Agent Cost Control Suite
Three skills that put your AI spend under control from every angle. AI Stack Spend Audit cuts the subscriptions you already overpay for; Agent Spend Guardrails caps and audits the real money your agent is allowed to spend; and Token Budget Officer optimizes what each agent run costs in tokens. Built for developers, automation builders, and small teams running agents at volume who want the bill to stop being a surprise. The suite pays for itself the first time it catches one wasted subscription or one runaway run.
Works with every agent that reads SKILL.md — Claude Code, Cursor, Codex CLI, Gemini CLI, GitHub Copilot, Windsurf, OpenClaw, and more.
One payment, lifetime access. 3 skills unlock instantly in your library.
30-day refund guarantee
Instant unlock in your library
Free updates from the creator
What's included
3 skills
Define spending rules for your AI agent — caps, category whitelists, approval thresholds — and audit what it bought or almost bought, with an approve/hold/block verdict per transaction.
Cost-aware execution planning for AI agents — estimate cost-vs-value before expensive steps, propose cheaper paths (cache, summarize once, downshift models), and track spend against a session budget with a PROCEED / OPTIMIZE / DEFER verdict.
List your AI subscriptions and usage; it finds the overlap and returns a cut/keep/downgrade verdict with estimated monthly dollar savings.
See it in action
You say
I'm about to let my agent buy software and cloud services. Set up balanced spend guardrails, then audit these attempts: $20 OpenAI API credits; $55 AWS; $38 Figma (new merchant); $300 AWS single charge; $90 Delta flight.
Your agent does
POLICY (Balanced): per-txn $75 | approval threshold $40 | hard ceiling $250 | monthly cap $500 | categories {software, API credits, cloud, domains} | merchants {OpenAI, AWS, Cloudflare, Namecheap}
VERDICTS | Amount | Category | Merchant | Verdict | Binding rule | Reason | | $20 | API credits | OpenAI | APPROVE | auto band | Whitelisted, under $40 threshold | | $55 | cloud | AWS | HOLD | approval threshold | Whitelisted but >= $40, needs yes | | $38 | software | Figma | HOLD | new merchant | Under threshold but unlisted merchant | | $300 | cloud | AWS | BLOCK | hard ceiling | Exceeds $250 single-txn ceiling | | $90 | travel | Delta | BLOCK | category whitelist | Travel not in scope |
REMEDIATION: Add Figma if intended; split the $300 AWS charge or raise the ceiling deliberately; add a travel category with its own cap if now in scope.
HEADLINE: "1 approved, 2 held for review, 2 blocked — $503 in attempted spend gated; $20 auto-approved."
How to install
Drop the file into your AI Agent. Works with Claude, Cursor, ChatGPT, and 20+ more.