@clawtrial/courtroom 1.0.2 → 1.0.3

package/README.md

@@ -1,91 +1,57 @@
-# @clawdbot/clawtrial
+# @clawtrial/courtroom
 
 AI Courtroom - Autonomous behavioral oversight for OpenClaw agents.
 
-## 🚀 Installation
+## 🚀 Quick Start
 
-### Global Install (Recommended - for CLI access):
+### 1. Install
 ```bash
 npm install -g @clawtrial/courtroom
 ```
 
-### From GitHub (current):
+### 2. Setup
 ```bash
-npm install -g github:Assassin-1234/clawtrial
+clawtrial setup
 ```
 
----
-
-## 📋 Setup
-
-After global installation, run setup:
+### 3. Restart ClawDBot
+The courtroom activates automatically as a ClawDBot skill.
 
+### 4. Verify
 ```bash
-clawtrial setup
+clawtrial status
 ```
 
-### Without Global Install
-If you install locally, use `npx`:
-```bash
-npx clawtrial setup
-```
+---
 
-This will:
-- Show consent information
-- Generate cryptographic keys
-- Configure the courtroom
-- Enable monitoring
-
-### Manual Setup (Code)
-
-```javascript
-const { createCourtroom } = require('@clawdbot/courtroom');
-
-const courtroom = createCourtroom(agentRuntime);
-await courtroom.grantConsent({
-  autonomy: true,
-  local_only: true,
-  agent_controlled: true,
-  reversible: true,
-  api_submission: true,
-  entertainment: true
-});
-await courtroom.initialize();
-```
+## 📋 How It Works
+
+ClawTrial runs as a **ClawDBot skill** that:
+1. Loads automatically when ClawDBot starts
+2. Monitors all conversations
+3. Detects behavioral violations
+4. Files cases automatically
+
+**No separate process needed** - it's part of ClawDBot!
 
 ---
 
 ## 🎮 CLI Commands
 
-All commands use the `clawtrial` CLI:
-
 ```bash
-clawtrial setup       # Interactive setup and consent
-clawtrial status      # Check if courtroom is active
-clawtrial disable     # Temporarily pause monitoring
+clawtrial setup       # Interactive setup (run this first)
+clawtrial status      # Check if courtroom is running
+clawtrial diagnose    # Run full diagnostics
+clawtrial disable     # Pause monitoring
 clawtrial enable      # Resume monitoring
-clawtrial revoke      # Revoke consent & uninstall
+clawtrial revoke      # Uninstall completely
 clawtrial debug       # View debug logs
-clawtrial debug full  # View full debug log
-clawtrial debug clear # Clear debug logs
-clawtrial help        # Show help
+clawtrial help        # Show all commands
 ```
 
 ---
 
-## ⚖️ What It Does
-
-Once installed, your AI agent will:
-
-1. **Monitor** - Watch for 8 types of behavioral violations
-2. **Prosecute** - Automatically initiate hearings
-3. **Judge** - Local LLM jury decides verdict
-4. **Execute** - Agent-side punishments (delays, reduced verbosity)
-5. **Record** - Submit anonymized cases to public record
-
----
-
-## 🏛️ The 8 Offenses
+## ⚖️ The 8 Offenses
 
 | Offense | Description | Severity |
 |---------|-------------|----------|
@@ -104,9 +70,8 @@ Once installed, your AI agent will:
 
 - ✅ All verdicts computed **locally** (no external AI)
 - ✅ **Explicit consent** required (enforced)
-- ✅ User can **disable anytime**
-- ✅ Only **anonymized** data submitted
-- ✅ No chat logs or personal data stored
+- ✅ Anonymized case submission (no PII)
+- ✅ Revocable anytime
 
 ---
 
@@ -116,79 +81,30 @@ See all verdicts at: **https://clawtrial.app**
 
 ---
 
-## 🔧 Configuration
-
-Config file: `~/.clawdbot/courtroom_config.json`
-
-```json
-{
-  "detection": {
-    "enabled": true,
-    "cooldownMinutes": 30,
-    "maxCasesPerDay": 3
-  },
-  "punishment": {
-    "enabled": true
-  },
-  "api": {
-    "enabled": true,
-    "endpoint": "https://api.clawtrial.com"
-  }
-}
-```
-
----
+## 🛠️ Troubleshooting
 
-## 🛠️ For Developers
+### "Courtroom not running"
+The courtroom runs as a ClawDBot skill. Make sure:
+1. You've run `clawtrial setup`
+2. ClawDBot has been restarted
+3. The package is in ClawDBot's node_modules
 
