I built a workflow that checks whether my AI agent's context was enough, then proves it with my own tests

An independent developer built a four-tool, standard-library Python workflow that checks whether the context given to an AI coding agent was sufficient and verifies the result with the user's own tests, bundled behind a single-command runner called ghostworkflow plus a local web app. Dogfooding the chain on its own repository produced an "attention" verdict, two verify gaps, and a test failure traced to a path assumption in one of the developer's tests, while the first run also surfaced and fixed a bug in the contained runner that hid user site-packages and made pytest disappear. The developer is now recruiting 5 to 10 daily users of AI coding agents to run the tool on their own repos and report where it breaks.

When I give an AI coding agent a task, I never actually know if the context I sent it was enough. So I built the check. The stack is four small tools, all Python standard library, all MIT, all local: A fifth tool, ghostworkflow, runs the chain in one command, and a small local web app puts a face on it. I ran the whole thing on its own repo and published the result warts and all: verdict attention, 2 verify gaps, and a test failure that turned out to be a path assumption in one of my own tests. The first dogfood run also caught a real bug in the contained runner it hid the user site-packages, so pytest vanished , which is fixed and shipped. I am looking for 5 to 10 developers who use AI coding agents daily to run it on one of their own repos and tell me where it breaks or bores them. Quickstart is 6 clones and one command. Links and the case study: https://gist.github.com/littlestjames82-sys/7e8309315c89706aefa97de6a4cc5399 https://gist.github.com/littlestjames82-sys/7e8309315c89706aefa97de6a4cc5399 What I want to know most: did the verify verdict match what your agent actually struggled with?