agentleFS
KrishP147KrishP147/skills/spend-gate/SKILL.md

spend-gate

Skill37 starsChanged 47 days agoMITView on GitHub

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.

  • Installs packages

2 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

2 rules. About 0 are common, 1 is distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Every billable action gets its own gate, every time: estimate → balance → explicit yes → log.

    line 6
  2. Very specific:

    Log: before running, in skilleddocs/spend.md (create with header):

    line 12

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

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):
    | 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 (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.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.