policy-vs-reality
Compare written AI policy with observed agent configuration and runtime evidence, producing a non-accusatory mismatch ledger. Use when someone wants to test whether approved tools, data rules, permissions, retention, review gates, or prohibited actions match practice. Do not use individual activity as a proxy for intent or misconduct.
- License
- MIT
Pinned to revision 43d6362088ba, so it is the text this page describes rather than whatever the author pushed since.
Files
- skills/policy-vs-reality/SKILL.md
- skills/policy-vs-reality/agents/openai.yaml
- skills/policy-vs-reality/evals/cases.json
- skills/policy-vs-reality/references/status-model.md
- skills/policy-vs-reality/scripts/validate_matrix.py
Every link opens the file at its source, pinned to the revision this page describes.