llama-cpp

llama-cpp is a skill for Claude Code, Codex from perasyudha/Nyxora. It costs 18 tokens per session (2,513 once invoked), scanned A, a copy of llama-cpp, MIT.

A way to run language models locally with llama.cpp using GGUF model files, including on CPUs, Apple Silicon and several types of graphics cards.

In plain words
What is it for?
Use it to discover compatible Hugging Face models, select a compressed model version for your RAM or graphics memory, and run a local command-line tool or server.
Why use it?
It helps you choose a model file that fits your available memory and build the command needed to run it without sending prompts to a hosted service.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/perasyudha/nyxora/llama-cpp
Any agent
npx skills add perasyudha/Nyxora --skill llama-cpp
Clone the repo
git clone --depth 1 https://github.com/perasyudha/Nyxora

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for llama-cpp

README.md
[![agentmods](https://agentmods.dev/badge/skills/perasyudha/nyxora/llama-cpp.svg)](https://agentmods.dev/skills/perasyudha/nyxora/llama-cpp)
Your own site
<a href="https://agentmods.dev/skills/perasyudha/nyxora/llama-cpp"><img src="https://agentmods.dev/badge/skills/perasyudha/nyxora/llama-cpp.svg" alt="Measured on agentmods" height="20"></a>
Per session 18 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,513 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. Scan, not verified.
Origin 100% copy Near-identical to another mod in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00018 $0.02513
Opus 5 $0.00009 $0.01256
Sonnet 5 $0.00004 $0.00503
Haiku 4.5 $0.00002 $0.00251

Measured 3d ago against content hash e4c5af2438d0, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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 3d 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.

curl http://localhost:8080/v1/chat/completions \
Origin

This is a copy

100% identical to llama-cpp — 4 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

packages/core/playbooks/mlops/inference/llama-cpp/SKILL.md · 250 lines

How it starts

The opening of the file, as written. The whole thing — 250 lines — stays where its author put it; the contents beside it link to each section on GitHub.

llama.cpp + GGUF

Use this skill for local GGUF inference, quant selection, or Hugging Face repo discovery for llama.cpp.

When to use

  • Run local models on CPU, Apple Silicon, CUDA, ROCm, or Intel GPUs
  • Find the right GGUF for a specific Hugging Face repo
  • Build a llama-server or llama-cli command from the Hub
  • Search the Hub for models that already support llama.cpp
  • Enumerate available .gguf files and sizes for a repo
  • Decide between Q4/Q5/Q6/IQ variants for the user's RAM or VRAM

Model Discovery workflow

Prefer URL workflows before asking for hf, Python, or custom scripts.

  1. Search for candidate repos on the Hub:
    • Base: https://huggingface.co/models?apps=llama.cpp&sort=trending
    • Add search=<term> for a model family
    • Add num_parameters=min:0,max:24B or similar when the user has size constraints
  2. Open the repo with the llama.cpp local-app view:
    • https://huggingface.co/<repo>?local-app=llama.cpp
  3. Treat the local-app snippet as the source of truth when it is visible:
    • copy the exact llama-server or llama-cli command
    • report the recommended quant exactly as HF shows it
  4. Read the same ?local-app=llama.cpp URL as page text or HTML and extract the section under Hardware compatibility:
    • prefer its exact quant labels and sizes over generic tables
    • keep repo-specific labels such as UD-Q4_K_M or IQ4_NL_XL
    • if that section is not visible in the fetched page source, say so and fall back to the tree API plus generic quant guidance
  5. Query the tree API to confirm what actually exists:
    • https://huggingface.co/api/models/<repo>/tree/main?recursive=true
    • keep entries where type is file and path ends with .gguf
    • use path and size as the source of truth for filenames and byte sizes
    • separate quantized checkpoints from mmproj-*.gguf projector files and BF16/ shard files
    • use https://huggingface.co/<repo>/tree/main only as a human fallback
  6. If the local-app snippet is not text-visible, reconstruct the command from the repo plus the chosen quant:
    • shorthand quant selection: llama-server -hf <repo>:<QUANT>
    • exact-file fallback: llama-server --hf-repo <repo> --hf-file <filename.gguf>
  7. Only suggest conversion from Transformers weights if the repo does not already expose GGUF files.

Read the full file on GitHub · 250 lines

Files

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.

Changes

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.

  1. 3d ago First seen · 250 lines · 18 tokens per session scan A e4c5af2438d0

Subscribe to this mod's changes

llama-cpp is a skill published in the GitHub repository perasyudha/Nyxora (5 stars, last pushed 3d ago), licensed MIT. It adds 18 tokens to every session and 2,513 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). It is 100% identical to llama-cpp, differing in 4 lines, and is treated as a copy.

Related

Other skills, from other repositories

hive-mcp

Use this skill when the user wants to install, configure, connect, verify, or debug Hive MCP in an AI client — Claude, ChatGPT/OpenAI, Grok, Cursor, Windsurf, VS Code, Gemini CLI, or Codex — including OAuth browser sign-in, headless API-key fallback, missing tools, 401/auth errors, and hosted-vs-stdio questions. For…

hive-intel/hive-sdk · 106 tokens

hive-defi-research

Use this skill when the user asks about DeFi protocol metrics — TVL, fees, revenue, yields, APY, stablecoin supply, bridge volume, or chain-level DeFi totals — or wants protocols compared ("Aave vs Compound", "top protocols by TVL", "best stablecoin yields"). Use it whenever the answer needs current protocol-level…

hive-intel/hive-sdk · 106 tokens

hive-dex-pool-analysis

Use this skill when the user asks about a DEX pool or trading pair — liquidity depth, recent swaps/trades, OHLCV candles, trending pools, fee tiers, or token-level DEX flow on a chain — including "how deep is the X/Y pool", "what's trading on Uniswap", or a pasted pair address. For CEX prices, order books, and funding…

hive-intel/hive-sdk · 104 tokens

hive-market-research

Use this skill for any live crypto market question — prices, 24h moves, liquidity, exchange/venue data, OHLC candles, order books, tickers, funding rates, derivatives, trading context — even casual asks like "what's BTC at" or "is ETH pumping". Use it whenever the answer needs current market numbers instead of memory.…

hive-intel/hive-sdk · 109 tokens

hive-network-infrastructure

Use this skill when the user asks about chain state or transaction plumbing — gas prices, blocks, transaction receipts and status ("did my tx go through"), event logs, supported networks, fee data, or RPC diagnostics. Use it whenever the answer needs current chain-level evidence. For wallet holdings use…

hive-intel/hive-sdk · 81 tokens

hive-nft-research

Use this skill when the user asks about NFT collections or assets on EVM chains — ownership, metadata, traits, floor prices, sales, rarity, spam/authenticity checks — like "what's the floor on this collection", "who owns this NFT", "is this collection spam". Use it whenever the user needs current NFT evidence rather…

hive-intel/hive-sdk · 102 tokens