runpod-gpu-cloud

runpod-gpu-cloud is a skill for Claude Code, Codex from synthetic-sciences/openscience. It costs 32 tokens per session (750 once invoked), scanned A, original, Apache-2.0.

Safely inspect and operate RunPod resources with runpodctl, live product data, and explicit approval before paid or destructive actions.

Skill for Claude CodeCodex

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.

agentmods
npx agentmods add skills/synthetic-sciences/openscience/runpod
Any agent
npx skills add synthetic-sciences/openscience --skill runpod
Clone the repo
git clone --depth 1 https://github.com/synthetic-sciences/openscience

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 runpod-gpu-cloud

README.md
[![agentmods](https://agentmods.dev/badge/skills/synthetic-sciences/openscience/runpod.svg)](https://agentmods.dev/skills/synthetic-sciences/openscience/runpod)
Your own site
<a href="https://agentmods.dev/skills/synthetic-sciences/openscience/runpod"><img src="https://agentmods.dev/badge/skills/synthetic-sciences/openscience/runpod.svg" alt="Measured on agentmods" height="20"></a>
Per session 32 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 750 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin unknown 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 $0.00032 $0.00750
Opus 5 $0.00016 $0.00375
Sonnet 5 $0.00006 $0.00150
Haiku 4.5 $0.00003 $0.00075

Measured today against content hash d7c6b62089b4, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

runpod-gpu-cloud 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 today.

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.

backend/cli/skills/cloud-compute/runpod/SKILL.md · 56 lines

How it starts

The opening of the file, as written. The whole thing — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.

RunPod GPU Cloud

Use this skill for RunPod identity, Pod, and related compute workflows. RunPod product surfaces and CLI commands evolve; distinguish Pods from Serverless and verify the current command reference for the requested product.

OpenScience credential boundary

  • A key saved in Customize > Compute > RunPod is encrypted control-plane data and is not exported to Bash, Task, notebooks, kernels, plugins, or MCP servers.
  • Use provider_compute with account, list_resources, resource_status, or list_availability for live account, Pod, Pod-detail, and GPU availability reads. OpenScience owns the exact reviewed runpodctl argv.
  • Test connection uses the same boundary for exactly runpodctl user.
  • The saved key is admitted only when Test connection approves a root/admin-managed, non-writable runpodctl executable. A normal user-owned Homebrew or manual install remains credential-only and cannot be used by provider_compute until a managed/native adapter exists.
  • OpenScience updates last_used only after the command succeeds.
  • Never print or persist the key. The saved credential cannot create, start, stop, restart, update, delete, transfer, or change resources; dashboard storage does not authenticate a generic agent shell.

Current CLI contract

runpodctl --help
runpodctl user

Use the installed runpodctl help and current official docs to select the current read-only list/status command, then again before constructing any mutation. Do not reuse remembered Pod create, Serverless, registry, or storage flags.

Operating policy

  1. Confirm the product surface, GPU memory/count, cloud type or reliability needs, region, image, disk/volume, ports, runtime estimate, interruption tolerance, and maximum budget.
  2. Query current inventory and provider-displayed pricing immediately before a recommendation.
  3. Present one recommended configuration and the exact live quoted terms. Label total cost as an estimate.
  4. Get explicit approval before creating, starting, stopping, resizing, terminating, or changing storage or endpoints.
  5. After mutation, retain the resource ID and reconcile with a read-only list/status command. Never blindly retry an ambiguous launch.
  6. Verify the actual workload and requested artifacts; a running Pod or ready endpoint is not proof of scientific success.
  7. Stop idle billable resources. Verify outputs before termination and ask separately before deleting persistent storage.

Read the full file on GitHub · 56 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. today First seen · 56 lines · 32 tokens per session scan A d7c6b62089b4

Subscribe to this mod's changes

runpod-gpu-cloud is a skill published in the GitHub repository synthetic-sciences/openscience (3,432 stars, last pushed today), licensed Apache-2.0. It adds 32 tokens to every session and 750 once invoked, about $0.0002 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 2026-09-03.

Related

Other skills, from other repositories

lambda-labs-gpu-cloud

Reserved and on-demand GPU cloud instances for ML training and inference. Use when you need dedicated GPU instances with simple SSH access, persistent filesystems, or high-performance multi-node clusters for large-scale training.

OpenLAIR/dr-claw · 47 tokens

imaging-data-commons

Query and download public cancer imaging data from NCI Imaging Data Commons. Invoke for any question about IDC collections, cancer imaging datasets, DICOM data access, radiology (CT, MR, PET) or pathology AI training sets, metadata queries, visualization, or license checks — even when the user doesn't explicitly…

K-Dense-AI/scientific-agent-skills · 75 tokens

lab-hardware-cad

Design custom laboratory hardware as parametric build123d models and export fabrication-ready STEP, STL, and DXF files - microfluidic chips and molds, optomechanical mounts and breadboard adapters, cuvette and microplate holders, tube racks, animal-behavior rigs, and 3D-printed instrument fixtures. Use when a research…

K-Dense-AI/scientific-agent-skills · 106 tokens

analytical-method-validation

Plan, execute, and document validation, verification, and transfer of analytical procedures under the governing framework - ICH Q2(R2) and Q14, USP / / , ICH M10 bioanalytical, CLSI EP, or ISO/IEC 17025. Use for HPLC, LC-MS/MS, GC, CE, ICP-MS, dissolution, qNMR, qPCR, NIR, and ligand binding or cell-based assays…

K-Dense-AI/scientific-agent-skills · 281 tokens

diffdock

DiffDock and DiffDock-L molecular docking. Use for protein-small-molecule pose prediction from PDB or sequence plus SMILES/SDF/MOL2, batch docking, virtual screening, and pose-confidence interpretation. Not for binding affinity prediction.

K-Dense-AI/scientific-agent-skills · 51 tokens

anndata

Data structure for annotated matrices in single-cell analysis. Use when working with .h5ad files or integrating with the scverse ecosystem. This is the data format skill—for analysis workflows use scanpy; for probabilistic models use scvi-tools; for population-scale queries use cellxgene-census.

K-Dense-AI/scientific-agent-skills · 63 tokens