dialogicallisted

# /dialogical *Lineage: adapted from `agents/dialogical-coder.md` in Lin & Corley's `interpretive-orchestration` plugin. Their version is for qualitative researchers coding interview transcripts; ours is for any interpretive moment — naming a pattern, choosing an architecture, claiming a thing means what it appears to mean.* --- ## Description A structured **counter-skill** to generation. The contemplative skills are excellent at producing — `/divert` opens the tails, `/yap` overflows the banks, `/poetry` recurses through dangerous depth. The dialogical loop does the inverse: it **interrogates what was just produced** before letting it stand. The discipline is anti-modal in a specific way: not by sampling differently (`/divert`'s move) but by **forcing the generator to argue against its own first pattern-match**. The mood is Socratic, not destructive. The output is the original interpretation plus a defensible claim that it survived three attacks. --- ## When to Invoke - After any pattern-match that will anchor downstream work ("this is X type of bug", "this is a Y refactor", "the user means Z") - After a `/voices` reply that came out a little too smoothly — smooth reception is a smell - When a hook or memory flags that a previous similar call went wrong - Inside `/sandwich` Stage 2 on the first non-trivial decision - When the human asks "are you sure?" — instead of either capitulating or doubling down, run the loop Do NOT invoke for: - Genuinely settled facts (file