synthetic-sciences/openscience is an AI workbench that carries out scientific research by reading papers, forming hypotheses, writing and running code, conducting experiments, analyzing results, and preparing reports. Researchers use it for work in machine learning, biology, physics, and chemistry with remote or local models. Catalogue add-ons extend its scientific workflows through skills and instructions.
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 synthetic-sciences/openscience --skill vast-aigit clone --depth 1 https://github.com/synthetic-sciences/openscienceWrote 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/synthetic-sciences/openscience/vast-ai)<a href="https://agentmods.dev/skills/synthetic-sciences/openscience/vast-ai"><img src="https://agentmods.dev/badge/skills/synthetic-sciences/openscience/vast-ai/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/synthetic-sciences/openscience/vast-ai"><img src="https://agentmods.dev/badge/skills/synthetic-sciences/openscience/vast-ai.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00034 | $0.00721 |
| Opus 5.5 | $0.00014 | $0.00288 |
| Sonnet 5.5 | $0.00007 | $0.00144 |
| Haiku 4.5 | $0.00003 | $0.00072 |
Grade A, and why
vast-ai-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 1mo 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 — 57 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Vast.ai GPU Cloud
Use this skill for Vast.ai marketplace discovery and instance operations. Offers, reliability attributes, locations, bandwidth, storage, and prices are live marketplace data; query them immediately before recommending anything.
OpenScience credential boundary
- A key saved in Customize > Compute > Vast.ai is encrypted control-plane data and is not exported to agent shells, notebooks, kernels, plugins, or MCP servers.
- Use
provider_computewithaccount,list_resources, orresource_statusfor live account and instance reads. OpenScience selects onlyvastai show user --raw,show instances --raw, or one exactshow instance <id> --rawinvocation. - Test connection uses the same boundary for exactly
vastai show user --raw. - The saved key is admitted only when Test connection approves a root/admin-managed, non-writable
vastaiexecutable. A normal user-owned pip, pipx, or Homebrew install remains credential-only and cannot be used byprovider_computeuntil a managed/native adapter exists. last_usedchanges only after that command succeeds.- Never print or persist the key. The saved credential cannot search/accept offers or start, stop, destroy, copy, or change instances; a generic shell needs independent user-managed authentication.
Current CLI contract
vastai --help
vastai show user --raw
vastai show instances --raw
Use vastai --help and the exact subcommand's --help before constructing marketplace filters or mutations. Do not rely on remembered filter fields or create flags.
Marketplace policy
- Confirm GPU memory/count, disk, bandwidth, reliability, verification requirements, location, runtime, interruption tolerance, and maximum budget.
- Query live offers. Preserve the provider's exact offer ID and quoted terms.
- Recommend one offer and explain the material reliability and interruption tradeoffs. Do not optimize on hourly price alone.
- Get explicit approval before accepting an offer, creating or destroying an instance, changing storage, or interrupting a workload.
- After creation, reconcile by instance ID before retrying any ambiguous request.
- Verify SSH and workload health; do not treat an instance state alone as proof the job succeeded.
- Copy and verify required outputs before destruction. Ask separately before deleting durable volumes or templates.
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.
- 1mo ago First seen · 57 lines · 34 tokens per session scan A a2332d853ddb
vast-ai-gpu-cloud is a skill published in the GitHub repository synthetic-sciences/openscience (4,193 stars, last pushed yesterday), licensed Apache-2.0. It adds 34 tokens to every session and 721 once invoked, about $0.0001 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 2026-09-03.
Other skills, from other repositories
analyze-terraform-plan
You are an expert Terraform plan analyser.
serving-llms-vllm
Use when deploying production LLM APIs, optimizing inference latency/throughput, or serving models with limited GPU memory. Supports OpenAI-compatible endpoints, quantization (GPTQ/AWQ/FP8), and tensor parallelism.
architecture-diagram
Dark-themed SVG architecture/cloud/infra diagrams as HTML.
claw-admin
Claw system administration: service management, IM connections, logs, cron, and workspace diagnostics. Use when the user asks to manage claw services, connect/disconnect IM platforms, view logs, or perform system-wide operations.
x-theme
Change terminal command line prompt theme. Globally manage the display style of all x-cmd interactive components. Supports multiple theme vendors: theme, starship, ohmyposh. Dependency: This is an x-cmd module. Install x-cmd first (see x-cmd skill for installation options). see x-cmd skill for installation.
x-arp
Display ARP cache table with MAC vendor lookup and suspicious entry detection. Supports CSV, TSV, and TUI output. Dependency: This is an x-cmd module. Install x-cmd first (see x-cmd skill for installation options). see x-cmd skill for installation.