agentmods.dev

finetune-model

finetune-model is a skill for Claude Code, Codex from NVIDIA/deepops. It costs 40 tokens per session (757 once invoked), scanned A, original, BSD-3-Clause.

A readiness check for fine-tuning an AI model on one scheduled GPU server. It checks the host, cached model inputs, required files, and a pinned software container, but does not train the model.

In plain words
What is it for?
Use it to diagnose whether one DeepOps Slurm GPU node is ready for a fine-tuning job and to identify missing model data or container requirements.
Why use it?
It prevents missing files, unsuitable machines, or unapproved software from being confused with successful fine-tuning, and makes clear that multi-node training is unsupported.

Skill for Claude CodeCodex ✓ vendor

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 python3 scripts/validation/validate_finetune.py --json \.

not rated 1.5krepo +2 yesterday A scan 40 tokens original BSD-3-Clause

Good fit Use it to diagnose whether one DeepOps Slurm GPU node is ready for a fine-tuning job and to identify missing model data or container requirements.

Compare 6 skills from other repositories ↓
View source ↗ NVIDIA/deepops
About the project

DeepOps is a collection of automation tools for deploying and managing compute clusters that use NVIDIA GPUs with Kubernetes or Slurm. It supports environments ranging from full data-center clusters to individual machines needing GPU drivers, Docker, and NVIDIA container support.

NVIDIA/deepops · 1,485 stars · on GitHub

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/NVIDIA/deepops
agentmods
npx agentmods add skills/nvidia/deepops/finetune-model

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 finetune-model

README.md
[![agentmods](https://agentmods.dev/badge/skills/nvidia/deepops/finetune-model/github.svg)](https://agentmods.dev/skills/nvidia/deepops/finetune-model)
Your own site
<a href="https://agentmods.dev/skills/nvidia/deepops/finetune-model"><img src="https://agentmods.dev/badge/skills/nvidia/deepops/finetune-model/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 finetune-model

Your own site · 80×15
<a href="https://agentmods.dev/skills/nvidia/deepops/finetune-model"><img src="https://agentmods.dev/badge/skills/nvidia/deepops/finetune-model.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 40 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 757 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 $0.00040 $0.00757
Opus 5.5 $0.00016 $0.00303
Sonnet 5.5 $0.00008 $0.00151
Haiku 4.5 $0.00004 $0.00076

Measured yesterday against content hash 9f6daf5f88f4, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

finetune-model 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 yesterday.

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/finetune-model/SKILL.md · 63 lines

How it starts

The opening of the file, as written. The whole thing — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Check fine-tuning readiness

This skill checks preparation only. It provides no training recipe. A ready result always has training_validated: false. Multi-node training is unsupported here; do not invent a distributed command or report a successful fine-tune from this check.

Preconditions

  • Read the readiness guide. Run from the repository root as the intended model consumer on the selected compute host, not the login node. The validator checks local host identity against the scheduler record; do not bypass a mismatch.
  • Obtain authorization for the target and read-only scheduler queries. Specify one node and one partition. An IDLE node with an unallocated GPU is required; this conservative check does not accept mixed, draining or flagged nodes.
  • Follow manage-model-cache for an approved shared cache, immutable revision and complete reviewed required-file list. Supported inputs are Hugging Face tokenizer.json plus safetensors weights; list every extra model-specific asset. Indexed weights require every shard.
  • Select a site-reviewed fine-tuning image pinned by digest, using Pyxis syntax registry#repository@sha256:<digest>. Do not use mutable tags, credentials in the reference, or substitute an unreviewed image to get a pass.

Readiness check

Set the variables to reviewed values. For sharded weights, replace the final file argument with model.safetensors.index.json; the validator follows its weight map. Add every additional file needed by the selected model.

python3 scripts/validation/validate_finetune.py --json \
  --node "$NODE" --partition "$PARTITION" \
  --container-image "$TRAINING_IMAGE" \
  --cache-dir "$HF_HUB_CACHE" --repo-id "$MODEL_REPO" --revision "$MODEL_REVISION" \
  --require-file config.json --require-file tokenizer.json \
  --require-file tokenizer_config.json --require-file model.safetensors
Result Next action
Exit 0, status: ready, ok: true Report readiness only, including that container execution and training remain unproven.
Exit 1, status: not_ready Report every errors[] stage. Repair the named prerequisite through its approved procedure; do not drain nodes, install software or download models implicitly.
Exit 2, status: bad_input Correct explicit inputs or unsupported flags using --help. No scheduler commands run for bad input.

Read the full file on GitHub · 63 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. yesterday First seen · 63 lines · 40 tokens per session scan A 9f6daf5f88f4

Subscribe to this mod's changes

finetune-model is a skill published in the GitHub repository NVIDIA/deepops (1,485 stars, last pushed yesterday), licensed BSD-3-Clause. It adds 40 tokens to every session and 757 once invoked, about $0.0002 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 2026-11-06.

Data and AI
Related

finetune-model compared with skills from other repositories

finetune-model next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
finetune-modelNVIDIA/deepopsSkill1.5kyesterdayBSD-3-ClauseA40Claude Code, Codex
agent-platform-model-registrygoogle/skillsSkill22kyesterdayApache-2.0A60Claude Code, Codex
foundry-config-setupmicrosoft/agent-frameworkSkill15kyesterdayMITA65Claude Code, Codex
google-cloud-solution-agentic-analytics-spark-knowledge-cataloggoogle/skillsSkill22kyesterdayApache-2.0A132Claude Code, Codex
training-checkwanshuiyin/Auto-claude-code-research-in-sleepSkill19k3d agoMITA35Claude Code
nemo-automodel-launcher-configNVIDIA/skillsSkill3.9kyesterdayApache-2.0A30Claude Code
finetuningmicrosoft/skillsSkill3.2kyesterdayMITA132Claude Code