Skip to content
Back to skills

Spend Gate

ASecurity

Gate any billable action (GPU pods/instances, paid APIs or tiers, cloud credits) behind a cost estimate, a live balance check, and an explicit yes for that action. Use before any create/deploy on a paid provider (runpodctl, vultr-cli, aws/gcloud/az, modal, provider MCP create/deploy/run/start/update), any paid API call, or when spend-guard blocks one.

  • 17 stars
  • 0 votes
  • 0 copies
  • 1 view
  • Added October 18, 2026
ai-agentsgoawsapi

Works with

  • cli
  • api
  • mcp

Security analysis

A92/100
  • mediumInstalls packages at runtime which could introduce malicious dependencies

Pro scans all 3 files and shows the line behind each finding

Scanned October 18, 2026

npx -y skills add KrishP147/skills --skill spend-gate --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Spend Gate?

Add the live security badge to your README. It updates with every re-scan.

Security grade badge for Spend Gate
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/krishp147-spend-gate/badge)](https://www.skillsdirectory.com/skills/krishp147-spend-gate)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
SKILL.md
---
name: spend-gate
description: Gate any billable action (GPU pods/instances, paid APIs or tiers, cloud credits) behind a cost estimate, a live balance check, and an explicit yes for that action. Use before any create/deploy on a paid provider (runpodctl, vultr-cli, aws/gcloud/az, modal, provider MCP create/deploy/run/start/update), any paid API call, or when spend-guard blocks one.
---

Every billable action gets its own gate, every time: estimate → balance → explicit yes → log. A budget, a spend cap, or an earlier "go ahead with the plan" is context, not approval.

1. **Classify**: pod/instance creation, paid deploys, MCP create/deploy/run/start/update tools on a paid provider (e.g. job submits, endpoint updates, pod start), per-token or per-request paid APIs. Unsure → treat as billable.
2. **Estimate**: unit price × hours/tokens/requests. Prefer the tool's own quote or dry run; else the provider's pricing page, cited with URL and read date. Remembered prices don't count.
3. **Balance**: the provider's read-only billing/balance call if one exists (e.g. Runpod MCP `list-billing`; it shows spend history, not credit, so say which you got). No free balance read → say so in the gate and ask the user for the balance or to confirm it; never skip this step. Read-only calls only.
4. **Gate**: show the command, unit price + source, estimated total, live balance. Wait for an explicit yes to *this* action, repeats of approved actions included.
5. **Log** before running, in `skilleddocs/spend.md` (create with header):
   ```markdown
   | when (local) | amount | purpose | price source | resource id |
   |---|---|---|---|---|
   ```
   Fill the resource id into the same row once known. A declined gate is logged too: one row, amount 0, purpose starting "declined:". Untracked → exclude `skilleddocs/` per [TRACKING.md](../handoff-auto/TRACKING.md) (it also covers the `pip install .` hazard).
6. **Run**, then for anything that bills while idle (pod, instance, endpoint, volume): give the teardown or auto-stop now, and remind again when the work is done.

Blocked by the spend-guard hook → [HOOK.md](HOOK.md).

Files in this skill

  • HOOK.md2.2 KB
  • README.md4.2 KB
  • SKILL.md2.1 KB

Attribution

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments

Loading comments…

Newsletter

Get the weekly list of safe new skills, and the ones we pulled.