deck
Shows exactly which lines of code your AI agent's decision rests on, before you approve it.
deck turns an AI coding agent's decision into a short list of claims, each tied to the exact file and line that proves it, instead of a long chat essay you have to mine for the actual choice. It's free and open source with no plan to charge, runs on the same agent session you're already in rather than calling its own model, and refuses a claim if the line it points to doesn't exist. You can try a live deck in the browser before installing anything.
What holds up
- +Free and open source, with no plan to charge — stated outright, not 'free for now'
- +Ties every claim to the exact file and line that proves it — a broken reference gets refused
- +Runs on the agent session you already have — deck itself never calls a separate model
Mind the limits
- −Only shows decisions the agent explicitly wrapped in a deck command — nothing else gets logged
- −Useful only if you're already working with a coding agent — no value without one
Picked here? Add the badge
Put it on your site. It links back to this page. Free for every listed product.
<a href="https://stillworks.dev/products/p/deck/"><img src="https://stillworks.dev/badge/deck.svg" alt="Picked by StillWorks" width="230" height="54"></a>