{"slug": "i-built-a-workflow-that-checks-whether-my-ai-agent-s-context-was-enough-then-it", "title": "I built a workflow that checks whether my AI agent's context was enough, then proves it with my own tests", "summary": "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.", "body_md": "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.\n\nThe stack is four small tools, all Python standard library, all MIT, all local:\n\nA fifth tool, ghostworkflow, runs the chain in one command, and a small local web app puts a face on it.\n\nI 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.\n\nI 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)\n\nWhat I want to know most: did the verify verdict match what your agent actually struggled with?", "url": "https://wpnews.pro/news/i-built-a-workflow-that-checks-whether-my-ai-agent-s-context-was-enough-then-it", "canonical_source": "https://dev.to/littlestjames82sys/i-built-a-workflow-that-checks-whether-my-ai-agents-context-was-enough-then-proves-it-with-my-own-4214", "published_at": "2026-10-19 03:41:21+00:00", "updated_at": "2026-10-19 03:48:51.124313+00:00", "lang": "en", "topics": ["ai-agents", "ai-tools", "developer-tools", "ai-safety"], "entities": ["ghostworkflow", "pytest", "Python"], "also_reported_by": [], "alternates": {"html": "https://wpnews.pro/news/i-built-a-workflow-that-checks-whether-my-ai-agent-s-context-was-enough-then-it", "markdown": "https://wpnews.pro/news/i-built-a-workflow-that-checks-whether-my-ai-agent-s-context-was-enough-then-it.md", "text": "https://wpnews.pro/news/i-built-a-workflow-that-checks-whether-my-ai-agent-s-context-was-enough-then-it.txt", "jsonld": "https://wpnews.pro/news/i-built-a-workflow-that-checks-whether-my-ai-agent-s-context-was-enough-then-it.jsonld"}}