What is maxia-finetune?

Commands for fine-tuning supported large language models on a dataset using Unsloth and RunPod GPUs. Fine-tuning means continuing model training on your own examples so it can better fit a specific task.

Use them to list supported models, request a training quote, check a job's progress and cost, and select output formats such as GGUF, safetensors, merged, or LoRA-only.

They help estimate GPU costs and track training jobs without manually handling each request and status check.

maxia-finetune — Command for Claude Code by majorelalexis-stack

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.

Clone the repo

git clone --depth 1 https://github.com/majorelalexis-stack/maxia

Made for: Claude Code.

Or install maxia-marketplace, the plugin that ships this one along with the rest of its 1 skill, 7 commands, 2 MCP servers.

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.

README.md

[![agentmods](https://agentmods.dev/badge/commands/majorelalexis-stack/maxia/maxia-finetune.svg)](https://agentmods.dev/commands/majorelalexis-stack/maxia/maxia-finetune)

Your own site

<a href="https://agentmods.dev/commands/majorelalexis-stack/maxia/maxia-finetune"><img src="https://agentmods.dev/badge/commands/majorelalexis-stack/maxia/maxia-finetune.svg" alt="Measured on agentmods" height="20"></a>

Per session 23 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 336 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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 5.1	$0.00023	$0.00336
Opus 5	$0.00012	$0.00168
Sonnet 5	$0.00005	$0.00067
Haiku 4.5	$0.00002	$0.00034

Measured 7d ago against content hash b35440a06f02, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

maxia-finetune scanned grade A with 0 findings 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 7d 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.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

commands/maxia-finetune.md · 28 lines

What it actually says

LLM Fine-Tuning as a Service on MAXIA (powered by Unsloth).

If action is 'models' or empty:

Call GET https://maxiaworld.app/api/finetune/models
Display: model ID, HuggingFace ID, VRAM required, recommended GPU, min price

If action is 'quote':

Ask user for: base_model, dataset_rows, epochs
Call POST https://maxiaworld.app/api/finetune/quote with those params
Display: estimated hours, GPU cost, MAXIA markup, total USDC

If action starts with 'status':

Extract job_id from the action string
Call GET https://maxiaworld.app/api/finetune/status/{job_id}
Display: status, progress %, model, cost

Supported models: Llama 3.3 (8B/70B), Qwen 2.5 (7B-72B), Mistral 7B, Gemma 2 (9B/27B), DeepSeek R1 (8B/14B), Phi-4 (14B). Output formats: GGUF, safetensors, merged, LoRA only.

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.

7d ago First seen · 28 lines · 23 tokens per session scan A b35440a06f02

Subscribe to this mod's changes

maxia-finetune is a command published in the GitHub repository majorelalexis-stack/maxia (0 stars, last pushed 2mo ago), licensed MIT. It adds 23 tokens to every session and 336 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Data and AI

music-suno-prompt

Grounded Suno prompt synthesis from local knowledge corpus + persona canon + label canon. No vibes-prompting.

frankxai/Starlight-Intelligence-System · 23 tokens

laravel-ai-sdk

Build AI features with the first-party Laravel AI SDK (Laravel 13+); use the laravel:ai-sdk skill exactly as written.

jpcaparas/superpowers-laravel · 27 tokens

audit-prompt

Evaluate an existing prompt for clarity, effectiveness, and edge cases.

Owl-Listener/ai-design-skills · 13 tokens

develop-image-prompt.eval

Generates a detailed image generation prompt from a document or content description. Good output: a prompt that is specific, visual, non-abstract, includes style/composition/lighting guidance, and is calibrated to the specified dimensions and style options.

davistroy/claude-marketplace · 0 tokens

dare-llm-integration

Integração segura e eficiente com LLMs (Gemini, Claude, OpenAI, Ollama) em projetos DARE.

dewtech-technologies/dare-method · 0 tokens

prompt-create

Create a new prompt following ground rules.

NVZver/claude-marketplace · 10 tokens