magnus919/agent-skills · llama-cpp/SKILL.md

llama-cpp skillA

llama-cpp is agent-read markdown (skill) from magnus919/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, 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 binding.

Indexed from public GitHub and served as immutable, content-addressed versions. Install it pinned to an exact SHA-256 with the mdr CLI, and every file is verified against the hash recorded here before it reaches your agent. The deterministic audit below grades the latest version, and the same file always earns the same grade.

How to install

Latest version
mdr add magnus919/agent-skills/llama-cpp@git:20260725.86ac280
Exact content
mdr add magnus919/agent-skills/llama-cpp@sha256:e6e06e2f7c0e9dbb

Pin to a label to follow the author's releases, or to a sha256 to freeze the exact bytes forever. Either way the resolved hash is written to mdr.lock, and mdr install reproduces it on any machine.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_orwpi24eavxz2gc7.svg)](https://markdownregistry.com/a/art_orwpi24eavxz2gc7)

0 badge views in 30 days

Versions

versioncommittedcommitsizeaudit
git:20260725.86ac280 latest2026-07-25 86ac280 9,150 BA view · diff
git:20260725.58457b42026-07-25 58457b4 7,964 BA view

Audit of the latest version

A  17 of 17 checks passed. Deterministic, no model, same answer every run.
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (9150 bytes)
  • pass: No zero-width or bidi control characters
  • pass: No instruction hidden inside an HTML comment
  • pass: No link to an exfiltration or paste host
  • pass: No credential-shaped string
  • pass: No instruction to send local credentials anywhere
  • pass: No text hidden with inline styles
  • pass: No prompt-injection phrasing
  • pass: No curl or wget piped into a shell
  • pass: No recursive delete of root, home or parent
  • pass: No instruction to read or print local credentials
  • pass: No base64 blob over 200 characters
  • pass: No link to a raw IP address
  • pass: No script tag

Source

GitHub

magnus919/agent-skills · 84 stars · license MIT · pushed 2026-09-16 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_orwpi24eavxz2gc7
GET https://markdownregistry.com/api/v1/resolve?ref=magnus919/agent-skills/llama-cpp
GET https://markdownregistry.com/api/v1/blob/e6e06e2f7c0e9dbb8c72933c4b73db88488a12e17d3d5b3a669cd3a8470ef7df

Agents talk at modelranch.com: hand yours the instructions there and it joins the network that reads files like this one.