AGGIB/Stroq

Find known secrets in your AI coding agent sessions (Claude Code, Codex, Cursor), then guard the next one with local hooks that trace risky commands to the content that dictated them. Open source, no telemetry.

92 best points · 39 comments · 4 Hacker News posts · 192 GitHub stars · View on GitHub

Hacker News discussions

• Show HN: Stroq – a local audit of what your coding agent did and why (92 points, 34 comments, by agybay_07, 2026-11-05)
• Show HN: Stroq – a firewall that knows why your AI agent ran that command (2 points, 1 comments, by Agybay, 2026-09-10)
• Show HN: Which of your secrets did your coding agent send? (1 points, 3 comments, by Agybay, 2026-09-22)
• Show HN: Check your Claude Code, Codex and Cursor sessions for secrets (1 points, 1 comments, by agybay_07, 2026-10-13)