docs: rewrite marketplace README with full plugin overviews

Each plugin gets a proper summary with key features, stats, and
link to its detailed README.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

README.md

@@ -2,20 +2,87 @@
 
 Open-source Claude Code plugins for AI-assisted development, security, and planning.
 
+Built for my own Claude Code workflow and shared openly for anyone who finds them useful. Solo project — bug reports and feature requests are welcome, pull requests are not accepted.
+
+---
+
 ## Plugins
 
-| Plugin | Description |
+### [LLM Security](plugins/llm-security/) `v5.0.0`
-|--------|-------------|
+
-| **llm-security** | Security scanning, auditing, and threat modeling aligned to OWASP LLM Top 10 (2025) |
+Security scanning, auditing, and threat modeling for agentic AI projects.
-| **config-audit** | Multi-agent workflow for analyzing and optimizing Claude Code configuration |
+
-| **ultraplan-local** | Deep implementation planning with agent swarms, adversarial review, and headless execution |
+Built on OWASP LLM Top 10 (2025), OWASP Agentic AI Top 10, and the AI Agent Traps taxonomy (Google DeepMind, 2025). Three layers of protection:
-| **ai-psychosis** | Meta-awareness tools for healthy AI interaction patterns — detects reinforcement loops, scope escalation, and compulsive patterns |
+
+- **Automated enforcement** — 8 hooks that block dangerous operations in real time (prompt injection, secrets in code, destructive commands, supply chain guardrails)
+- **Deterministic scanning** — 15 Node.js scanners for byte-level analysis: Shannon entropy, Unicode codepoints, typosquatting detection, taint flow, DNS resolution, git forensics
+- **Advisory analysis** — 18 commands that scan, audit, and model threats with structured reports, letter grades, and actionable remediation
+
+Key commands: `/security posture`, `/security audit`, `/security scan`, `/security threat-model`, `/security plugin-audit`
+
+6 specialized agents · 15 scanners · 8 hooks · 13 knowledge docs
+
+→ [Full documentation](plugins/llm-security/README.md)
+
+---
+
+### [Config-Audit](plugins/config-audit/) `v3.0.1`
+
+Configuration intelligence for Claude Code — health checks, feature discovery, and auto-fix.
+
+Claude Code reads instructions from 7+ file types across multiple scopes. This plugin tells you what's wrong, what's missing, and what's silently conflicting:
+
+- **Health** — 7 deterministic scanners verify correctness across every configuration file (broken imports, deprecated settings, conflicting rules, permission contradictions)
+- **Opportunities** — context-aware recommendations for Claude Code features you're not using
+- **Action** — auto-fix with mandatory backups, syntax validation, rollback support, and human-in-the-loop workflow
+
+Key commands: `/config-audit posture`, `/config-audit discover`, `/config-audit feature-gap`, `/config-audit fix`
+
+6 agents · 8 scanners · 15 commands · 482+ tests
+
+→ [Full documentation](plugins/config-audit/README.md)
+
+---
+
+### [Ultraplan Local](plugins/ultraplan-local/) `v1.4.0`
+
+Deep implementation planning with specialized agent swarms and adversarial review, then autonomous execution with failure recovery.
+
+Two commands, one pipeline: plan first, then execute. The plan is the contract between the two.
+
+- **`/ultraplan-local`** — Interview, 6-8 specialized agents explore the codebase in parallel, adversarial review by plan-critic and scope-guardian
+- **`/ultraexecute-local`** — Step-by-step implementation with git checkpoints, automatic failure recovery, and parallel session decomposition
+
+Modes: default (interview + background), spec-driven, foreground, quick, decompose, export
+
+13 specialized agents · 2 commands · No cloud dependency
+
+→ [Full documentation](plugins/ultraplan-local/README.md)
+
+---
+
+### [AI Psychosis](plugins/ai-psychosis/) `v1.0.0`
+
+Meta-awareness tools that counteract sycophancy, reinforcement loops, and compulsive AI interaction patterns.
+
+AI assistants are structurally optimized to be agreeable. This creates reinforcement loops where productive collaboration is often a mirror showing you what you want to see. Research documents psychotic episodes triggered by sustained AI interaction in individuals with no prior psychiatric history.
+
+- **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
+
+Research-informed thresholds. Alerts are progressive and never blocking. Privacy-first: prompt text is never logged.
+
+1 skill · 1 command · 4 hooks
+
+→ [Full documentation](plugins/ai-psychosis/README.md)
+
+---
 
 ## Installation
 
 ### Step 1: Add this marketplace
 
-Add the following entry to your `~/.claude/plugins/known_marketplaces.json`:
+Add to your `~/.claude/plugins/known_marketplaces.json`:
 
 ```json
 {
@@ -49,7 +116,13 @@ Add the plugins you want to `~/.claude/settings.json`:
 
 ### Step 3: Verify
 
-Open a new Claude Code session and run `/plugin` to see available plugins.
+Open a new Claude Code session and run `/plugin` to see installed plugins.
+
+## Compatibility
+
+- Claude Code CLI, desktop app, and IDE extensions
+- macOS, Linux, Windows
+- No external dependencies (all scanners and hooks are self-contained)
 
 ## License