agentmods.dev

cost

cost is a command for Claude Code from vast-ai/vast-claude-plugin. It costs 16 tokens per session (575 once invoked), scanned A, original, MIT.

A command that reports current spending on Vast.ai, a service for renting cloud computers with GPUs, along with the account balance, running hourly cost, projected daily cost, and recent charges.

In plain words
What is it for?
Check account credit, calculate the hourly cost of running instances, estimate a 24-hour cost, and review recent charges.
Why use it?
It makes ongoing GPU rental costs visible without checking several account views or manually adding instance rates.

Command for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Part of the vastai plugin — 2 skills, 5 commands shipped together

not rated 3repo 2mo ago A scan 16 tokens original MIT

Good fit Check account credit, calculate the hourly cost of running instances, estimate a 24-hour cost, and review recent charges.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/vast-ai/vast-claude-plugin/cost
View source ↗ vast-ai/vast-claude-plugin
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.

Clone the repo
git clone --depth 1 https://github.com/vast-ai/vast-claude-plugin

Made for: Claude Code.

Or install vastai, the plugin that ships this one along with the rest of its 2 skills, 5 commands.

Wrote 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.

agentmods badge for cost

README.md
[![agentmods](https://agentmods.dev/badge/commands/vast-ai/vast-claude-plugin/cost.svg)](https://agentmods.dev/commands/vast-ai/vast-claude-plugin/cost)
Your own site
<a href="https://agentmods.dev/commands/vast-ai/vast-claude-plugin/cost"><img src="https://agentmods.dev/badge/commands/vast-ai/vast-claude-plugin/cost.svg" alt="Measured on agentmods" height="20"></a>
Per session 16 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 575 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00016 $0.00575
Opus 5 $0.00008 $0.00287
Sonnet 5 $0.00003 $0.00115
Haiku 4.5 $0.00002 $0.00057

Measured 7d ago against content hash 1f7e080517b8, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

cost 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 7d 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.

commands/cost.md · 43 lines

What it actually says

/vast:cost

Report current Vast.ai spend at a glance.

Steps

  1. Account balance. Run:

    vastai show user --raw

    Report credit (current balance) and email. On a 401 with "Two Factor Authentication" in the body, the account has 2FA enabled and no active TFA session — recommend !vastai tfa login --method-type totp --code <CODE> (with ! prefix so the code stays out of the transcript), then retry.

  2. Active spend rate. Run:

    vastai show instances-v1 --raw -a

    -a / --all auto-fetches every page, sidestepping the interactive Fetch next page? (y/N) prompt that otherwise blocks non-interactive sessions even under --raw. (If -a is undesired for some reason, pass --limit <N> instead — read the current per-page cap from vastai show instances-v1 --help.)

    From the response object, sum instances[].dph_total (dollars per hour) across rows whose actual_status is running. Report as $/hr and project a 24h cost.

  3. Recent invoices. Run:

    vastai show invoices-v1 -c --raw --limit <N> --latest-first
    • -c (--charges) is required to select charges (use -i / --invoices for paid invoices).
    • --limit <N> short-circuits the same pagination prompt; read the current cap from vastai show invoices-v1 --help.
    • --latest-first is supported on show invoices-v1 (NOT on show instances-v1 — different flag sets).

    Summarize results[] over the last three months. Group by charge_type (i=instance, v=volume, s=serverless) if the user wants a breakdown.

Notes

  • --raw is required on every call.
  • Use show invoices-v1, not the legacy show invoices.
  • Pagination gotcha (skill rule 9): always pass --limit on show instances-v1 and show invoices-v1. Each command's --help lists its supported flags — they differ.
  • See skills/vastai/SKILL.md § "Account & Billing" for the full billing surface.
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. 7d ago First seen · 43 lines · 16 tokens per session scan A 1f7e080517b8

Subscribe to this mod's changes

cost is a command published in the GitHub repository vast-ai/vast-claude-plugin (3 stars, last pushed 2mo ago), licensed MIT. It adds 16 tokens to every session and 575 once invoked, about $0.0001 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 2026-08-31.

CloudDevOps and cloudFinance and fintech
Related

Other commands, from other repositories

cost-optimize

You are a cloud cost optimization expert specializing in reducing infrastructure expenses while maintaining performance and reliability. Analyze cloud spending, identify savings opportunities, and implement cost-effective architectures across AWS, Azure, GCP, and OCI. Where provider-specific code appears below, adapt…

wshobson/agents · 0 tokens

finops

Create FinOps strategy with cloud cost management, optimization, governance, and forecasting.

tractorjuice/arc-kit · 15 tokens

azure-cost

Azure cost and pricing analysis for a subscription — Advisor cost recommendations, retail pricing lookups, and quota-driven right-sizing signals, scoped to one subscription.

WYRE-AI/msp-claude-plugins · 29 tokens

estimate-cost

Estimate AWS costs for planned infrastructure or analyze current spending.

armanzeroeight/fastagent-plugins · 10 tokens

estimate-gcp-cost

Estimate GCP resource costs and provide optimization recommendations.

armanzeroeight/fastagent-plugins · 9 tokens

cost-optimize

You are a cloud cost optimization expert specializing in reducing infrastructure expenses while maintaining performance and reliability. Analyze cloud spending, identify savings opportunities, and implement cost-effective architectures across AWS, Azure, and GCP.

HermeticOrmus/LibreUIUX-Claude-Code · 0 tokens