docs(readme): meet the repo-standard first-screen contract

The repo-standard gate reported 5 ERRORs against this README: it opened
with the badge block instead of an H1, carried no `## Install`,
`## Non-goals` or `## Changelog` heading, and offered `marketplace add`
plus an `enabledPlugins` block but no CLI install command — so an agent
told "install this" found nothing to run.

- Open with the H1, then the forge description verbatim, then the badges.
  Description == catalog == README opening line is the one agreement a
  machine can check from inside the repo.
- Promote install to a top-level `## Install` on the first screen and add
  `claude plugin install ai-psychosis@ktg-plugin-marketplace`. The
  settings.json form stays beside it, not instead of it.
- Add `## Non-goals` (not clinical, not blocking, not telemetry, not a
  productivity tracker, not portable off Claude Code, English-only) and
  `## Changelog` pointing at CHANGELOG.md.
- Move the Compatibility table up as `## Requirements` rather than
  duplicating it.
- Fix the AI-disclosure link: `../../README.md#ai-generated-code-disclosure`
  resolved outside the repo and its anchor did not exist in the catalog
  README either. Points at this repo's own GOVERNANCE.md#can-i-trust-this.

Gate: 0 ERROR, 12 checks pass. One WARN left standing — the H1 is
`# Interaction Awareness`, not `# ai-psychosis`. Human titles are the
org norm (10 of 14 repos) and the gate defers this to the operator.

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_011FzfsK6Mj3BNcfLosWUs2J

README.md

@@ -1,3 +1,7 @@
+# Interaction Awareness
+
+Meta-awareness tools for healthy AI interaction patterns. Detects reinforcement loops, scope escalation, narrative crystallization, and other compulsive patterns.
+
 <!-- badges -->
 ![version](https://img.shields.io/badge/version-1.2.2-blue)
 ![platform](https://img.shields.io/badge/platform-Claude_Code-7C3AED)
@@ -5,16 +9,42 @@
 ![hooks](https://img.shields.io/badge/hooks-4-orange)
 ![license](https://img.shields.io/badge/license-MIT-brightgreen)
 
-# Interaction Awareness
-
-> **Solo-maintained, fork-and-own.** This plugin is a starting point, not a vendor product. Issues are welcome as signals; pull requests are not accepted. See [GOVERNANCE.md](GOVERNANCE.md) for the full model and what upstream provides.
-
-*AI-generated: all code produced by Claude Code through dialog-driven development. [Full disclosure →](../../README.md#ai-generated-code-disclosure)*
-
 A Claude Code plugin that counteracts sycophancy, reinforcement loops, and
 compulsive interaction patterns through behavioral modification and
 programmatic pattern detection.
 
+> **Solo-maintained, fork-and-own.** This plugin is a starting point, not a vendor product. Issues are welcome as signals; pull requests are not accepted. See [GOVERNANCE.md](GOVERNANCE.md) for the full model and what upstream provides.
+
+*AI-generated: all code produced by Claude Code through dialog-driven development. [Full disclosure →](GOVERNANCE.md#can-i-trust-this)*
+
+## Install
+
+```bash
+claude plugin marketplace add https://git.fromaitochitta.com/open/ktg-plugin-marketplace.git
+claude plugin install ai-psychosis@ktg-plugin-marketplace
+```
+
+Or enable directly in `~/.claude/settings.json`:
+
+```json
+{
+  "enabledPlugins": {
+    "ai-psychosis@ktg-plugin-marketplace": true
+  }
+}
+```
+
+Layer 1 and Layer 2 are active immediately. No configuration needed —
+see [Quick start](#quick-start) for layer configuration and uninstall.
+
+## Requirements
+
+| Requirement | Version |
+|-------------|---------|
+| Claude Code | 1.0+ |
+| Node.js | 18+ (bundled with Claude Code) |
+| Platform | macOS, Linux, Windows |
+
 ## The problem
 
 AI assistants are structurally optimized to be agreeable. This creates
@@ -122,6 +152,27 @@ commented on, and omitted entirely when conditions are not met.
 **Enable:** Set `layer4: true` in `.claude/ai-psychosis.local.md`
 and restart Claude Code. Layer 4 is opt-in (off by default).
 
+## Non-goals
+
+- **Not a clinical instrument.** It measures interaction patterns, not mental
+  states. It does not diagnose, screen for, or treat anything, and no alert it
+  produces is a medical signal. If the underlying concern is health, the
+  address for that is a clinician.
+- **Not a blocker.** No hook ever exits non-zero or asks for confirmation.
+  Every alert is text injected into the conversation; the session continues
+  either way. The goal is awareness, not control.
+- **Not telemetry.** Prompt text is never written to disk, there is no network
+  call anywhere in the plugin, and nothing leaves the machine. See
+  [Privacy](#privacy).
+- **Not a productivity tracker.** There are no scores, streaks, or goals. The
+  metrics exist to surface spiral patterns, and they are aggregated only when
+  you ask for a report.
+- **Not portable outside Claude Code.** Layer 2 depends on Claude Code hook
+  events. Layer 1's instructions are conceptually portable, the detection is
+  not. See [Platform scope](#platform-scope).
+- **Not multilingual.** Pattern detection is English-only as of v1.2;
+  Norwegian patterns are deferred.
+
 ## What's new in v1.2.0
 
 v1.2.0 implements operational findings from Anthropic's
@@ -335,26 +386,6 @@ mode). Layer 2 reinforces Layer 1 with data-driven alerts.
 
 ## Quick start
 
-### Installation
-
-Add the marketplace and browse plugins with `/plugin`:
-
-```bash
-claude plugin marketplace add https://git.fromaitochitta.com/open/ktg-plugin-marketplace.git
-```
-
-Or enable directly in `~/.claude/settings.json`:
-
-```json
-{
-  "enabledPlugins": {
-    "ai-psychosis@ktg-plugin-marketplace": true
-  }
-}
-```
-
-Layer 1 and Layer 2 are active immediately. No configuration needed.
-
 ### Configure layers
 
 Create `~/.claude/ai-psychosis.local.md` for global config:
@@ -541,13 +572,10 @@ programmatic detection depends on hook events that only Claude Code provides.
 Other platforms would need equivalent hook systems to support this kind of
 real-time behavioral modification.
 
-## Compatibility
+## Changelog
 
-| Requirement | Version |
-|-------------|---------|
-| Claude Code | 1.0+ |
-| Node.js | 18+ (bundled with Claude Code) |
-| Platform | macOS, Linux, Windows |
+See [CHANGELOG.md](CHANGELOG.md) for the full version history. The
+"What's new" sections above cover the two most recent feature releases.
 
 ## References