soul-audit
por kapslap
Coding Agents & IDEsResumo
Evaluate any AI agent's soul file, system prompt, or AGENTS.md against the Guardian Angel v0.6 framework (Forrest.
Descrição
O que esta skill faz
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.
Quando usá-la
- 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
Exemplo de fluxo de trabalho
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
Instalação
clawhub install kapslap/soul-auditExecute o comando da CLI ou cole o prompt no Claude Code, Cursor, Codex ou no agente de código que você usa.