axolotl

axolotl is a skill for Claude Code, Codex from MilkyWay008/Hermes-OTG. It costs 24 tokens per session (1,186 once invoked), scanned A, a copy of axolotl, MIT.

A guide to Axolotl, a configuration-based tool for fine-tuning language models. It uses YAML files and supports methods such as LoRA, QLoRA, DPO, GRPO, and multimodal training, which combines text with other media.

In plain words
What is it for?
Use it to configure and run language-model fine-tuning, preference training, multimodal training, and distributed jobs across GPUs.
Why use it?
It helps you set up complex model-training jobs through configuration instead of writing the whole training process yourself. It also brings common fine-tuning methods and multi-GPU options into one workflow.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is ./build/all_reduce_perf -b 8 -e 128M -f 2 -g 3.

Good fit Use it to configure and run language-model fine-tuning, preference training, multimodal training, and distributed jobs across GPUs.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/MilkyWay008/Hermes-OTG
agentmods
npx agentmods add skills/milkyway008/hermes-otg/axolotl

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 axolotl

README.md
[![agentmods](https://agentmods.dev/badge/skills/milkyway008/hermes-otg/axolotl/github.svg)](https://agentmods.dev/skills/milkyway008/hermes-otg/axolotl)
Your own site
<a href="https://agentmods.dev/skills/milkyway008/hermes-otg/axolotl"><img src="https://agentmods.dev/badge/skills/milkyway008/hermes-otg/axolotl/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.

agentmods 80×15 button for axolotl

Your own site · 80×15
<a href="https://agentmods.dev/skills/milkyway008/hermes-otg/axolotl"><img src="https://agentmods.dev/badge/skills/milkyway008/hermes-otg/axolotl.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 24 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,186 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 97% copy Near-identical to another mod 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 5.1 $0.00024 $0.01186
Opus 5 $0.00012 $0.00593
Sonnet 5 $0.00005 $0.00237
Haiku 4.5 $0.00002 $0.00119

Measured 8d ago against content hash 180458a8fbe7, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

axolotl 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 8d 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.

Origin

This is a copy

97% identical to axolotl — 2 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

data/skills/mlops/training/axolotl/SKILL.md · 167 lines

How it starts

The opening of the file, as written. The whole thing — 167 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Axolotl Skill

What's inside

Expert guidance for fine-tuning LLMs with Axolotl — YAML configs, 100+ models, LoRA/QLoRA, DPO/KTO/ORPO/GRPO, multimodal support.

Comprehensive assistance with axolotl development, generated from official documentation.

When to Use This Skill

This skill should be triggered when:

  • Working with axolotl
  • Asking about axolotl features or APIs
  • Implementing axolotl solutions
  • Debugging axolotl code
  • Learning axolotl best practices

Quick Reference

Common Patterns

Pattern 1: To validate that acceptable data transfer speeds exist for your training job, running NCCL Tests can help pinpoint bottlenecks, for example:

./build/all_reduce_perf -b 8 -e 128M -f 2 -g 3

Pattern 2: Configure your model to use FSDP in the Axolotl yaml. For example:

fsdp_version: 2
fsdp_config:
  offload_params: true
  state_dict_type: FULL_STATE_DICT
  auto_wrap_policy: TRANSFORMER_BASED_WRAP
  transformer_layer_cls_to_wrap: LlamaDecoderLayer
  reshard_after_forward: true

Pattern 3: The context_parallel_size should be a divisor of the total number of GPUs. For example:

context_parallel_size

Pattern 4: For example: - With 8 GPUs and no sequence parallelism: 8 different batches processed per step - With 8 GPUs and context_parallel_size=4: Only 2 different batches processed per step (each split across 4 GPUs) - If your per-GPU micro_batch_size is 2, the global batch size decreases from 16 to 4

context_parallel_size=4

Pattern 5: Setting save_compressed: true in your configuration enables saving models in a compressed format, which: - Reduces disk space usage by approximately 40% - Maintains compatibility with vLLM for accelerated inference - Maintains compatibility with llmcompressor for further optimization (example: quantization)

save_compressed: true

Pattern 6: Note It is not necessary to place your integration in the integrations folder. It can be in any location, so long as it’s installed in a package in your python env. See this repo for an example: https://github.com/axolotl-ai-cloud/diff-transformer

Read the full file on GitHub · 167 lines

Files

What ships with it

4 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. 8d ago First seen · 167 lines · 24 tokens per session scan A 180458a8fbe7

Subscribe to this mod's changes

axolotl is a skill published in the GitHub repository MilkyWay008/Hermes-OTG (15 stars, last pushed 28d ago), licensed MIT. It adds 24 tokens to every session and 1,186 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. It is 97% identical to axolotl, differing in 2 lines, and is treated as a copy.

Related

Other skills, from other repositories

hunt-llm-ai

Hunt LLM/AI feature bugs — prompt injection, indirect injection, exfiltration viatool-use/markdown, ASCII smuggling, agentic AI security (OWASP Agentic Apps 2026, ASI01-ASI10). Patterns: direct injection ('ignore previous instructions'), indirect injection via documents/web pages/email the model reads, ASCII smuggling…

uphiago/recon-skills · 256 tokens

lijigang-skill

A Chinese-language approach to writing precise, highly structured prompts, sometimes using Lisp-like notation. It combines concise wording, philosophical questioning, and a process for defining roles, conditions, output formats, and revisions.

momozi1996/awesome-ai-persona-skills · 169 tokens

baoyu-skill

A Chinese-language approach to explaining AI tools and writing prompts—instructions that tell an AI what you want. It emphasizes step-by-step teaching, hands-on testing, plain-language technical explanations, and organized knowledge sharing.

momozi1996/awesome-ai-persona-skills · 153 tokens

hf-model-card-research

Extract structured metadata — downloads, likes, benchmark claims, file sizes, author statements — from HuggingFace model cards. Used when the user asks you to "check these models on HF", "pull benchmarks for these variants", or "compare what authors claim.".

AtlasOmnia/donna-starter · 35 tokens

llm-wiki

Build and maintain a Karpathy-style LLM knowledge base — a self-compiling Obsidian markdown wiki where an Agent ingests raw sources, compiles cross-linked concept/entity/summary pages, answers queries against the corpus, lints the graph for health, and audits in-context human feedback filed from Obsidian or the local…

JeanBaissari/llm-wiki-monorepo · 185 tokens

interactive-prompt-analyzer

World-class prompt analyzer v3: multi-modal, predictive, self-improving, context-aware, with real-time cost estimation, counterfactual reasoning, cross-session learning, adversarial testing, and autonomous optimization.

sloemo01/hermes-skills-bundle · 49 tokens