tdimino/claude-code-minoan · skills/integration-automation/llama-cpp/SKILL.md

llama-cpp skillA

llama-cpp is agent-read markdown (skill) from tdimino/claude-code-minoan: Run GGUF models directly, load LoRA adapters, benchmark inference speed, and serve models via llama-server using llama.cpp. Includes Qwen 3.5 serve scripts (9B dense + F16, 35B MoE) with asymmetric KV cache and thinking mode. Secondary to Ollama; use when needing direct model control or LoRA hot-loading. Triggers on 'llama.cpp', 'GGUF', 'LoRA adapter', 'benchmark inference', 'llama-server'..

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 tdimino/claude-code-minoan/llama-cpp@git:20260416.4e43d41
Exact content
mdr add tdimino/claude-code-minoan/llama-cpp@sha256:3694828170edb027

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_hfdvgsvwndo4hs44.svg)](https://markdownregistry.com/a/art_hfdvgsvwndo4hs44)

0 badge views in 30 days

Versions

versioncommittedcommitsizeaudit
git:20260416.4e43d41 latest2026-04-16 4e43d41 5,683 BA view · diff
git:20260302.00067a32026-03-02 00067a3 5,692 BA view · diff
git:20260301.c2df5aa2026-03-01 c2df5aa 4,707 BA view · diff
git:20260205.4f7b49b2026-02-05 4f7b49b 4,136 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 (5683 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

tdimino/claude-code-minoan · 41 stars · license MIT · pushed 2026-09-14 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_hfdvgsvwndo4hs44
GET https://markdownregistry.com/api/v1/resolve?ref=tdimino/claude-code-minoan/llama-cpp
GET https://markdownregistry.com/api/v1/blob/3694828170edb0279be0c2460cf03a06d6b3de37982607ad5c832c93d3c25e6f

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