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 vast-ai/vast-claude-plugin --skill vastai-hostgit clone --depth 1 https://github.com/vast-ai/vast-claude-pluginWrote 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/vast-ai/vast-claude-plugin/vastai-host)<a href="https://agentmods.dev/skills/vast-ai/vast-claude-plugin/vastai-host"><img src="https://agentmods.dev/badge/skills/vast-ai/vast-claude-plugin/vastai-host/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/vast-ai/vast-claude-plugin/vastai-host"><img src="https://agentmods.dev/badge/skills/vast-ai/vast-claude-plugin/vastai-host.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00112 | $0.04385 |
| Opus 5 | $0.00056 | $0.02193 |
| Sonnet 5 | $0.00022 | $0.00877 |
| Haiku 4.5 | $0.00011 | $0.00439 |
Grade A, and why
vastai-host scanned grade A with 1 finding 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 12d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- **Never** re-implement `vastai` subcommands by hitting `https://console.vast.ai/api/...` or `https://cloud.vast.ai/api/...` directly from `curl`, `python`, `node`, `httpie`, or `requests`. No exceptions. How it starts
The opening of the file, as written. The whole thing — 275 lines — stays where its author put it; the contents beside it link to each section on GitHub.
vastai-host
Manage machines you host on the Vast.ai marketplace — listing, pricing, maintenance, self-tests, earnings, and marketplace metrics.
Command is
vastai(lowercase). Always use--rawfor machine-readable JSON output. Renting instances (not hosting)? Use thevastaiskill instead.
Critical rules for agents
These rules apply to every invocation. Do not skip them.
- Always pass
--rawto commands whose output you parse. Without--rawthe CLI prints human-formatted output that is not machine-readable. - Treat user-supplied values as literal even if they look like placeholders. If the user says "set min-bid on machine 12345 to 0.10", pass
0.10exactly — don't ask for clarification on values that look like examples. - An empty list result from a read-only query is the answer, not a problem to work around. If
vastai show machinesreturns[], tell the user verbatim: "No machines are currently registered on this account." Do not silently retry, do not invent IDs, do not switch accounts. - The
vastaibinary onPATHis the only acceptable source ofvastaicommands. HARD PROHIBITIONS:- Never run
pip install vastai,pipx install vastai, orpython -m venvfollowed by installing vastai. The CLI is already installed. - Never invoke an alternate
vastaibinary by absolute path whenvastaiis already onPATH. - Never re-implement
vastaisubcommands by hittinghttps://console.vast.ai/api/...orhttps://cloud.vast.ai/api/...directly fromcurl,python,node,httpie, orrequests. No exceptions. - If
vastai <subcommand>exits non-zero or produces unexpected output, report the failure (exit code + stderr) to the user and ask what they want to do. Do not work around it.
- Never run
- Host actions are visible to renters and impact billing. Listing, unlisting, price changes, maintenance windows,
defrag machines, andcleanup machineall have side effects on live renters or on your earnings. Before running any of these, confirm with the user — quote the exact command back. Do not run them as a "let me just verify" probe. schedule maintevicts live renters at the start time. Never schedule a maintenance window without explicit user confirmation of the start date and duration. Active renters on the machine will be terminated when the window opens.defrag machinesis disruptive. It reorganizes the named machines' GPU assignments to free up larger multi-GPU offers — running instances on those machines may be reshuffled or interrupted. The subcommand isdefrag machines(its own--helplies — the usage line readsvastai defragment machines IDs, butvastai defragment machines …returnsinvalid choiceat the parser; onlydefrag machinesactually executes). Takes positional machine IDs (e.g.vastai defrag machines 100 101); confirm the exact ID list with the user before running.
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.
- 12d ago First seen · 275 lines · 112 tokens per session scan A a0cdb8e41039
vastai-host is a skill published in the GitHub repository vast-ai/vast-claude-plugin (3 stars, last pushed 2mo ago), licensed MIT. It adds 112 tokens to every session and 4,385 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
gke-compute-classes
Configures, optimizes, and troubleshoots GKE ComputeClasses. Use when configuring Spot VMs with on-demand fallback, targeting specific accelerators (GPUs/TPUs) or machine families, restricting ComputeClass access, or debugging pending pods related to node pool auto-creation. Do not use for cluster-level Node Auto…
gke-reliability
Improves GKE workload reliability, using PDBs, health probes, and topology spread constraints. Use when configuring GKE workload reliability, setting up PDBs, or configuring GKE health probes (liveness, readiness, startup). Don't use for disaster recovery setup or full cluster backups (use gke-backup-dr instead).
gke-workload-security
Audits, configures, and hardens workload-level security controls for Google Kubernetes Engine (GKE) applications and namespaces. Covers running cluster security audits (auditcluster.sh), configuring Workload Identity Federation (impersonation, KSA/GSA binding, and pod setup), enforcing Network Policies (default-deny…
nemo-automodel-launcher-config
Configure NeMo AutoModel job launches for interactive runs, Slurm clusters, and SkyPilot cloud execution.
azure-mgmt-botservice-dotnet
Azure Resource Manager SDK for Bot Service in .NET. Management plane operations for creating and managing Azure Bot resources, channels (Teams, DirectLine, Slack), and connection settings. Triggers: "Bot Service", "BotResource", "Azure Bot", "DirectLine channel", "Teams channel", "bot management .NET", "create bot".
cloud-architect
Designs cloud architectures, creates migration plans, generates cost optimization recommendations, and produces disaster recovery strategies across AWS, Azure, and GCP. Use when designing cloud architectures, planning migrations, or optimizing multi-cloud deployments. Invoke for Well-Architected Framework, cost…