LaunchKit · 2026
Back to Skills

soul-audit

Evaluate any AI agent's soul file, system prompt, or AGENTS.md against the Guardian Angel v0.6 framework (Forrest.

1
295 downloads
by @kapslap

Setup & Installation

openclaw skills install @kapslap/soul-audit

Or with the ClawHub CLI, for registry-managed skill folders outside a full OpenClaw workspace:

npx clawhub install soul-audit

Version History

v1.1.1Mar 14, 2026 - Version note by skill developer:

Remove 'angel' from all references — Guardian framework language only

What This Skill Does

Scores an AI agent's soul file, system prompt, or AGENTS.md against the Guardian Angel v0.7 framework, a rubric derived from Forrest Landry's Immanent Metaphysics. Produces a structured report with dimension scores, identified gaps, and symmetry violations. Useful before deploying or upgrading an agent's ethical configuration.

Uses a scored 12-dimension rubric rather than vague heuristics, making gaps concrete and comparable across different agent configurations.

When to use it

  • Auditing a custom agent's SOUL.md before deployment
  • Checking if a system prompt would behave differently when monitored vs unmonitored
  • Comparing two agent configurations on ethical rigor
  • Identifying which dimensions of an agent's ethics need the most work
  • Preparing a documented ethics baseline for a new AI project

Example Workflow

Here's how your AI assistant might use this skill in practice.

INPUT

User asks: 'Audit my AGENTS.md against the Guardian Angel framework'

AGENT
  1. 1Reads the specified AGENTS.md from the workspace
  2. 2Loads the rubric from references/rubric.md
  3. 3Scores each of the 12 dimensions 0-3 with brief justifications
  4. 4Identifies symmetry violations where behavior would differ under observation
  5. 5Outputs the full structured report with strengths, gaps, and ranked recommendations
OUTPUT

A scored Soul Audit Report showing overall score out of 45, per-dimension breakdown, critical gaps with document quotes, and prioritized improvement steps