Moses Coordinator

MO§ES™ Coordinator — Lightweight daemon that monitors OpenClaw Gateway WebSocket for session events, detects sequence violations (Primary → Secondary → Obser...

This coordinator is a local monitoring daemon that connects to a local OpenClaw Gateway WebSocket and invokes a local audit script when it detects out-of-order agent responses. Before installing or running it: 1) Verify the referenced audit script (~/.openclaw/workspace/skills/moses-governance/scripts/audit_stub.py) exists and review its source — the coordinator executes it via subprocess, so a compromised or malicious audit script would run with your user privileges. 2) Note the minor inconsistencies between SKILL.md and the packaged script (different subprocess argument forms and an unused STATE_PATH); confirm which behavior you expect and that the audit logging call will produce the intended ledger entries. 3) Install the websockets package in a controlled environment (e.g., virtualenv) and consider running the coordinator in a sandbox or under a dedicated user if you will run it persistently. 4) Don’t provide credentials because none are required; ensure launchd/systemd entries point to the correct, reviewed script path. If the audit_stub.py is from a trusted source and reviewed, the skill appears coherent for its stated purpose.

Type: OpenClaw Skill Name: moses-coordinator Version: 1.0.2 The moses-coordinator skill implements a background daemon that monitors local session traffic via WebSockets (ws://127.0.0.1:18789) and executes an external script (audit_stub.py) via subprocess to log sequence violations. While these behaviors are consistent with its stated purpose of agent governance, the combination of persistent background monitoring, shell execution, and explicit instructions for establishing macOS persistence (launchd) are classified as high-risk capabilities. No evidence of malicious intent was found, and the documentation (SKILL.md) proactively advises against providing sensitive secrets (MOSES_OPERATOR_SECRET).