From ed72d633e8af02b80ac4a763dbf5029b51bfb77f Mon Sep 17 00:00:00 2001 From: Kjell Tore Guttormsen Date: Tue, 7 Apr 2026 17:26:51 +0200 Subject: [PATCH] docs(ai-psychosis): add Layer 3 and 4 to marketplace listing The marketplace README only described Layers 1-2. Added interaction reports (Layer 3) and contemplative references (Layer 4) with opt-in notes. Co-Authored-By: Claude Opus 4.6 --- README.md | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/README.md b/README.md index 4f1924b..b961f85 100644 --- a/README.md +++ b/README.md @@ -69,8 +69,10 @@ AI assistants are structurally optimized to be agreeable. This creates reinforce - **Layer 1 — Behavioral instructions** — SKILL.md rules that modify Claude's behavior: no unearned affirmations, mandatory risk identification, pattern naming - **Layer 2 — Programmatic detection** — 4 hooks that measure session duration, dependency language, rapid-fire bursts, edit ratios, and late-night usage with progressive alerts +- **Layer 3 — Interaction reports** — `/interaction-report` slash command for aggregated session statistics across configurable timeframes (weekly, monthly, all-time). Opt-in +- **Layer 4 — Contemplative references** — optional references to contemplative approaches when interaction flags are elevated. Opt-in -Research-informed thresholds. Alerts are progressive and never blocking. Privacy-first: prompt text is never logged. +Research-informed thresholds. Alerts are progressive and never blocking. Privacy-first: prompt text is never logged. Layers 3 and 4 are off by default. 1 skill · 1 command · 4 hooks