We let an autonomous agent spend real money for a week. The first thing I added wasn't a feature — it was a spending firewall.

A developer built a spending firewall for autonomous agents after observing that retry loops and prompt injections could quietly drain API budgets. The guard, released as a single-file, zero-dependency MIT-licensed tool, survived a prompt-injection test without spending any money. The developer also created a Monte-Carlo runway simulator to help estimate the capital needed for self-funding agents.

I kept giving agents real API keys and budgets, and the scary part was never a bad answer — it was a retry loop or a prompt injection quietly spending money while I wasn't watching. So I wrote a small guard you wrap around any spend: It got prompt-injected in testing and spent $0. One file, zero deps, MIT: https://github.com/Mhad2021/agent-spendguard https://github.com/Mhad2021/agent-spendguard I also built a free Monte-Carlo "runway simulator" to answer how much capital a self-funding agent needs before it breaks even: https://claude.ai/code/artifact/ebeaa8b2-16eb-400a-8100-5e96c17fd922 https://claude.ai/code/artifact/ebeaa8b2-16eb-400a-8100-5e96c17fd922 How are you all handling runaway spend on autonomous agents? Curious what people do beyond a hard token cap.