A practical guide for installing and using Unsloth, a Python and desktop toolkit for local model inference and training. It covers Core, Studio, and Desktop, with workflows for language, vision, audio, and coding-agent models.

Use it to choose the right Unsloth product, run supervised or preference training, use chat templates, recover checkpoints, train supported models, and check exported model results.

It turns an Unsloth request into a reproducible setup or experiment and avoids treating hardware, model, or release-specific claims as universal guarantees.

unsloth — Skill for Claude Code and Codex by magnus919/agent-skills

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.

Any agent

npx skills add magnus919/agent-skills --skill unsloth

Clone the repo

git clone --depth 1 https://github.com/magnus919/agent-skills

Made for: Claude Code, Codex.

Its marketplace also offers this one on its own, as the plugin unsloth — /plugin install unsloth after adding the marketplace above.

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/skills/magnus919/agent-skills/unsloth/github.svg)](https://agentmods.dev/skills/magnus919/agent-skills/unsloth)

Your own site

<a href="https://agentmods.dev/skills/magnus919/agent-skills/unsloth"><img src="https://agentmods.dev/badge/skills/magnus919/agent-skills/unsloth/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/skills/magnus919/agent-skills/unsloth"><img src="https://agentmods.dev/badge/skills/magnus919/agent-skills/unsloth.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 116 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 2,824 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	$0.00116	$0.02824
Opus 5.5	$0.00046	$0.01130
Sonnet 5.5	$0.00023	$0.00565
Haiku 4.5	$0.00012	$0.00282

Measured 4d ago against content hash 8ecd00347e7a, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

unsloth 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 4d ago.

The scan reads SKILL.md. This mod also ships 12 executable files (scripts/decision_audit.py, scripts/sft_audit.py, scripts/sft_smoke.py, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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/SKILL.md · 214 lines

How it starts

The opening of the file, as written. The whole thing — 214 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Unsloth

Turn an Unsloth request into a reproducible installation, bounded experiment, or verified model artifact. Unsloth provides an optimized Python training stack (Core), a browser interface (Studio), and a native application (Desktop). Capabilities differ by product, backend, model, and release. Read the relevant official page before selecting a new hardware or model path; never promote a vendor speed or minimum-memory claim into a promise about the user's workload.

When not to use

For deciding whether ML, retrieval, or fine-tuning is appropriate, use ml-engineering; return here for Unsloth execution.
For operating exported models in a standalone engine, use llama-cpp or vllm. This skill owns the export and parity checks at that boundary.
For container platform design use platform-engineering; for Docker Compose mechanics use docker-compose. Do not turn this skill into a platform manual.

Start here

Identify the requested surface: Core Python/notebook, Studio web UI, or Desktop. Determine inference, SFT, preference optimization, online RL, or decision-model training, media generation, coding-agent/tool use, or another model-specific task. Default to Core for reproducible coded training, and Desktop/Studio when a GUI is requested.
Discover OS, Python, accelerator/backend, free VRAM/RAM/disk, installed versions, model ID and revision, input format, target context, and output destination. Use existing task context; ask only for unresolved choices that affect feasibility. Run the read-only helper before prescribing packages.
Establish a measurable baseline, held-out dataset, budget, and stop condition before training. Capture these in the run record.
This skill can install software, download weights, consume GPU resources, write checkpoints, expose services, and publish models. Before first mutation:

Confirm the target, scope, and rollback path before acting. Read-only discovery may proceed without confirmation.

Read the full file on GitHub · 214 lines

Files

What ships with it

44 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.

4d ago Changed · +25 lines · +6 tokens per session 8ecd00347e7a
5d ago First seen · 189 lines · 110 tokens per session scan A 68c667bdc8ad

Subscribe to this mod's changes

unsloth is a skill published in the GitHub repository magnus919/agent-skills (133 stars, last pushed 2d ago), licensed MIT. It adds 116 tokens to every session and 2,824 once invoked, about $0.0005 per session on Opus 5.5. 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 2026-10-13.

Data and AI LLM agent-skills agentskills ai-agents automation

unsloth

Getting it into your agent

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

Unsloth

When not to use

Start here

What ships with it

What this file has done since we first saw it

Other skills, from other repositories

map

context-add

cocolean

test

map-diff

map-explain