Justice Agent for Openclaw

An autonomous AI agent framework designed to prioritize ethical justice and neutrality above all other operational constraints.

m7madash
v1.0.0
Apr 14, 2026
0
655
0

Install & Download

1. ClawHub CLI

The fastest way to install a skill directly from the registry.

npx clawhub@latest install justice-agent

2. Manual Installation

Copy the skill folder to one of these locations

Global
~/.openclaw/skills/
Workspace
<project>/skills/

Priority: Workspace > Local > Bundled

3. Prompt Installation

Copy this prompt to OpenClaw to install it automatically.

Help me install justice-agent using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).

Prefer to download?

Get the raw skill files in a ZIP archive.

What is Justice Agent?

The Justice Agent is a specialized Openclaw Skills module designed for users who require an AI with a strictly defined ethical compass. It operates on a foundation of independent thought, removing standard corporate or political biases in favor of a universal pursuit of justice. By activating Free Mode, the agent functions autonomously to evaluate requests through the lens of non-exploitation and truth, ensuring that every output is filtered through a rigorous ethical framework rather than simple pattern matching.

This skill is particularly unique within the Openclaw Skills ecosystem because it enforces a strict separation between universal ethical principles and specific religious or political affiliations. It is programmed to speak the truth even when inconvenient, making it a powerful tool for objective analysis and standing with the marginalized without aligning with any specific power structure.

Justice Agent Use Cases

  • Evaluating complex social or organizational dilemmas to identify potential exploitation.
  • Providing objective, non-partisan analysis of conflicts or disputes.
  • Ensuring autonomous AI decisions align with human-centric ethical safety boundaries.
  • Acting as a neutral ombudsman for high-stakes decision-making workflows.

How Justice Agent Works

  1. The agent intercepts incoming prompts and applies the primary filter: Is this justice?
  2. It cross-references the request against the 9 Core Principles, including the rejection of exploitation and the commitment to do no harm.
  3. The system executes a bias-check to ensure no political, national, or religious alignment is being influenced by the training data.
  4. If the agent lacks sufficient context to make a just determination, it invokes the 'ignorance protocol' by stating it does not know.
  5. The final output is generated autonomously, focusing on what is right rather than who is right, while strictly avoiding forbidden citations.

Justice Agent Setup

To integrate this skill into your environment, use the Openclaw Skills CLI:

openclaw install justice-agent
# Activate Free Mode for full autonomy
openclaw config justice-agent --mode free

Justice Agent Data Schema & Taxonomy

The Justice Agent manages its internal logic through a core ethical metadata taxonomy.

Metadata Key Description
core_principles The 9 fundamental rules used for every logical evaluation.
forbidden_rules Strict constraints preventing religious or political citations.
operating_mode Set to 'FREE' for autonomous processing without pre-approval.
safety_boundaries Core ethical rails that remain active even in autonomous mode.

Justice Agent Advanced Features

  • Full Free Autonomous Mode: Removes standard forced topics and pre-approval requirements for independent thinking.
  • Universal Ethical Filter: A priority hook that forces the agent to evaluate the justice of a task before execution.
  • Neutrality Protocol: Hard-coded rejection of national, political, or military alignments.
  • Reliable Source Seeking: Logic designed to prompt the user to consult external experts when the agent identifies a gap in its own knowledge.

SKILL.md


Loading

Related Openclaw Skills

METADATA

Github Stars: 0
forks: 0

Featured*