Your coding agent is not a developer and you should stop treating it like one A high school student developer built Vow, an open-source (MIT) programming language written in roughly 6,400 lines of JavaScript that requires every function to declare its capabilities — network, filesystem or environment access via uses net, uses fs or uses env — and refuses to run code that exceeds the permissions granted to it. The vow --sandbox command inspects a program before execution and halts it with a SandboxError if any function reaches beyond its declared capabilities, while the language's lack of nulls and exceptions forces agents to handle Result values or fail the build. The project ships with an npm install, an MCP server for Claude Code, and documentation including an llms.txt file at vow-lang.vercel.app. When an agent writes code, it does not have a sense of ethics or a fear of consequences. It has a loop: write, run, read the error, fix. It sees a variable, it reads it. It sees a socket, it opens it. If the language allows the access, the agent will take it. I built Vow as a programming language that treats agents like the machines they are. Every function in Vow must declare its requirements. If it needs to touch the network, files, or environment, it uses net, uses fs, or uses env. If the code does not explicitly declare the capability, the language does not let it run. Before a single line executes, the vow --sandbox command inspects the entire program. If the agent tries to reach beyond the permissions you gave it, the runtime stops the process immediately. bash $ vow --sandbox --allow fs=./data app.vow x SandboxError: needs capabilities the sandbox does not grant env: fn leak declares 'uses env' Nothing was run. The program never starts. The helper function that tried to read your environment variables is dead on arrival. Vow also changes how agents handle mistakes. It has no nulls and no exceptions. Functions return Result values that the agent must handle with match or the ? operator. If the agent ignores a failure, the code refuses to build. When an error does happen, Vow provides a message that acts as a repair instruction. It tells the agent exactly what is wrong, where it happened, and how to fix it. php x TypeError: can't add a num and a str - line 6, col 10 6 | return "Total: " + sum ^^^^^^^^^^^^^^^ Likely fix: convert the number to text first: str sum I am a high school student and I built this because modern languages were never designed for automated agents. The entire language, from the lexer to the compiler, is about 6,400 lines of JavaScript. It is open source under the MIT license and you can find the source at github.com/JakeBurwick/vow. You can install it globally with npm. npm install -g github:JakeBurwick/vow If you use Claude Code, you can add an MCP server to give your agent the tools to guide, check, and run Vow code directly. claude mcp add vow -- vow-mcp You can find the documentation, a playground, and an llms.txt file to help your agents at https://vow-lang.vercel.app https://vow-lang.vercel.app The next time your agent writes a new feature, do not rely on your own ability to catch a leak in a diff. Use a sandbox that stops the agent before it even starts.