llama-cpp plugin
Operate, configure, benchmark, and troubleshoot llama.cpp across CPU, Metal, CUDA, HIP/ROCm, Vulkan, SYCL, and hybrid or multi-GPU systems. Use when installing or building llama.cpp, selecting or inspecting GGUF models, running llama-cli or bounded llama-completion, serving an OpenAI-compatible API with llama-server, tuning memory and performance, or diagnosing backend, context, template, and API failures. Do not use for model training or fine-tuning, general inference-framework selection, llama-cpp-python or other bindings, LlamaIndex, Ollama, or LM Studio operation.
How to install the llama-cpp plugin
Run both commands inside Claude Code. The first adds the marketplace once; the second installs the plugin.
/plugin marketplace add magnus919/agent-skills
/plugin install llama-cpp@magnus-agent-skillsWhat's inside llama-cpp
1 part read from the plugin's own files.
Skills 1
Claude loads it when the task matches- llama-cpp
Operate, configure, benchmark, and troubleshoot llama.cpp across CPU, Metal, CUDA, HIP/ROCm, Vulkan, SYCL, and hybrid or multi-GPU systems. Use when installing or building llama.cpp, selecting or inspecting GGUF models, running llama-cli or bounded llama-completion, serving an OpenAI-compatible API with llama-server, tuning memory and performance, or diagnosing backend, context, template, and API failures. Do not use for model training or fine-tuning, general inference-framework selection, llama-cpp-python or other bindings, LlamaIndex, Ollama, or LM Studio operation.
Using llama-cpp in Claude Code
Skills need no command. Claude reads them when your request matches what they describe.
Update, turn off or remove
- Update the plugin (shell)
- claude plugin update llama-cpp@magnus-agent-skills
- Refresh the marketplace
- /plugin marketplace update magnus-agent-skills
- Turn it off for now
- /plugin disable llama-cpp@magnus-agent-skills
- Remove it
- /plugin uninstall llama-cpp@magnus-agent-skills
Skills in llama-cpp
- llama-cppmagnus919/agent-skills
Operate, configure, benchmark, and troubleshoot llama.cpp across CPU, Metal, CUDA, HIP/ROCm, Vulkan, SYCL, and hybrid or multi-GPU systems. Use when installing or building llama.cpp, selecting or inspecting GGUF models, running llama-cli or bounded llama-completion, serving an OpenAI-compatible API with llama-server, tuning memory and performance, or diagnosing backend, context, template, and API failures. Do not use for model training or fine-tuning, general inference-framework selection, llama-cpp-python or other bindings, LlamaIndex, Ollama, or LM Studio operation.
17 files176stars
llama-cpp plugin questions
How do I install the llama-cpp plugin?
In Claude Code run /plugin marketplace add magnus919/agent-skills, then /plugin install llama-cpp@magnus-agent-skills.
What does the llama-cpp plugin include?
llama-cpp bundles 1 skill.
How do I update or remove the llama-cpp plugin?
Update it with claude plugin update llama-cpp@magnus-agent-skills in your shell, or from the Installed tab of /plugin. Remove it with /plugin uninstall llama-cpp@magnus-agent-skills.