Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/maystudios/claude-skills/llama-cppnpx skills add maystudios/claude-skills --skill llama-cppgit clone --depth 1 https://github.com/maystudios/claude-skillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/maystudios/claude-skills/llama-cpp)<a href="https://agentmods.dev/skills/maystudios/claude-skills/llama-cpp"><img src="https://agentmods.dev/badge/skills/maystudios/claude-skills/llama-cpp.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00185 | $0.02199 |
| Opus 5 | $0.00093 | $0.01099 |
| Sonnet 5 | $0.00037 | $0.00440 |
| Haiku 4.5 | $0.00018 | $0.00220 |
Grade A, and why
llama-cpp scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
# Query via curl How it starts
The opening of the file, as written. The whole thing — 187 lines — stays where its author put it; the contents beside it link to each section on GitHub.
llama.cpp -- C/C++ LLM Inference Framework Guide
Official Documentation
| Source | URL |
|---|---|
| GitHub Repository | https://github.com/ggml-org/llama.cpp |
| C API Header (llama.h) | https://github.com/ggml-org/llama.cpp/blob/master/include/llama.h |
| C++ RAII Wrappers | https://github.com/ggml-org/llama.cpp/blob/master/include/llama-cpp.h |
| Build Instructions | https://github.com/ggml-org/llama.cpp/blob/master/docs/build.md |
| Server Documentation | https://github.com/ggml-org/llama.cpp/blob/master/tools/server/README.md |
| Quantization Tool | https://github.com/ggml-org/llama.cpp/blob/master/tools/quantize/README.md |
| GGUF Specification | https://github.com/ggml-org/ggml/blob/master/docs/gguf.md |
| Function Calling Docs | https://github.com/ggml-org/llama.cpp/blob/master/docs/function-calling.md |
| Multimodal Docs | https://github.com/ggml-org/llama.cpp/blob/master/docs/multimodal.md |
| Examples Directory | https://github.com/ggml-org/llama.cpp/tree/master/examples |
| HuggingFace GGUF Hub | https://huggingface.co/docs/hub/gguf-llamacpp |
| Llama-Unreal Plugin | https://github.com/getnamo/Llama-Unreal |
What is llama.cpp?
llama.cpp is a pure C/C++ LLM inference engine with minimal dependencies, designed for high-performance local inference across CPUs and GPUs. Key properties:
- MIT licensed, extremely active development (~daily releases, currently b8766+)
- Widest hardware support: NVIDIA (CUDA), AMD (ROCm/Vulkan), Apple (Metal), Intel (SYCL/Vulkan), Qualcomm (OpenCL), ARM, WebGPU
- GGUF model format: single-file, mmap-compatible, 40+ quantization types from 1.5-bit to 16-bit
- Built-in HTTP server: OpenAI-compatible API, Anthropic Messages API, streaming, function calling, multimodal
- Language bindings: Python (llama-cpp-python), Go, Rust, C#, Node.js, Java, Swift, and more
Quick Start
Run a model via server (fastest path)
# Install
brew install llama.cpp # macOS/Linux
winget install llama.cpp # Windows
# Start server with a HuggingFace model
llama-server -hf bartowski/Llama-3.3-70B-Instruct-GGUF:Q4_K_M -ngl 99
# Query via curl
curl http://localhost:8080/v1/chat/completions \
-H "Content-Type: application/json" \
-d '{"messages":[{"role":"user","content":"Hello"}],"temperature":0.8}'
What ships with it
6 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 4d ago First seen · 187 lines · 185 tokens per session scan A 3d0cf6e2a8f9
llama-cpp is a skill published in the GitHub repository maystudios/claude-skills (21 stars, last pushed 19d ago), licensed MIT. It adds 185 tokens to every session and 2,199 once invoked, about $0.0009 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
ue-mcp-native-cpp
Use when writing or modifying native C++ UCLASSes in an Unreal project via ue-mcp. Covers createcppclass → writecppfile → livecodingcompile loop, when to use build vs Live Coding, and the addmoduledependency workflow. Pulls in any time the user asks to write a new native class, add a UPROPERTY, or implement a…
cpp
Use when writing, reviewing, modernizing, building, or debugging C++ - RAII and resource lifetime, smart-pointer ownership, move semantics and the Rule of Zero/Five, target-based CMake with FetchContent, and killing undefined behavior with ASan/UBSan/TSan plus clang-tidy. NOT borrow-checker / Result-Option / cargo…
debug-cuda-kernel-correctness
Guide the agent through a systematic process of isolating, reproducing, and diagnosing correctness errors in CUDA kernels — covering indexing bugs, layout mismatches, synchronization races, reduction errors, numerical drift, and out-of-bounds memory access.
optimize-global-memory-access
Guide the agent through diagnosing and restructuring CUDA global memory access patterns to maximize effective memory bandwidth, covering coalescing requirements, vectorized loads, AoS vs SoA layouts, shared memory staging for non-coalesced patterns, and L2 cache behavior.
write-cuda-gemm-kernel
Guide the agent through designing and implementing a correct, performance-aware CUDA GEMM kernel (C = alpha A B + beta C) for a specific problem configuration, including decisions about tiling strategy, memory hierarchy usage, tensor core eligibility, and when to defer to cuBLAS or CUTLASS instead.
choose-tile-size-and-work-partitioning
Guide the agent through selecting tile sizes and work partitioning strategies for a CUDA or Triton kernel, based on shared memory budget, register pressure, occupancy targets, problem shape, and access pattern.