| name | managing-guardrails |
| description | Enforcement of safety guardrails, axiom verification, secret scanning, and mutability protections. |
| type | skill |
| version | 1.0.0 |
| category | chain |
| agents | ["system-architecture-specialist","master-system-orchestrator"] |
| knowledge | ["safety-governance.json"] |
| scripts | ["scripts/guardian/axiom_checker.py","scripts/guardian/harm_detector.py","scripts/guardian/mutability_guard.py","scripts/guardian/secret_scanner.py","scripts/validation/audit_values.py","scripts/validation/fix_values.py"] |
| tools | [] |
| related_skills | ["sandboxing-security"] |
| references | [".agentrules"] |
| settings | {"auto_approve":false,"timeout_seconds":300} |
Safety Gating & Mutability Protection
This skill manages internal safety enforcements, checking model inputs/outputs for compliance with core axioms, scanning files for exposed secrets, and protecting system files from unauthorized mutation.
When to Use
Use this skill when auditing workspace secrets, verifying code alignment with ethical rules, or locking down configuration files.
Prerequisites
- Conda environment initialized.
Process
Follow these procedures to scan the workspace and enforce safety enforcements.
Checking Axioms & Safety
Run the checkers to scan the workspace:
conda run -p D:\Anaconda\envs\cursor-factory python scripts/guardian/axiom_checker.py
conda run -p D:\Anaconda\envs\cursor-factory python scripts/guardian/secret_scanner.py
Auditing Core Value Mappings
Ensure all codebase elements align with value tables:
conda run -p D:\Anaconda\envs\cursor-factory python scripts/validation/audit_values.py
Best Practices
- Strict Compliance: Reject any change that triggers mutability or safety guardrail warnings.
- Fail Closed: If a secret scan fails, block the commit or operation immediately.
