dstack-prototyping

A prototyping workflow for testing model-serving setups on real hardware with dstack, a tool for running workloads on chosen compute resources.

In plain words
What is it for?
Use it to test and verify a model-serving service, select suitable hardware or backend options, and confirm the model responds through its service URL.
Why use it?
It helps uncover whether the image, model download, command, hardware, and service settings actually work before deploying a long-running service.

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/dstackai/dstack/dstack-prototyping
Any agent
npx skills add dstackai/dstack --skill dstack-prototyping
Clone the repo
git clone --depth 1 https://github.com/dstackai/dstack

Made for: Claude Code, Codex.

Per session 80 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,017 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00080 $0.01017
Opus 5 $0.00040 $0.00508
Sonnet 5 $0.00016 $0.00203
Haiku 4.5 $0.00008 $0.00102

Measured 2d ago against content hash ea5e40395584, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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 2d 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.

skills/dstack-prototyping/SKILL.md · 101 lines

How it starts

The opening of the file, as written. The whole thing — 101 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.

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/ and https://recipes.vllm.ai/models.json
  • SGLang docs: https://docs.sglang.io/ (fetch /llms.txt for the page index)
  • SGLang model recipes: https://docs.sglang.io/cookbook/autoregressive/intro
  • Release notes: https://github.com/vllm-project/vllm/releases and https://github.com/sgl-project/sglang/releases
  • Performance-loop methodology (profiling, benchmark contracts): https://www.lmsys.org/blog/2026-07-02-agent-assisted-sglang-development

Use A Task Before Service

Before submitting a service, start a long-lived task:

Read the full file on GitHub · 101 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. 2d ago First seen · 101 lines · 80 tokens per session scan A ea5e40395584

Subscribe to this mod's changes

dstack-prototyping is a skill published in the GitHub repository dstackai/dstack (2,229 stars, last pushed 4d ago), licensed MPL-2.0. It adds 80 tokens to every session and 1,017 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.

Related

Other skills, from other repositories

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…

leptonai/leptonai · 122 tokens

Oracle ADK Expert

Build production agentic applications on OCI using Oracle Agent Development Kit with multi-agent orchestration, function tools, and enterprise patterns.

frankxai/claude-code-oracle-skills · 29 tokens

mcp-apps-builder

MANDATORY for ALL MCP server work - mcp-use framework best practices and patterns. READ THIS FIRST before any MCP server work, including: Creating new MCP servers Modifying existing MCP servers (adding/updating tools, resources, prompts, widgets) Debugging MCP server issues or errors Reviewing MCP server code for…

Shubhamsaboo/awesome-llm-apps · 139 tokens

project-graveyard

Scans the developer's machine for dead side projects, autopsies each one from its git history (died at the payments wall, killed by a newer project, finished but never shipped), surfaces their personal death patterns, and picks the corpse most worth resurrecting — then helps ship it. Use when the user mentions…

Shubhamsaboo/awesome-llm-apps · 127 tokens

commit-archaeologist

Reconstructs why code exists from local git history, including the introducing commit, later changes, current authors, repeated companion files, and likely intent. Use when the user asks "why does this code exist", "who wrote this function and why", or to "explain the history of this function" before a rewrite…

Shubhamsaboo/awesome-llm-apps · 82 tokens

dependency-doctor

Checks requirements.txt, pyproject.toml, and package.json dependency manifests for surface-level direct-dependency footguns: standard-library shadowing pins, abandoned backports, unpinned dependencies, and obvious intra-manifest conflicts, plus opt-in PyPI yanked releases. Use when the user asks to check a manifest…

Shubhamsaboo/awesome-llm-apps · 115 tokens