dstack is a control plane that provisions and coordinates GPU computing for machine-learning development, training, inference, and agent workloads across cloud providers, Kubernetes, and on-premises clusters. It is used by teams running workloads on NVIDIA, AMD, Google TPU, or Tenstorrent hardware. The catalogue add-ons operate dstack through its CLI, API, or server workflow.
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.
npx skills add dstackai/dstack --skill dstack-prototypinggit clone --depth 1 https://github.com/dstackai/dstackWrote 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.
[](https://agentmods.dev/skills/dstackai/dstack/dstack-prototyping)<a href="https://agentmods.dev/skills/dstackai/dstack/dstack-prototyping"><img src="https://agentmods.dev/badge/skills/dstackai/dstack/dstack-prototyping/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.
<a href="https://agentmods.dev/skills/dstackai/dstack/dstack-prototyping"><img src="https://agentmods.dev/badge/skills/dstackai/dstack/dstack-prototyping.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Rogue Agent · line 72 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
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 | $0.00080 | $0.01446 |
| Opus 5.5 | $0.00032 | $0.00578 |
| Sonnet 5.5 | $0.00016 | $0.00289 |
| Haiku 4.5 | $0.00008 | $0.00145 |
Grade A, and why
dstack-prototyping 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 17d 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.
How it starts
The opening of the file, as written. The whole thing — 134 lines — stays where its author put it; the contents beside it link to each section on GitHub.
dstack Prototyping
Use /dstack for CLI commands, YAML fields, apply/attach behavior, service URLs,
and other dstack syntax. This skill explains how to use dstack runs while the
model-serving configuration is still unknown.
Goal
Find a working dstack service configuration for the requested model.
Before submitting a service, use a task on real hardware to test the serving image, install/runtime assumptions, model download, cache path, command, port, launch flags, resources, env vars, backend/fleet choice, and local model request. Then submit the same configuration as a service and verify the model through the dstack service URL.
Choose Where To Run
Pick the offer whose hardware best fits the goal at hand. Only when several offers fit comparably, choose a VM-based backend, an SSH fleet, or a Kubernetes fleet: they support idle instances and/or instance volumes, so later runs reuse the provisioned/idle instance or instance volumes for caching model weights (and possibly other writes), while container-based backends start clean on every run.
Fetch https://dstack.ai/docs/concepts/backends.md and classify backends
from the fetched document, not from memory.
If the intention is to use PD disaggregation, the fleet must use placement: cluster. Since PD disaggregation implies running a router, unlike workers that must run on GPUs, the router normally should run on a CPU instance. Use dstack fleet to see existing fleets and dstack fleet get <fleet name> --json to inspect a specific fleet.
Check Serving Sources
Check serving-framework sources early enough to choose the image, command, launch flags, resources, cache paths, request format, and expected model behavior.
For vLLM and SGLang, use these as credible sources:
- vLLM recipes and model index:
https://recipes.vllm.ai/andhttps://recipes.vllm.ai/models.json - SGLang docs:
https://docs.sglang.io/(fetch/llms.txtfor the page index) - SGLang model recipes:
https://docs.sglang.io/cookbook/autoregressive/intro - Release notes:
https://github.com/vllm-project/vllm/releasesandhttps://github.com/sgl-project/sglang/releases - Performance-loop methodology (profiling, benchmark contracts):
https://www.lmsys.org/blog/2026-07-02-agent-assisted-sglang-development
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.
- 17d ago Changed · +14 lines f11387e72db4
- 1mo ago Changed · +19 lines ba03e0cddb37
- 1mo ago First seen · 101 lines · 80 tokens per session scan A ea5e40395584
dstack-prototyping is a skill published in the GitHub repository dstackai/dstack (2,284 stars, last pushed today), licensed MPL-2.0. It adds 80 tokens to every session and 1,446 once invoked, about $0.0003 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 2026-08-30.
Other skills, from other repositories
skypilot-multi-cloud-orchestration
Multi-cloud orchestration for ML workloads with automatic cost optimization. Use when you need to run training or batch jobs across multiple clouds, leverage spot instances with auto-recovery, or optimize GPU costs across providers.
lepton-cli
Operate NVIDIA DGX Cloud Lepton through the globally installed lep CLI. Use when the user asks to inspect or manage Lepton workspaces, endpoints/deployments, dev pods, batch jobs, fine-tuning jobs, Ray clusters, Slurm clusters, Dynamo endpoints, storage, secrets, nodes, ingress, templates, logs, authentication, or…
guardrails-developer-create-guardrails
Helps developers create a NeMo Guardrails configuration for an LLM application. Use when users want to build, scaffold, configure, test, or iterate on input, output, retrieval, dialog, execution, Colang, or catalog-based guardrails. Trigger keywords - create guardrails, build guardrails, scaffold config, write rails…
skypilot-multi-cloud-orchestration
Multi-cloud orchestration for ML workloads with automatic cost optimization. Use when you need to run training or batch jobs across multiple clouds, leverage spot instances with auto-recovery, or optimize GPU costs across providers.
skypilot-multi-cloud-orchestration
Multi-cloud orchestration for ML workloads with automatic cost optimization. Use when you need to run training or batch jobs across multiple clouds, leverage spot instances with auto-recovery, or optimize GPU costs across providers.
skypilot-multi-cloud-orchestration
Multi-cloud orchestration for ML workloads with automatic cost optimization. Use when you need to run training or batch jobs across multiple clouds, leverage spot instances with auto-recovery, or optimize GPU costs across providers.