Claude Code 플러그인
공개 Claude Code 마켓플레이스의 플러그인 7개입니다. 각 플러그인은 함께 설치되는 스킬, 슬래시 명령, 에이전트, 훅 또는 MCP 서버를 묶습니다.
필터와 일치하는 7개의 플러그인을 표시합니다. 필터 초기화
Estimate the floor (self-) cost of a self-hosted LLM token: electricity + hardware amortization, measured on the server. Not the market API price.
opsCapture clean, repeatable screenshots of a GUI desktop app (IDEs, browsers, native apps) on an isolated Xvfb display: drive it with python-Xlib, capture with ImageMagick, annotate with a highlight box, crop or arrow. Never touches the operator's live desktop.
opsPrepare a Linux server with NVIDIA or Intel Arc GPUs for LLM and neural-network workloads: NVIDIA driver + CUDA from the official repo or the in-tree Intel i915/xe driver with distro firmware, Docker Engine with verified GPU access (NVIDIA Container Toolkit or /dev/dri passthrough) as the mandatory base, staged verification gates for both vendors, optional docker-compose presets for vLLM, Infinity, OpenWebUI and Ollama plus Intel Arc stacks (llama.cpp SYCL/Vulkan, Ollama, OpenVINO, vLLM), GPU power limits persisted via systemd, case fans driven by GPU temperature and Intel Arc idle-power fixes (ASPM).
opsRead-only discovery for a fleet harness repository: a POSIX probe sent over ssh collects OS, kernel, CPU, RAM, disks, Docker, NVIDIA and Intel Arc GPUs, addresses, ports, tunnels and DNAT rules; discover.py turns it into the host card after comparing it with the card, render_index.py validates every card and regenerates the host index and an optional self-contained network map.
opsOnboard a server into a fleet harness repository: reach it over ssh with a confirmed host key, discover it read-only with server-discovery, place it in a namespace, write the host card and README, mirror its compose stacks and system configs, add it to the namespace Topology, regenerate the index, and hand a box with an incomplete GPU stack to gpu-server-setup once the user agrees.
opsCheck whether a host or a whole namespace of a fleet harness repository is healthy, read-only: a POSIX pass over boot history, clock, units, disks, OOM, containers, resolvers, ports, NVIDIA and Intel Arc GPUs and PCIe AER, drift against the host card, stacks against the mirror, and functional probes of every service, rolled up into healthy, warming up, degraded, broken or unreachable.
opsDrive a remote Windows machine over RDP from an AI agent: the RDP client runs on an isolated Xvfb display, the operator watches the same screen in a VNC window and can take over by hand, the session survives between agent turns, and lock screens are recovered by an NLA reconnect instead of typing the password.
ops