The Token Cost of Shell Commands

You asked your AI coding agent to debug a simple test failure, and it somehow ended up recursively reading your entire .git/objects history. If your API bills are climbing while your agent seemingly just browses your codebase, you aren’t alone. Developers often blame the LLM model choice or a poorly written system prompt. But the …

Coding Agents Just Reopened Your Software Supply Chain Blind Spot

Most organizations spent years hardening their software supply chain. The model is familiar: dependencies flow through a controlled repository, policies determine what is allowed, scanning catches what slips through, and every action is logged for auditability. It works because human developers operate within environments that enforce these rules. AI coding agents break that assumption entirely. …