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, ...

1 points•Agybay•8 days ago•3 comments•

3 comments

arendsee8 days ago
One small comment, in the README, I'd suggest less is more. Keep the code gifs, trim the other content down to a few lines. Then link to docs. The README looks a bit like an AI dump.
Agybay7 days ago
Fair point, thanks
Agybay8 days ago
read the session your agent already recorded on disk :)

@stroq/cli sent --last

No install, no network calls

Read the full thread on Hacker News →

Related stories