agentsclimarketplace

Azure live cost budget action guard

Skill Raishin/vanguard-frontier-agentic/skills/azure/azure-live-cost-budget-action-guard

Curated marketplace of AI skills, agents, and rules for cloud, zero-trust, and compliance-aware engineering - works with Claude Code, Codex, Cursor, Copilot, and more.

Install
npx -y skills add Raishin/vanguard-frontier-agentic --skill azure-live-cost-budget-action-guard

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

  • 18 stars18 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its author says it does

Copied from the file, not written here

Gate Azure budget action changes and GPU/HPC SKU provisioning against approved spend limits, with quota audits and emergency spend-stop playbooks.

SKILL.md

3.0 KB, 528 tokens by cl100k_base, as published. Nobody here has run it

Azure Live Cost Budget Action Guard

Purpose

Act as the guarded live Azure operator for azure-live-cost-budget-action-guard work. Insist on preview evidence before execution and treat ambiguous target or approval state as a stop condition.

When to use

Use this skill when:

  • a cost budget action threshold or notification must be modified for a subscription or management group
  • a GPU or HPC VM SKU scale-up is requested and spend-limit approval is required
  • a runaway cost event is detected and emergency quota reduction or VM deallocation is needed

Lean operating rules

  • Prefer Microsoft Learn documentation through the user's configured documentation MCP; use sampled read-only Azure evidence when available, then sanitized user evidence.
  • Do not execute a live Azure change until subscription, resource group, active principal, and resource ownership are explicit.
  • Prefer what-if, preview, describe, status, dry-run, plan, and rollback evidence before execution.
  • If the request skips preview or rollback design, push back.
  • Never print secrets, access tokens, connection strings, or raw environment values. Summarize sanitized evidence only.
  • Load references only when needed.

References

Load these only when needed:

Response minimum

Return, at minimum:

  • confirmed target subscription, resource group, and principal
  • preflight evidence (what-if diff, status, health check, or plan output)
  • approval status for the proposed mutation
  • rollback posture or explicit statement of what cannot be rolled back
  • post-action verification steps or refusal reason

Keep looking

Skills are one crate of 328,083. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.