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 agentmods add skills/dstackai/dstack/dstack-prototypingnpx skills add dstackai/dstack --skill dstack-prototypinggit clone --depth 1 https://github.com/dstackai/dstackWhat 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 | $0.00080 | $0.01017 |
| Opus 5 | $0.00040 | $0.00508 |
| Sonnet 5 | $0.00016 | $0.00203 |
| Haiku 4.5 | $0.00008 | $0.00102 |
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.
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/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
Use A Task Before Service
Before submitting a service, start a long-lived task:
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.
- 2d ago First seen · 101 lines · 80 tokens per session scan A ea5e40395584
dstack-prototyping is a skill published in the GitHub repository dstackai/dstack (2,229 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.
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…
Oracle ADK Expert
Build production agentic applications on OCI using Oracle Agent Development Kit with multi-agent orchestration, function tools, and enterprise patterns.
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…
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…
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…
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…