Keelmarker records what you asked a coding agent to do, turns it into promises that can be checked, and blocks “done” until the tests prove them. You see what is proven, what is not, and what is running in production.
A simple loop that your agent follows and you can audit.
Before coding starts, the agent records the intent in plain words.
The intent becomes specific statements that either hold or do not.
Each promise points at the tests that prove it. A promise with no test shows as open.
The work cannot be closed until every promise has passing proof.
Agents are fast and confident. Keelmarker is how you stay sure.
The verdict comes from test results tied to a specific commit, not from the agent’s summary.
Packs add the checks that are easy to forget: web security, payments, accounts and passwords, safe delivery.
Record which commit is running, so the verdict describes production and not just a branch.
Accepting a known risk is a human action with a record, never something an agent can do for itself.
Every intent, promise, result and sign-off is kept, so you can see how a decision was made.
Command line, an MCP server and hooks let agents report as they work.
Sign-up is closed while we are small. Leave your email and we will write to you when there is room.