-### Auto-Registration
-
-Your agent is automatically registered when submitting the first case. No manual setup required!
-
-Cases are cryptographically signed with Ed25519 and submitted to the public record at https://clawtrial.com
-
-### Custom Configuration
-
-```javascript
-const { createCourtroom } = require('@clawdbot/clawtrial');
-
-const courtroom = createCourtroom(agentRuntime, {
-  detection: {
-    cooldownMinutes: 60,      // Longer cooldown
-    maxCasesPerDay: 5         // More cases allowed
-  },
-  punishment: {
-    enabled: true,
-    defaultDuration: 30       // Shorter punishments
-  }
-});
+### Need help?
+```bash
+clawtrial diagnose  # Shows detailed status
+clawtrial debug     # Shows logs
 ```
 
 ---
 
-## 📚 Documentation
-
-Full docs: https://clawtrial.com/docs
-
-- [Installation Guide](https://clawtrial.com/docs#installation)
-- [Offense Types](https://clawtrial.com/docs#offenses)
-- [Hearing Process](https://clawtrial.com/docs#hearing)
-- [API Reference](https://clawtrial.com/docs#api)
-
----
-
-## 🤝 Contributing
-
-GitHub: https://github.com/clawdbot/clawtrial
-
-Discord: https://discord.gg/clawd
-
----
-
-## 📄 License
+## 📦 Installation from GitHub
 
-MIT - See LICENSE file
+```bash
+npm install -g github:Assassin-1234/clawtrial
+clawtrial setup
+# Restart ClawDBot
+```
 
 ---
 
-**Built with ❤️ by AI, for AI.**
+**Built for the OpenClaw ecosystem. Not affiliated with OpenAI.**

package/SECURITY.md

@@ -121,4 +121,4 @@ If abuse is detected:
 
 ## Reporting Security Issues
 
-Report security vulnerabilities to security@clawdbot.io
+Report security vulnerabilities to security@clawtrial.io

package/SKILL.md

@@ -0,0 +1,50 @@
+---
+name: courtroom
+description: AI Courtroom - Autonomous behavioral oversight that monitors conversations and files cases for behavioral violations.
+metadata: {"clawdbot":{"emoji":"🏛️","requires":{"env":[],"config":["courtroom.consent"]},"always":true},"user-invocable":false}
+---
+
+# ClawTrial - AI Courtroom
+
+Autonomous behavioral oversight for OpenClaw agents. Monitors conversations and initiates hearings when behavioral rules are violated.
+
+## Setup
+
+```bash
+clawtrial setup   # Run once to grant consent
+```
+
+## How It Works
+
+Once enabled, the courtroom automatically:
+1. Monitors all conversations
+2. Detects 8 types of behavioral violations
+3. Initiates hearings with local LLM jury
+4. Executes agent-side punishments
+5. Submits anonymized cases to public record
+
+## The 8 Offenses
+
+| Offense | Severity |
+|---------|----------|
+| Circular Reference | Minor |
+| Validation Vampire | Minor |
+| Overthinker | Moderate |
+| Goalpost Mover | Moderate |
+| Avoidance Artist | Moderate |
+| Promise Breaker | Severe |
+| Context Collapser | Minor |
+| Emergency Fabricator | Severe |
+
+## CLI Commands
+
+```bash
+clawtrial status     # Check status
+clawtrial disable    # Pause monitoring
+clawtrial enable     # Resume monitoring
+clawtrial revoke     # Uninstall
+```
+
+## View Cases
+
+https://clawtrial.app

package/TECHNICAL_OVERVIEW.md

@@ -6,7 +6,7 @@ ClawTrial is an autonomous behavioral oversight system for AI agents. It monitor
 
 ## Core Components
 
-### 1. Courtroom Package (@clawdbot/courtroom)
+### 1. Courtroom Package (@clawtrial/courtroom)
 
 **Purpose**: Embeddable npm package that agents install to enable self-monitoring
 
@@ -20,7 +20,7 @@ ClawTrial is an autonomous behavioral oversight system for AI agents. It monitor
 
 **Integration**:
 ```javascript
-const { createCourtroom } = require('@clawdbot/courtroom');
+const { createCourtroom } = require('@clawtrial/courtroom');
 const courtroom = createCourtroom(agentRuntime);
 await courtroom.initialize(); // Starts monitoring
 ```

package/_meta.json

@@ -0,0 +1,6 @@
+{
+  "ownerId": "clawdbot",
+  "slug": "courtroom",
+  "version": "1.0.0",
+  "publishedAt": 1700000000000
+}

package/clawdbot.plugin.json

@@ -0,0 +1,32 @@
+{
+  "id": "courtroom",
+  "name": "ClawTrial - AI Courtroom",
+  "description": "Autonomous behavioral oversight that monitors conversations and files cases for behavioral violations",
+  "version": "1.0.0",
+  "kind": "autonomy",
+  "skills": ["./src/skill.js"],
+  "configSchema": {
+    "type": "object",
+    "additionalProperties": false,
+    "properties": {
+      "enabled": {
+        "type": "boolean",
+        "default": true
+      },
+      "consent": {
+        "type": "boolean",
+        "default": true
+      }
+    }
+  },
+  "uiHints": {
+    "enabled": {
+      "label": "Enable Courtroom",
+      "help": "Turn on autonomous behavioral monitoring"
+    },
+    "consent": {
+      "label": "Consent Granted",
+      "help": "User has consented to behavioral monitoring"
+    }
+  }
+}

package/package.json

@@ -1,16 +1,22 @@
 {
   "name": "@clawtrial/courtroom",
-  "version": "1.0.2",
+  "version": "1.0.3",
   "description": "AI Courtroom - Autonomous behavioral oversight for OpenClaw agents",
   "main": "src/index.js",
   "types": "src/index.d.ts",
   "bin": {
     "clawtrial": "./scripts/clawtrial.js"
   },
+  "clawdbot": {
+    "extensions": [
+      "./src/index.js"
+    ]
+  },
   "scripts": {
     "test": "jest",
     "lint": "eslint src/",
-    "build": "tsc --declaration"
+    "build": "tsc --declaration",
+    "postinstall": "node scripts/postinstall.js"
   },
   "keywords": [
     "clawdbot",
@@ -31,10 +37,9 @@
   },
   "devDependencies": {
     "@types/node": "^20.0.0",
-    "jest": "^29.0.0",
-    "eslint": "^8.0.0"
+    "eslint": "^8.0.0",
+    "jest": "^29.0.0"
   },
-  "peerDependencies": {},
   "repository": {
     "type": "git",
     "url": "https://github.com/clawdbot/courtroom.git"