It organizes the information needed to adapt language models without having to assemble separate guidance for training and deployment.

unsloth-training — Plugin for Claude Code by duyet

unsloth-training

unsloth-training is a plugin for Claude Code from duyet/codex-claude-plugins. Its manifest loads nothing; the 1 skill it bundles cost 45 tokens per session together, scanned A, original, no licence file.

A plugin for fine-tuning large language models with Unsloth using supervised fine-tuning (SFT) or GRPO, a method that trains models with reward-based feedback. It includes dataset preparation, vision models, and model export options.

In plain words

What is it for?: Preparing datasets, fine-tuning text or vision models, using FP8 or Apple Silicon MLX, and exporting models to GGUF or mobile environments.
Why use it?: It organizes the information needed to adapt language models without having to assemble separate guidance for training and deployment.

Written for Claude Code: a Claude Code plugin manifest.

Good fit Preparing datasets, fine-tuning text or vision models, using FP8 or Apple Silicon MLX, and exporting models to GGUF or mobile environments.

Compare 6 plugins from other repositories ↓

Install in Claude Code

/plugin marketplace add duyet/codex-claude-plugins

/plugin install unsloth-training

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/duyet/codex-claude-plugins

Made for: Claude Code.

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/plugins/duyet/codex-claude-plugins/unsloth-training/github.svg)](https://agentmods.dev/plugins/duyet/codex-claude-plugins/unsloth-training)

Your own site

<a href="https://agentmods.dev/plugins/duyet/codex-claude-plugins/unsloth-training"><img src="https://agentmods.dev/badge/plugins/duyet/codex-claude-plugins/unsloth-training/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/plugins/duyet/codex-claude-plugins/unsloth-training"><img src="https://agentmods.dev/badge/plugins/duyet/codex-claude-plugins/unsloth-training.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session not measured What this adds to a session before it is invoked.

When invoked not measured The manifest loads nothing itself; its 1 skill cost 45 tokens a session between them.

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

Origin unknown No closer match found in the catalogue.

Security

Grade A, and why

unsloth-training 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 18d 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.

unsloth-training/.claude-plugin/plugin.json · 13 lines

The source is not reproduced here

No licence file

Read it on GitHub

Contents

What it installs

The manifest is a name and a version. 1 skill travel with it, and installing the plugin installs all of them — 45 tokens a session between them. Each is measured on its own page, and each can be installed alone.

Skill unsloth-training A 45 tokens

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.

18d ago Changed · +2 lines c5f4a765d29d
2mo ago First seen · 11 lines scan A f5c63c63fd71

Subscribe to this mod's changes

unsloth-training is a plugin published in the GitHub repository duyet/codex-claude-plugins (15 stars, last pushed 18d ago), with no licence file. Its token cost is not measured: this kind of file is read by the harness, not the model. 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 2026-09-03.

Data and AI Learning and teaching

unsloth-training next to 6 plugins from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
unsloth-trainingduyet/codex-claude-plugins	Plugin	15	18d ago	none	A	—	Claude Code
anthropic-technical-deep-divecuriositech/some_claude_skills	Plugin	263	yesterday	MIT	A	—	Claude Code
ml-system-design-interviewcuriositech/some_claude_skills	Plugin	263	yesterday	MIT	A	—	Claude Code
training-hubRed-Hat-AI-Innovation-Team/training_hub	Plugin	105	9d ago	Apache-2.0	A	—	Claude Code
sodam-promptsodam-ai/SoDam-Prompt-Eng	Plugin	1	2mo ago	Apache-2.0	A	—	Claude Code
prompt-evaluatorisabela-valonni/prompt-evaluator	Plugin	5	4mo ago	MIT	A	—	Claude Code
calibre-mcpJarzembak/calibremcp	Plugin	0	3mo ago	MIT	A	—	Claude Code