train

train is a skill for Claude Code, Codex from simple-agent-lab/AutoTrainess. It costs 19 tokens per session (333 once invoked), scanned A, original, MIT.

A guide for training language models with LlamaFactory, using supervised fine-tuning or reinforcement learning. Training data is used to produce a model ready for evaluation.

In plain words
What is it for?
It helps run benchmark training, choose between supervised fine-tuning and reinforcement learning, validate runs, and export the trained model.
Why use it?
It keeps model training focused on the method supported by the current evidence and provides a reproducible workflow instead of an improvised one.

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/simple-agent-lab/autotrainess/train
Any agent
npx skills add simple-agent-lab/AutoTrainess --skill train
Clone the repo
git clone --depth 1 https://github.com/simple-agent-lab/AutoTrainess

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 train

README.md
[![agentmods](https://agentmods.dev/badge/skills/simple-agent-lab/autotrainess/train.svg)](https://agentmods.dev/skills/simple-agent-lab/autotrainess/train)
Your own site
<a href="https://agentmods.dev/skills/simple-agent-lab/autotrainess/train"><img src="https://agentmods.dev/badge/skills/simple-agent-lab/autotrainess/train.svg" alt="Measured on agentmods" height="20"></a>
Per session 19 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 333 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. 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.

ModelPer sessionOnce invoked
Fable 5 $0.00019 $0.00333
Opus 5 $0.00010 $0.00167
Sonnet 5 $0.00004 $0.00067
Haiku 4.5 $0.00002 $0.00033

Measured 3d ago against content hash a1f2243f4305, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

train 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 3d ago.

The scan reads SKILL.md. This mod also ships 2 executable files (scripts/install_llamafactory.sh, scripts/run_llamafactory.sh), 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.

autotrainhub/train/SKILL.md · 35 lines

What it actually says

train

Purpose

Run the simplest valid benchmark-oriented training workflow with LlamaFactory, choose the training mode that matches the current stage and evidence, and export a model ready for evaluation.

When to use

  • When training data is ready and the next step is to run model training.
  • When the current stage requires supervised fine-tuning.
  • When current evidence supports reinforcement learning.

Core rules

  • Use hiyouga/LlamaFactory for all training work.
  • Read shared/llamafactory.md before running training.
  • Choose the training mode that matches the current stage and evidence.
  • Keep the workflow minimal and reproducible.
  • Export final_model/ for downstream evaluation.
  • Do not switch to another framework or a custom training loop.

Run caution

Long training jobs are allowed, but should be started deliberately. Prefer a short validation run first unless there is already clear evidence that a long run is necessary.

Workflow

  1. Read shared/llamafactory.md.
  2. Decide whether the current stage requires sft/stage.md or rl/stage.md.
  3. Follow the selected stage document.
  4. Run training through the provided script in scripts/.
  5. Export final_model/ for evaluation.
Files

What ships with it

5 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 · 35 lines · 19 tokens per session scan A a1f2243f4305

Subscribe to this mod's changes

train is a skill published in the GitHub repository simple-agent-lab/AutoTrainess (21 stars, last pushed 1mo ago), licensed MIT. It adds 19 tokens to every session and 333 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 2026-08-30.

Related

Other skills, from other repositories

openmaic-classroom

将 RAG 检索结果、文档块或知识图谱概念转换为 OpenMAIC 互动课程。当用户要求将知识库内容、检索到的文档片段、上传的文档、或知识图谱中的概念批量转换为教学课件/互动课堂时使用此技能。支持纯需求生成、基于 PDF 内容的课程生成、和基于概念图遍历的批量课堂生成。.

Tencent/WeKnora · 102 tokens

openai-docs

Use when the user asks how to build with OpenAI products or APIs and needs up-to-date official documentation with citations, help choosing the latest model for a use case, or model upgrade and prompt-upgrade guidance; prioritize OpenAI docs MCP tools, use bundled references only as helper context, and restrict any…

Haohao-end/openagent · 74 tokens

vllm-model-tutorial

Generate comprehensive Chinese technical tutorial documents for specific vLLM models (e.g., Qwen3-VL, DeepSeek-V3, Llama 4, InternVL3, etc.). Produces deep-dive model walkthrough documents with Mermaid architecture diagrams, comparison tables, input preprocessing flows, forward pass analysis, ViT computation (for…

shen-shanshan/vllm-dev-skills · 246 tokens

learning-visualization-skill

Generate single-file HTML visual explanations for learning and review. Use this skill when the user wants concept maps, process diagrams, principle demos, comparison diagrams, timelines, AI/ML model visualizations, or animated teaching pages that make a topic easier to understand,复习, or present.

mingchen666/Reviva · 64 tokens

ai-engineering-curriculum

Use when structured AI engineering curriculum — 382 skills + 99 prompts across 20 phases covering ML, deep learning, LLMs, agents, and production systems. Use when learning AI, building AI skills,.

oyi77/1ai-skills · 50 tokens

model-fine-tuning

Use when fine-tune LLMs and ML models — LoRA, QLoRA, PEFT, Hugging Face. Dataset prep, training, evaluation, deployment. Use when working with model fine tuning.

oyi77/1ai-skills · 49 tokens