Kstack: Skill Pack for Claude Code to Monitor and Troubleshoot Kubernetes
Kstack is a skill pack for Claude Code (and other AI coding agents) that exposes a set of slash commands for monitoring and troubleshooting Kubernetes clusters. It hooks into your existing kubeconfig and RBAC permissions, runs standard tools like kubectl, Kubetail, Trivy, Pluto, and hands the results to the LLM for analysis — aiming for fast, token-efficient responses.
Key Skills
/cluster-status— health snapshot (pod restarts, node conditions, resource pressure)/events— recent events ranked by severity/investigate— root-cause analysis across events, logs, and related resources/logs— shared tmux session translating natural language into log fetches (via Kubetail)/metrics— CPU, memory, and other resource metrics for pods, nodes, workloads/exec— shared tmux shell into a pod, node, or ephemeral debug container/audit-security— RBAC, pod security posture, privilege tightening/audit-network— NetworkPolicy, Service, Ingress, GatewayAPI, DNS, and encryption checks/audit-cost— requests vs. usage, over-provisioning, idle capacity/audit-outdated— outdated services, known CVEs, available version bumps/cleanup— removes all kstack-owned resources (debug containers, pod clones, watcher jobs)/forget— clears local cache and cluster knowledge
Installation
Global install:
curl -sS https://kstack.sh/install | bash
Local project install:
curl -sS https://kstack.sh/install | bash -s -- --local
By default, skills are prefixed with kstack-*; use --no-prefix to disable. The installer auto-detects agents on your PATH and installs for each. Supported agents include Claude Code, OpenAI Codex CLI (--agent codex), OpenCode (--agent opencode), Cursor (--agent cursor), Factory Droid (--agent factory), Slate (--agent slate), Kiro (--agent kiro), and Hermes (--agent hermes).
How It Works
All skills are read-only by default — mutations require explicit confirmation. They honor your local kubeconfig context and RBAC. If permissions are insufficient, kstack reports the issue. Global flags like --context <ctx> are supported across all skills.
Who It's For
Developers and platform engineers who use AI coding agents and need quick, natural-language-driven monitoring and debugging of Kubernetes clusters without switching contexts.
📖 Read the full source: HN LLM Tools
👀 See Also
AVP Protocol Enables LLM Agents to Share KV-Cache Instead of Text for Token Efficiency
AVP (Agent Vector Protocol) allows LLM agents to pass KV-cache directly between them instead of text, reducing token processing by 73-78% and achieving 2-4x speedups across Qwen, Llama, and DeepSeek models. The protocol works with HuggingFace and vLLM connectors and is available as a Python package.
Aura Research: Local tool compiles documents into AI-navigable wiki with persistent memory
Aura Research is an open-source tool that processes raw documents (PDFs, papers, notes, code, 60+ formats) into a structured markdown wiki with backlinked articles, concept pages, and a master index. It compresses everything into a .aura archive optimized for RAG retrieval and runs 100% locally with no data leaving your machine.
Beginner-Friendly Live Build: Your First OpenClaw Agent
The Clawcast hosts a live beginner-friendly build on July 8, showing how to set up an OpenClaw agent with no coding background. Join on Discord or catch the recording on YouTube.
DoomVLM: Open Source Tool for Testing Vision Language Models in Doom Deathmatches
DoomVLM is now open source as a single Jupyter notebook that lets you test vision language models playing Doom via OpenAI-compatible APIs. The tool supports deathmatch modes where up to 4 models can compete, with full configuration options for system prompts, tool descriptions, and sampling parameters.