billus-model-ops

billus-model-ops is a skill for Codex from BillusA1111/billus-model-skill-library. It costs 113 tokens per session (1,254 once invoked), scanned A, original, Apache-2.0.

A repository workflow for engineering and changing machine-learning models, including text, vision-language, and image-generation systems. It first identifies the project’s training or generation framework and active launch path.

In plain words
What is it for?
Use it when working on training, distributed execution, fine-tuning adapters, tokenizers, vision-language connections, diffusion pipelines, image editing, or related model infrastructure.
Why use it?
It helps avoid changing the wrong configuration or code path in an unfamiliar model repository. It keeps changes small and records validation information for other engineers.

Skill for Codex

Written for Codex: agents/openai.yaml present. Also seen: mentions Codex.

Good fit Use it when working on training, distributed execution, fine-tuning adapters, tokenizers, vision-language connections, diffusion pipelines, image editing, or related model infrastructure.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/billusa1111/billus-model-skill-library/billus-model-ops
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 BillusA1111/billus-model-skill-library --skill billus-model-ops
Clone the repo
git clone --depth 1 https://github.com/BillusA1111/billus-model-skill-library

Made for: 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 billus-model-ops

README.md
[![agentmods](https://agentmods.dev/badge/skills/billusa1111/billus-model-skill-library/billus-model-ops/github.svg)](https://agentmods.dev/skills/billusa1111/billus-model-skill-library/billus-model-ops)
Your own site
<a href="https://agentmods.dev/skills/billusa1111/billus-model-skill-library/billus-model-ops"><img src="https://agentmods.dev/badge/skills/billusa1111/billus-model-skill-library/billus-model-ops/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 billus-model-ops

Your own site · 80×15
<a href="https://agentmods.dev/skills/billusa1111/billus-model-skill-library/billus-model-ops"><img src="https://agentmods.dev/badge/skills/billusa1111/billus-model-skill-library/billus-model-ops.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 113 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,254 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00113 $0.01254
Opus 5 $0.00056 $0.00627
Sonnet 5 $0.00023 $0.00251
Haiku 4.5 $0.00011 $0.00125

Measured 10d ago against content hash 194b6a58b303, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

billus-model-ops 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 10d ago.

The scan reads SKILL.md. This mod also ships 3 executable files (scripts/detect_training_stack.py, scripts/new_experiment_note.py, scripts/summarize_training_log.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.

skills/billus-model-ops/SKILL.md · 96 lines

How it starts

The opening of the file, as written. The whole thing — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Billus Model Ops

Overview

Use this skill for the model repos you touch every day: Hugging Face training stacks, DeepSpeed or FSDP scale-up flows, PEFT or QLoRA adaptation, VL wiring, and diffusion-style image generation or editing systems. Start from repository evidence, identify the active framework path, make the smallest viable change, and leave behind validation notes another engineer can trust.

Quick Start

  1. Identify the framework stack.
    • Run python scripts/detect_training_stack.py <repo-root> when the repo is unfamiliar.
    • Confirm the actual launch path with rg -n "accelerate launch|deepspeed|torchrun|Trainer\\(|DiffusionPipeline|LoraConfig|vision_tower|projector|ControlNet" <repo-root>.
  2. Classify the task.
    • Trainer, scheduler, batch size, optimizer, data path: read references/frameworks-hf-accelerate-deepspeed.md
    • LoRA, QLoRA, adapter merge, low-bit finetune: read references/frameworks-peft-and-lowbit.md
    • LLaVA, Qwen-VL, InternVL, projector, image tokens, visual encoder: read references/frameworks-vl-stacks.md
    • diffusers, image edit, inpainting, ControlNet, IP-Adapter, scheduler, VAE: read references/frameworks-diffusers-image.md
    • Before final delivery, always read references/validation-and-release.md
  3. Keep the change bounded.
    • Prefer modifying the existing config or launch surface instead of introducing duplicate knobs.
    • Keep baseline seeds, datasets, eval prompts, and sample grids stable unless the task explicitly changes them.
  4. Validate before handoff.
    • Use the lightest repo-native smoke test that still exercises the changed path.
    • Summarize what was validated, what still needs a full run, and the main rollback lever.

Workflow

1. Map the active stack

Identify:

  • Trainer style: Hugging Face Trainer, raw PyTorch loop, Accelerate custom loop, DeepSpeed launcher, FSDP wrapper, diffusers trainer, or mixed custom code
  • Config surface: argparse, dataclass, YAML, JSON, Hydra, shell scripts, environment variables
  • Model family: decoder-only LLM, encoder-decoder, VL with vision tower plus projector, diffusion or flow image model
  • Runtime topology: single GPU, DDP, ZeRO, FSDP, CPU offload, mixed precision, low-bit adapters

Read the full file on GitHub · 96 lines

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. 10d ago First seen · 96 lines · 113 tokens per session scan A 194b6a58b303

Subscribe to this mod's changes

billus-model-ops is a skill published in the GitHub repository BillusA1111/billus-model-skill-library (11 stars, last pushed 6mo ago), licensed Apache-2.0. It adds 113 tokens to every session and 1,254 once invoked, about $0.0006 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

huggingface-accelerate

Simplest distributed training API. 4 lines to add distributed support to any PyTorch script. Unified API for DeepSpeed/FSDP/Megatron/DDP. Automatic device placement, mixed precision (FP16/BF16/FP8). Interactive config, single launch command. HuggingFace ecosystem standard.

davila7/claude-code-templates · 69 tokens

axolotl

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

davila7/claude-code-templates · 47 tokens

huggingface-accelerate

Simplest distributed training API. 4 lines to add distributed support to any PyTorch script. Unified API for DeepSpeed/FSDP/Megatron/DDP. Automatic device placement, mixed precision (FP16/BF16/FP8). Interactive config, single launch command. HuggingFace ecosystem standard.

OpenLAIR/dr-claw · 69 tokens

axolotl

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

OpenLAIR/dr-claw · 47 tokens

huggingface-accelerate

Simplest distributed training API. 4 lines to add distributed support to any PyTorch script. Unified API for DeepSpeed/FSDP/Megatron/DDP. Automatic device placement, mixed precision (FP16/BF16/FP8). Interactive config, single launch command. HuggingFace ecosystem standard.

synthetic-sciences/openscience · 69 tokens

axolotl

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

synthetic-sciences/openscience · 47 tokens