Moses Governance Single

MO§ES™ Governance — Single-agent constitutional control. Enforces behavioral modes, posture controls, role awareness, and SHA-256 chained audit trail in one...

This skill appears to do what it says: local governance and an append-only audit ledger. Before installing or running it, do the following: (1) inspect the two Python scripts (they are small and included) — they operate locally and do not contact the network; (2) confirm you are comfortable with files being created under ~/.openclaw and tighten directory permissions if needed (these files can reveal agent activity); (3) only set MOSES_OPERATOR_SECRET if you want cryptographic attestations, and never paste that secret into chat or into other agents; (4) note minor metadata inconsistencies (version and declared bins) and the lack of a homepage/author signature — treat the publisher as unverified and consider running the scripts in a sandbox or test environment first.

Type: OpenClaw Skill Name: moses-governance-single Version: 1.0.4 The moses-governance-single skill is a local framework designed to enforce behavioral constraints and maintain an audit trail for an AI agent. The Python scripts (audit_stub.py and init_state.py) implement a SHA-256 chained ledger and state management system that operates entirely on the local filesystem (~/.openclaw). There is no evidence of network activity, data exfiltration, or malicious execution; the use of HMAC for attestation and fcntl for file locking suggests a focus on integrity and data consistency rather than exploitation.