
/spider-mon-glossary	Reference for spider-mon output and Spider self-monitoring terminology
/spider-mon-tuning-guide	Tuning playbook — replicas, retention, search speed, HA — with exact setup.yaml keys
/spider-mon-check-changes	Compare two equal-length windows around a reference time T (since-T diff)
/spider-mon-compare-periods	Diff two explicit time windows (week-over-week, before/after deploy)
/spider-mon-compare-baseline	Diff current state against a previously-saved named baseline
/spider-mon-search-logs	Workflow for digging into server / GUI logs via spider-mon search
/spider-mon-alert-decode	Decode a Spider alert email or probe name into meaning, threshold, and next-step commands

Agents

Agent	What it does
spider-mon-troubleshooter	Reactive — auto-mode finds anomalies; symptom-driven mode focuses on a specific issue; returns severity, since-when, root cause + tuning
spider-mon-tuning-advisor	Proactive — given a goal (Nx load, retention, storage, search, HA), returns a concrete setup.yaml change list + verification plan

How it works

The plugin has no direct API dependency — it teaches Claude Code how to use spider-mon to accomplish self-monitoring review and troubleshooting tasks. It provides Claude with:

• Skills — workflows or reference docs that translate a goal into spider-mon invocations or interpret its output.
• Agents — autonomous agents that run a full investigation (reactive) or capacity plan (proactive) and return a structured JSON report.

All API calls go through the spider-mon binary using the configured profile.

Repository

Gitlab