A guide for llama.cpp, software that runs compatible language models locally, and GGUF, a model-file format used by it.

Use it to discover Hugging Face models, inspect GGUF files, choose a quantization, and build llama-server or llama-cli commands for local inference.

It helps choose a model file and quantization level that fit available CPU, GPU, RAM, or VRAM instead of guessing.

llama-cpp — Skill by StarryCod

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/starrycod/cogitum/llama-cpp

Any agent

npx skills add StarryCod/cogitum --skill llama-cpp

Clone the repo

git clone --depth 1 https://github.com/StarryCod/cogitum

Made for: Claude Code, Codex.

Per session 18 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 2,512 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 1 finding. Scan, not verified.

Origin original No closer match found 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.

Model	Per session	Once invoked
Fable 5	$0.00018	$0.02512
Opus 5	$0.00009	$0.01256
Sonnet 5	$0.00004	$0.00502
Haiku 4.5	$0.00002	$0.00251

Measured 2d ago against content hash 989057cfcb8a, 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 2d 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

Copies of this mod

3 near-identical copies found in the catalogue:

llama-cpp — 100% identical, 4 lines differ
llama-cpp — 98% identical, 2 lines differ
llama-cpp — 98% identical, 3 lines differ

cogitum/data/skills/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.

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
Open the repo with the llama.cpp local-app view:
- https://huggingface.co/<repo>?local-app=llama.cpp
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
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
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
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>
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.

2d ago First seen · 250 lines · 18 tokens per session scan A 989057cfcb8a

Subscribe to this mod's changes

llama-cpp is a skill published in the GitHub repository StarryCod/cogitum (11 stars, last pushed 3mo ago), licensed MIT. It adds 18 tokens to every session and 2,512 once invoked, about $0.0001 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.

Data and AI LLM Languages agent agentic ai anthropic cli

smoke-test

End-to-end smoke test skill for DeerFlow. Guides through: 1) Pulling latest code, 2) Docker OR Local installation and deployment (user preference, default to Local if Docker network issues), 3) Service availability verification, 4) Health check, 5) Final test report. Use when the user says "run smoke test", "smoke…

bytedance/deer-flow · 0 tokens

image-generation

Use this skill when the user requests to generate, create, imagine, or visualize images including characters, scenes, products, or any visual content. Supports structured prompts and reference images for guided generation.

bytedance/deer-flow · 42 tokens

podcast-generation

Use this skill when the user requests to generate, create, or produce podcasts from text content. Converts written content into a two-host conversational podcast audio format with natural dialogue.

bytedance/deer-flow · 38 tokens

vercel-deploy

Deploy applications and websites to Vercel. Use this skill when the user requests deployment actions such as "Deploy my app", "Deploy this to production", "Create a preview deployment", "Deploy and give me the link", or "Push this live". No authentication required - returns preview URL and claimable deployment link.

bytedance/deer-flow · 69 tokens

zeroclaw

Help users operate and interact with their ZeroClaw agent instance — through both the CLI (zeroclaw commands) and the REST/WebSocket gateway API. Use this skill whenever the user wants to: send messages to ZeroClaw, manage memory or cron jobs, check system status, configure channels or providers, hit the gateway API…

zeroclaw-labs/zeroclaw · 167 tokens

github-issue-triage

Issue triage and lifecycle management agent for ZeroClaw. Use this skill whenever the user wants to: triage open issues, close stale/duplicate/fixed issues, apply labels, run a backlog sweep, enforce the current issue stale policy, or handle a specific issue. Trigger on: 'triage issues', 'issue triage', 'sweep…

zeroclaw-labs/zeroclaw · 140 tokens

llama-cpp