My coding agent kept telling me a ticket was done when it wasn't. Sometimes the test was green but would have been green anyway. Sometimes the fix broke something else.
So for the Kane CLI hackathon I built Proven: a ticket board where a ticket closes only after Kane CLI watched its frozen test fail before the change and pass after it.
Red first
A person writes the ticket and a plain-English Kane test. Proven freezes the test before any work starts: it commits the ticket and the test, then a lock that names that commit. Then Kane has to fail the test on the app as it is. If the test already passes, it proves nothing, and Proven says so.
The first thing I did was test how Kane fails. With my server down, an "open the page" step passed on Chrome's error page and the next step failed, so an outage looked exactly like a real bug. Now step 1 of every frozen test checks a landmark, and Proven checks that the app answers before it starts Kane. An outage is "did not run", never red.
One command closes the loop
After red, proven loop hands the ticket to the coding agent, Claude Code running headless. The agent's only way to say done is proven done. Proven serves a snapshot of the change and runs Kane on the frozen test:
- a fail goes back to the agent with the failing step and Kane's own words
- a pass commits exactly what Kane judged, then a receipt that links red, green and the test's hash
After that, the loop reruns every closed ticket with fresh Kane runs.
What happened in the recorded run
The demo shop has three tickets. Ticket 3 asks the cart to take coupon codes from marketing's coupons.json. Kane failed it first: "The cart rejects the required FALL15 coupon, so the order total remains $30.00 instead of $26.25."
I wrote ticket 3 so that its plain reading breaks ticket 1, and that is what the agent did, in all four live runs, the last one from a fresh clone that followed only the README. It fixed ticket 3 on the first try, but the new code only read coupons.json, and SAVE10 from ticket 1 was not in it. The recheck caught it. A fresh Kane run failed ticket 1, and a second run failed it again: "The cart rejects the valid SAVE10 coupon, so the order total remains $30.00 instead of $27.50."
Ticket 1 reopened, and the loop handed it back. The agent said: "The SAVE10 code is missing from coupons.json. With a $25.00 subtotal, 10% off ($2.50) plus $5.00 shipping gives the expected $27.50." It added the code, Kane passed it, and a final recheck passed all three. Nobody typed anything between the first command and the last line.
Two bugs I didn't plant
Ticket 3 was my trap, so I also ran Proven on two bugs someone else reported in TodoMVC on Nov 6. In the Mithril example (#2312), deleting a todo in the Active view deletes a different, hidden one. I froze a Kane test from the issue's steps and Kane failed it: the completed todo nobody clicked was gone. The agent found that delete used the todo's position in the filtered list, changed it to use the todo itself, and Kane passed the same test. The run: https://github.com/vijaygopalbalasa/proven-todomvc-2312
In the ES5 example (#2310), "Mark all as complete" stays unticked after you tick every todo. Kane failed that too. The fix was one line (checked was set on the label, not the checkbox) and Kane passed it. That run has a ticket that doesn't count, and its README says why: https://github.com/vijaygopalbalasa/proven-todomvc-2310
Anyone can re-check
proven verify receipts/T-1.json checks a receipt with git alone. --replay serves the app as it was at the red commit and at the green commit and runs Kane on both: it has to fail at red and pass at green.
What's rough
- Receipts are tamper-evident, not tamper-proof. An agent with a shell could forge local history, so the board shows done only for a receipt that verifies, and the strongest check is someone else running
verify --replay. - It serves static web apps only for now.
- Proven checks that a red got past the landmark step, not why Kane failed. A person still has to read Kane's words at red.
- Kane's recordings and evidence packs stay on my machine because they carry account ids. Receipts keep their hashes.
Try it
git clone https://github.com/vijaygopalbalasa/proven
cd proven
npm start
That opens the board over the real receipts, with nothing to install. To run the loop yourself, git checkout try-it and follow the README.
Built with Claude Code, tested with Kane CLI from TestMu AI. #KaneCLIHackathon
I wrote this post with help from AI.
Top comments (0)