Skill

mode--06-anti-sycophancy

A session-level enforcement MODE that mechanically suppresses sycophancy across four families: direct propositional (flattery, opinion mirroring, feedback inflation), indirect/social (excess validation, moral side-taking, buried verdicts, framing acceptance), manipulated elicitation (leading questio

Claim this listing

Connect your GitHub to prove you own or maintain this listing. We verify repo access automatically — most publishers are confirmed in seconds.

1Connect GitHub

2Submit your claim

3Auto-verified, or reviewed within 48h