A set of instructions and tools for managing RunPod GPU servers and running large-language-model fine-tuning experiments remotely.

Use it to create and inspect approved RunPod pods, manage volumes, and run or monitor fine-tuning experiments.

It provides a defined process for checking training work and managing the required GPU resources while avoiding unrelated resources.

runpod — Skill for Claude Code and Codex by beyarkay

Install

Getting it into your agent

There is no command for this one: it runs only inside a plugin, and the catalogue could not identify which plugin ships it. The source is linked below.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/beyarkay/claude-skills/runpod/github.svg)](https://agentmods.dev/skills/beyarkay/claude-skills/runpod)

Your own site

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

Per session 43 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,736 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 1 finding. 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	$0.00043	$0.01736
Opus 5	$0.00022	$0.00868
Sonnet 5	$0.00009	$0.00347
Haiku 4.5	$0.00004	$0.00174

Measured 9d ago against content hash 2070694fb6d6, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

runpod scanned grade A with 1 finding 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 9d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl -s "https://api.wandb.ai/graphql" \

runpod/SKILL.md · 178 lines

How it starts

The opening of the file, as written. The whole thing — 178 lines — stays where its author put it; the contents beside it link to each section on GitHub.

RunPod Remote Training

Use this skill to manage RunPod GPU infrastructure and run LLM fine-tuning experiments on remote GPUs from the local machine.

Safety Rules (MANDATORY)

NEVER touch pods not created by us. Other people's pods exist on this account.
All resources must have -boyd- in the name
Confirm with user before any deletion (pods, volumes)
When listing pods, only act on pods with -boyd- in the name

Setup

# Load API keys
source /Users/brk/projects/mats/.env

# Load helper functions (rp_status, rp_train, rp_ssh_cmd, etc.)
source /Users/brk/projects/mats/runpod-testing/scripts/runpod-ctl.sh

# SSH wrapper (handles key, host checking, timeouts)
PSS=/Users/brk/projects/mats/runpod-testing/scripts/pod-ssh.sh

Common Operations

Check current status

source /Users/brk/projects/mats/.env
source /Users/brk/projects/mats/runpod-testing/scripts/runpod-ctl.sh
rp_status

Create a pod

# Use existing volume: vol-boyd-test (id=2kve3ufpe3, dc=US-TX-3)
runpodctl create pod \
  --name 'pod-boyd-TASKNAME' \
  --gpuType 'NVIDIA GeForce RTX 4090' \
  --gpuCount 1 \
  --imageName 'beyarkay/mats-training:latest' \
  --containerDiskSize 20 \
  --volumePath /workspace \
  --networkVolumeId '2kve3ufpe3' \
  --secureCloud --startSSH --ports '22/tcp'

After creation, get SSH info:

POD_ID="<from create output>"
rp_get_ssh_info "$POD_ID"
# Returns: IP PORT

Then write the SSH info to scripts/pod-connection.env:

echo "POD_HOST=<IP>" > /Users/brk/projects/mats/runpod-testing/scripts/pod-connection.env
echo "POD_PORT=<PORT>" >> /Users/brk/projects/mats/runpod-testing/scripts/pod-connection.env

SSH into pod

PSS=/Users/brk/projects/mats/runpod-testing/scripts/pod-ssh.sh
$PSS "hostname && nvidia-smi"

Copy files to pod

$PSS --scp /Users/brk/projects/mats/elicitation /workspace/mats-boyd/elicitation
$PSS --scp /Users/brk/projects/mats/.env /workspace/.env-boyd

Read the full file on GitHub · 178 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.

9d ago First seen · 178 lines · 43 tokens per session scan A 2070694fb6d6

Subscribe to this mod's changes

runpod is a skill published in the GitHub repository beyarkay/claude-skills (2 stars, last pushed 1mo ago), licensed MIT. It adds 43 tokens to every session and 1,736 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Cloud Data and AI DevOps and cloud

tensorrt-llm

High-throughput LLM inference on NVIDIA GPUs.

NousResearch/hermes-agent · 18 tokens

google-cloud-solution-guided-gke-ai-migration

Guides the migration of existing AI workloads (Cloud Run, Gemini API, Gemini Enterprise Agent Platform) to self-hosted GKE inference using gcloud and kubectl. Use when the user has an existing AI inference workload (on Cloud Run, the Gemini API, Gemini Enterprise Agent Platform, or a custom VM) and wants to move it to…

google/skills · 157 tokens

agent-platform-tuning

Agent Platform Model Tuning. Use when you need to fine-tune open models or Gemini models using Agent Platform infrastructure. Don't use for model training outside Agent Platform, model deployment to endpoints (use agent-platform-deploy), or managing serving endpoints (use agent-platform-endpoint-management).

google/skills · 64 tokens

modal

Modal is a serverless cloud platform for running Python on demand, including on-demand GPUs. Use when deploying or serving AI/ML models, running GPU-accelerated workloads (training, fine-tuning, inference), serving web endpoints, scheduling batch jobs, or scaling Python code to cloud containers with the Modal SDK.

K-Dense-AI/scientific-agent-skills · 65 tokens

gke-inference

Deploys and optimizes AI/ML inference workloads on GKE, using GPUs, TPUs, and model servers. Use when deploying GKE inference servers, configuring GKE GPU resources for inference, or deploying LLMs on GKE. Don't use for generic batch jobs or HPC task queues (use gke-batch-hpc instead).

google/skills · 74 tokens

agent-platform-endpoint-management

Manages Agent Platform serving endpoints. Use when you need to create, list, describe, update, or delete serving endpoints for model deployment on Agent Platform. Also use when troubleshooting endpoint permission, quota, or resource busy errors. Don't use for deploying models to endpoints or for running model…