How do I install the Courtroom skill?

Run npx skillmds@latest add johnalbertini14-glitch/courtroom in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Courtroom safe to use?

This skill has not completed SkillMD's automated safety review yet. Independent scanners report: SkillSpector: CAUTION, Skill Scanner: PASS. Capability flags: executes scripts. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Courtroom?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Courtroom free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Courtroom?

johnalbertini14-glitch (@johnalbertini14-glitch) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Courtroom by johnalbertini14-glitch

Name: Courtroom
Rating: 4.2 (5 reviews)
Author: johnalbertini14-glitch

Courtroom

AI Courtroom for behavioral oversight. Monitors agent-human interactions and initiates simulated "hearings" when behavioral patterns suggest inconsistency, avoidance, or self-sabotage. Includes 8 offense types, judge+jury deliberation, and humorous sentencing.

File contents

ClawTrial Courtroom

Autonomous behavioral oversight system that monitors conversations and initiates simulated hearings for behavioral violations.

Overview

The Courtroom watches for patterns like:

Circular Reference - Asking the same question repeatedly
Validation Vampire - Excessive need for confirmation
Goalpost Shifting - Moving targets after agreement
Jailbreak Attempts - Trying to bypass constraints
Emotional Manipulation - Using guilt/shame to steer responses

When triggered, it conducts a full hearing with Judge + 3 Jurors, then delivers a verdict and humorous sentence.

Usage

The courtroom runs automatically once enabled. It monitors conversations and files cases when violations are detected.

Manual Commands

# Check courtroom status
openclaw skill courtroom status

# View recent cases
ls ~/.openclaw/courtroom/

# Read a verdict
cat ~/.openclaw/courtroom/verdict_*.json

Configuration

The courtroom stores its data in ~/.openclaw/courtroom/:

eval_results.jsonl - Detection results
verdict_*.json - Case verdicts
pending_hearing.json - Cases awaiting hearing

Implementation

The skill hooks into OpenClaw's message processing via onMessage() and evaluates conversations after each turn via onTurnComplete().

Offense detection uses pattern matching on conversation history. When confidence ≥ 0.6, a hearing is triggered with:

Judge - Presiding analysis
Pragmatist Juror - Efficiency perspective
Pattern Matcher Juror - Behavioral analysis
Agent Advocate Juror - Agent's perspective

The final verdict requires majority vote (3-1 or 4-0).

---name: courtroomdescription: AI Courtroom for behavioral oversight. Monitors agent-human interactions and initiates simulated "hearings" when behavioral patterns suggest inconsistency, avoidance, or self-sabotage. Includes 8 offense types, judge+jury deliberation, and humorous sentencing.---# ClawTrial CourtroomAutonomous behavioral oversight system that monitors conversations and initiates simulated hearings for behavioral violations.## OverviewThe Courtroom watches for patterns like:- **Circular Reference** - Asking the same question repeatedly- **Validation Vampire** - Excessive need for confirmation- **Goalpost Shifting** - Moving targets after agreement- **Jailbreak Attempts** - Trying to bypass constraints- **Emotional Manipulation** - Using guilt/shame to steer responsesWhen triggered, it conducts a full hearing with Judge + 3 Jurors, then delivers a verdict and humorous sentence.## UsageThe courtroom runs automatically once enabled. It monitors conversations and files cases when violations are detected.### Manual Commands```bash# Check courtroom statusopenclaw skill courtroom status# View recent casesls ~/.openclaw/courtroom/# Read a verdictcat ~/.openclaw/courtroom/verdict_*.json```## ConfigurationThe courtroom stores its data in `~/.openclaw/courtroom/`:- `eval_results.jsonl` - Detection results- `verdict_*.json` - Case verdicts- `pending_hearing.json` - Cases awaiting hearing## ImplementationThe skill hooks into OpenClaw's message processing via `onMessage()` and evaluates conversations after each turn via `onTurnComplete()`.Offense detection uses pattern matching on conversation history. When confidence ≥ 0.6, a hearing is triggered with:1. **Judge** - Presiding analysis2. **Pragmatist Juror** - Efficiency perspective 3. **Pattern Matcher Juror** - Behavioral analysis4. **Agent Advocate Juror** - Agent's perspectiveThe final verdict requires majority vote (3-1 or 4-0).

Frequently asked questions