FinOpsFinOps

Coding-Agent Cloud Waste: How to Find and Contain What Your Agents Leave Running编程智能体的云浪费:如何发现并遏制智能体留下仍在运行的资源

Coding agents create VMs, databases, and deploys mid-task—then sessions end without teardown. A practical FinOps playbook for read-only audit, human-confirmed cleanup, Claude Code/Codex/MCP blind spots, and what --verify can (and cannot) prove.编程智能体会在任务中途创建虚拟机、数据库和部署,然后会话结束却没有拆除。一份实用的 FinOps 实操手册,涵盖只读审计、经人工确认的清理、Claude Code/Codex/MCP 盲区,以及 --verify 能够证明什么、不能证明什么。