mirror of
https://github.com/addyosmani/agent-skills.git
synced 2026-08-12 18:07:26 +02:00
Two latent Tier-3 bugs caught in review before the path was ever exercised: - The grader prompt embeds the full stream-json trace (up to megabytes) and was passed as an argv entry, which would fail with E2BIG on any real run. It now goes to `claude -p` over stdin; the executor prompt moves to stdin for the same reason. - The executor ran headless with no permission mode, so file edits and command runs could be denied, forcing the narrate-instead-of-perform failure mode that trace grading exists to catch. It now runs with --permission-mode acceptEdits and a pre-approved tool list (Read,Glob,Grep,Edit,Write,Bash), documented in the README.