Your AI opens your files.Now you'll know which ones.

Yes, if you build with an AI agent like Claude Code or Codex, on a Mac or on Windows. You don't need to know how to code. You paste one message into your agent, it runs agentwhy for you, and the answer opens as a page on your own computer, in plain words.

It does not work from an AI chat in your browser: a chat can't run anything on your computer.

Yes. It runs only on your computer. There is no account and no sign-up, and nothing is sent anywhere. It shows which file was opened, never what is inside it. If a file holds API keys, the keys are left out before anything is saved, so they never appear in your report.

Change the keys in the file it names, and nothing else. For each key, sign in to the service it belongs to, like your payments or AI account, open the page with your API keys and create a new one. Put the new key where the old one was, then delete the old key. Once it is deleted, whoever saw it can do nothing with it.

Each key takes a couple of minutes. Then tick the file off your list.

agentwhy stops the message before your AI gets it. It tells you which key it found and on which line, and what to do instead: put the key in the file with your API keys, and write its name in your message.

This works in Claude Code and Codex, when agentwhy's warnings in your chat are on. It recognises the keys of common services by their shape. A key it doesn't recognise still goes through.

Some apps name a new chat from your first message, so that message may already have been sent. When that can happen, agentwhy says so, and you change the key.

You can, and it is worth doing. But people keep reporting the same thing in public: they wrote a rule in their agent's instructions to stay away from the file with their keys, and it opened it anyway.

Telling your agent is a rule. agentwhy is a record of what actually happened.

It tells you the same day, not months later when someone else is already using your key. But there are three things it can't do.

• It can't take a file back. Once your agent has opened a file, it is opened. agentwhy tells you which one, so you know what to change.
• Stopping is not a lock. Switched on, it stops the obvious attempts, like a direct request for the file with your API keys. Anything that slips past still shows up in your report, because the report reads what already happened.
• It only sees the agents it works with. Today that is Claude Code and Codex. Work done in any other tool does not show up.

agentwhy reads the saved records your agent keeps as it works. If your agent opens a file in a way those records don't spell out, agentwhy can miss it. For example, from inside a small program your agent writes and runs, through a file name it puts together while working, or through another tool connected to your agent.

Stopping covers the usual ways of opening a file, not every way. When a saved record is incomplete, agentwhy says so.

By default, no. It only reads the saved records your agent already keeps on your computer while it works.

The warnings in your chat and stopping are the optional parts that add anything: a couple of lines in your project. It shows you those exact lines and asks first, and they can be taken out again at any time.

You can. But one afternoon of work can run to thousands of lines, written for machines rather than people, and every helper your agent started on its own keeps a separate file. agentwhy reads all of them and gives you one page.