Instructions for deploying and managing vLLM language models on GPU cloud machines through the pi command-line agent interface. vLLM is software that runs language models for serving requests.

Use them to create or configure DataCrunch or RunPod machines, start supported Qwen, GLM, or GPT-OSS models, set tensor parallelism, and interact with the models through pi.

They clarify how to set up GPU pods, share storage, assign GPUs, and configure model serving without conflicting command options or incorrect tool-call settings.

pi-pods — Skill for Claude Code by romiluz13

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 romiluz13/pi-agent-skills --skill pi-pods

Clone the repo

git clone --depth 1 https://github.com/romiluz13/pi-agent-skills

Made for: Claude Code.

Or install pi-skill, the plugin that ships this one along with the rest of its 11 skills.

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/romiluz13/pi-agent-skills/pi-pods/github.svg)](https://agentmods.dev/skills/romiluz13/pi-agent-skills/pi-pods)

Your own site

<a href="https://agentmods.dev/skills/romiluz13/pi-agent-skills/pi-pods"><img src="https://agentmods.dev/badge/skills/romiluz13/pi-agent-skills/pi-pods/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/romiluz13/pi-agent-skills/pi-pods"><img src="https://agentmods.dev/badge/skills/romiluz13/pi-agent-skills/pi-pods.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 86 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 452 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.

Model	Per session	Once invoked
Fable 5.1	$0.00086	$0.00452
Opus 5	$0.00043	$0.00226
Sonnet 5	$0.00017	$0.00090
Haiku 4.5	$0.00009	$0.00045

Measured 10d ago against content hash 3a2bbeb0238a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

pi-pods 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.

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.

pi-skills/pi-pods/SKILL.md · 29 lines

What it actually says

Pi Pods

Grounding

pi-mono/packages/pods/README.md — installation, pod management, model commands, GPU multi-assignment, and pre-defined models.
pi-mono/packages/pods/src/ — CLI commands implementation if needing deeper args validation.

Invariants

Auto-assignment: When running multiple models on the same pod, pi automatically assigns them to different GPUs.
Parameter Ignorance: When passing custom vLLM args with --vllm, the default CLI shortcuts for --memory, --context, and --gpus are ignored.

Workflows

Setup Pod: Use pi pods setup <name> "<ssh>" along with --mount for shared NFS storage (DataCrunch) or network volumes (RunPod).
Start Pre-defined Model: Use pi start <model> --name <name> for known agentic models (Qwen, GLM, GPT-OSS). The tool calling parsers are automatically configured.
Custom vLLM Args: Pass specific settings (e.g. tensor parallelism) using --vllm --tensor-parallel-size <N>.

Anti-patterns

Do not manually construct tool-calling parsers for pre-defined models like Qwen or GLM; pi configures hermes or glm4_moe automatically.
Do not assume models are downloaded redundantly on DataCrunch; emphasize the NFS shared models path (/mnt/hf-models).

Files

What ships with it

1 file 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.

references/CORPUS.md 224 B

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.

10d ago First seen · 29 lines · 0 tokens per session scan A 3a2bbeb0238a

Subscribe to this mod's changes

pi-pods is a skill published in the GitHub repository romiluz13/pi-agent-skills (18 stars, last pushed 4mo ago), licensed MIT. It adds 86 tokens to every session and 452 once invoked, about $0.0004 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.

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

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

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

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…