soul-audit
por kapslap
Coding Agents & IDEsResumen
Evaluate any AI agent's soul file, system prompt, or AGENTS.md against the Guardian Angel v0.6 framework (Forrest.
Descripción
Qué hace esta skill
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.
Cuándo usarla
- 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
Flujo de trabajo de ejemplo
User asks: 'Audit my AGENTS.md against the Guardian Angel framework'
- 1
Reads the specified AGENTS.md from the workspace
- 2
Loads the rubric from references/rubric.md
- 3
Scores each of the 12 dimensions 0-3 with brief justifications
- 4
Identifies symmetry violations where behavior would differ under observation
- 5
Outputs the full structured report with strengths, gaps, and ranked recommendations
A scored Soul Audit Report showing overall score out of 45, per-dimension breakdown, critical gaps with document quotes, and prioritized improvement steps
Instalación
clawhub install kapslap/soul-auditEjecuta el comando de la CLI o pega el prompt en Claude Code, Cursor, Codex o el agente de programación que uses.