Why we built shim-cli

Hi PH, Mertcan here, one of the makers.

shim-cli started with a question we couldn’t answer: what does a coding agent actually send to the model? When Claude Code reads a .env or a customer CSV to debug something, the contents go straight into the request, and you never see that step.

So we built two things. In Claude Code, a local hook masks secrets and personal data in tool results before the model reads them. shim watch shows what a session sent and what it cost. Everything runs on your machine: no account, no telemetry. It’s open source (Apache-2.0).

We launch here on October 18. Until then we’ll post one short thread a day on how it works and where it falls short.

Question for you: before you point an agent at a repo, do you check anything first?