claude

rubixkube

Eight skills (status, incidents, investigate, environments, tasks, rca, changes, knowledge), a read-only investigator agent, and the hosted MCP server with 25 tools, 4 prompts and 5 resources.

1 on GitHubby RubixKubev2.2.1MITupdated 1 month agomonitoring
/

Plugin rubixkube from marketplace rubixkube in rubixkube-io/rubixkube-for-ai. Commands read from the repo's manifest — 1 month ago.

What it installs

Skills (8)

  • changes

    Changes to incidents, recorded under the person's name: report a new incident, correct one, close one, answer what fixed it, run the RCA again, comment. Use when the person wants to create or close an incident, retry an RCA, or leave a note for the team.

  • environments

    The organization's sources (Kubernetes clusters, VMs, cloud accounts, connected tools), their health, the environments they are labelled with, and the latest infrastructure snapshot of one source. Use when the person asks what is connected, how one environment is doing, or needs an environment id fo

  • incidents

    List and read incidents: what the observers detected or people reported, open or resolved, by severity, status or environment. Use when the person asks what's broken, about alerts, about a specific incident id or console link, or wants incidents in one environment.

  • investigate

    Walk one incident end to end: what happened, the RCA and its evidence, what people found, what to do next. Use when the person asks why something is broken, wants the root cause, or says "investigate" or "debug" about a service, pod, VM or incident.

  • knowledge

    What RubixKube has recorded about the organization's systems and history: the knowledge graph of resources, incidents, RCAs, changes and people. Use when the person asks about a service's history, who worked on something, what fails most, or any question whose answer is in past incidents rather than

  • rca

    Root cause analyses: the report RubixKube writes for an incident, with the timeline, impact, root cause, contributing factors, remediation and rollback steps, proposed Tasks and evidence. Use when the person asks for the RCA, the root cause, the postmortem, or recent RCAs.

  • status

    One overview of what RubixKube sees: sources and their health, open incidents by severity, Tasks waiting for someone, RCAs finished in the last day. Use when the person asks what's going on, what needs attention, how production is, or wants a morning summary.

  • tasks

    Tasks are the Fixes and Follow-ups an RCA proposes or a person adds. List them, read one, create one, rename or reprioritise, move between statuses, assign. Use when the person asks what to work on, about action items or fixes, or wants to create, assign or close a Task.

Subagents (1)

  • rubixkube-investigator

    Read-only investigator for one RubixKube incident. Use when the person wants a thorough look at an incident without changing anything: it reads the incident, its RCA and evidence, the comments and the environment snapshot, and reports back. It never closes, creates or comments.

MCP servers (1)

  • rubixkube

    connects to: https://mcp.rubixkube.ai/mcp

View source on GitHub rubixkube.ai

Similar plugins

ruflo-swarm

claudecodex

Agent teams, swarm coordination, Monitor streams, and worktree isolation

2 skills · 2 commands · 2 agents

ruvnet/ruflo 81,589

Query Trackio projects, runs, and metrics using the `trackio` CLI. Use when the user needs to list projects/runs/metrics, get summaries, or retrieve metric values from local Trackio databases. Supports both human-readable and JSON output formats. Covers project discovery, run inspection, metric querying, and system metrics. Designed for LLM agents and automation scripts.

1 skill

sickn33/agentic-awesome-skills 49,620

amplitude

claudecodex

Use Amplitude as an expert analyst — instrument Amplitude, discover product opportunities, analyze charts, create dashboards, manage experiments, and understand users and accounts.

36 skills · 1 MCP server

anthropics/claude-plugins-official 47,076

Metrics collection, logging infrastructure, distributed tracing, SLO implementation, and monitoring dashboards

4 skills · 2 commands · 4 agents

wshobson/agents 42,461

818 cybersecurity skills covering web security, pentesting, DFIR, threat intelligence, cloud security, malware analysis, and more. Mapped to 6 frameworks.

200 skills

mukul975/Anthropic-Cybersecurity-Skills 36,021

Qdrant

claude

Agent skills for Qdrant vector search: scaling, performance optimization, search quality, monitoring, deployment, model migration, version upgrades, and SDK usage

33 skills

anthropics/knowledge-work-plugins 35,601

Maintain rubixkube?

This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.

claude & codex pluginslisted