judgectl Agent Skill

Community

Safely run approved ingestion and audits

Authordawsonblock
Version1.0.0
Installs0

System Documentation

What problem does it solve?

It prevents accidental or unauthorized data mutations while enabling controlled ingestion, validation, and auditing of approved public legal sources.

Core Features & Use Cases

  • Evidence-first operational guardrails: Enforces that the agent treats evidence as authoritative, keeps memory derivative, and avoids inventing or asserting claims without verified snapshots.
  • Approved-tool execution via judgectl: Directs the agent to use the command-line interface for health checks, source listing/validation/info, ingestion runs, and audit guardrails instead of touching internals.
  • Mutation safety controls: Requires --json output and uses dry-run semantics or explicit --yes for enabling/disabling sources and other mutations.

Quick Start

Run a health check with stable JSON output by asking the agent to execute: judgectl --json health.

Dependency Matrix

Required Modules

None required

Components

Standard package

đź’» Claude Code Installation

Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.

Please help me install this Skill:
Name: judgectl Agent Skill
Download link: https://github.com/dawsonblock/JUDGE_ATLAS/archive/main.zip#judgectl-agent-skill

Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
View Source Repository

Agent Skills Search Helper

Install a tiny helper to your Agent, search and equip skill from 471,000+ vetted skills library on demand.