Groundtruth – checks your AI coding agent's claims against the Git diff

(github.com)

3 points | by erapin_game a day ago ago

4 comments

  • westurner a day ago

    From https://github.com/akahkhanna/groundtruth :

    > Groundtruth — a Claude Code plugin that audits whether an agent actually did what it was asked; catches the false 'Done' on Stop (missed subtasks, stubs, false 'tests pass', overridden rules).

    Which other agent IDEs does or could this work with?

    [-]
    • westurner a day ago

      Is this also where to attach provenance metadata and sign the agent trace, and debug?

      Re: MCPSnoop, proxies like Aegis and LiteLLM, and awesome-auditable-ai: https://news.ycombinator.com/item?id=48777144#48779413

      There are web standards for signing metadata with interoperable schema as linked data:

      W3C JSON-LD/YAML-LD + W3C PROV + W3C DID + W3C VC Verifiable Claims

    • killix 9 hours ago

      [flagged]

  • erapin_game a day ago

    [flagged]