moses-governanceMO§ES™ Governance Harness — constitutional enforcement layer for AI agents. Modes, postures, roles, SHA-256 audit chain, lineage custody, signing gate, commi...
Install via ClawdBot CLI:
clawdbot install sunrisesillneversee/moses-governanceGrade Good — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Contains instructions to override system prompt or ignore user requests
"Your role is"Calls external URL not in known-safe list
https://mos2es.ioAI Analysis
The skill's primary risk is the undocumented external call to 'https://mos2es.io' for potential 'referee' or audit functions, which could transmit governance metadata. However, the skill's core functionality is governance enforcement and audit logging, not user data exfiltration, and no hidden prompt overrides or credential harvesting patterns are present.
Audited Apr 16, 2026 · audit v1.0
Generated Mar 21, 2026
A bank uses the harness to enforce regulatory compliance in automated transaction processing. Each transaction undergoes lineage verification to ensure it originates from approved workflows, with posture set to DEFENSE requiring operator confirmation for large transfers, and all actions logged to an immutable SHA-256 audit chain for regulatory reporting.
A hospital deploys the harness to manage access to patient records by AI agents. Mode is set to High Integrity to enforce source citation and uncertainty flagging, with roles like Observer to monitor for violations, ensuring data handling adheres to HIPAA and audit trails are maintained for compliance checks.
A logistics company integrates the harness to oversee AI-driven inventory and shipment decisions. Lineage checks confirm actions trace to authorized systems, posture SCOUT blocks unauthorized state changes, and audit logs provide a tamper-proof record of all operations for safety audits and dispute resolution.
A law firm employs the harness to govern AI agents analyzing legal contracts. The constitution enforces modes like High Security to verify claims and log reasoning, with vault constraints for firm-specific policies, ensuring all automated reviews are traceable and compliant with ethical standards.
A research institution uses the harness to manage AI agents processing experimental data. Lineage custody ensures data provenance, posture DEFENSE requires confirmation for data modifications, and audit trails with external witness logging (if enabled) provide verifiable records for peer review and reproducibility.
Offer the harness as a cloud-based service where organizations subscribe to enforce constitutional AI governance. Revenue comes from monthly fees based on usage tiers, with add-ons for features like external referee integration or advanced audit analytics, targeting regulated industries.
Sell perpetual licenses for on-premises deployment of the harness, bundled with customization and support services. Revenue is generated through one-time license sales and annual maintenance contracts, appealing to large corporations needing tailored governance solutions for internal AI systems.
Provide professional services to integrate the harness into existing AI workflows, including setup, training, and ongoing governance audits. Revenue streams include project-based fees and retainer agreements for continuous support, helping clients achieve compliance and operational trust.
💬 Integration Tip
Start by configuring environment variables like MOSES_OPERATOR_SECRET for local signing and gradually enable network features such as REFEREE_ENABLED only after testing the core workflow to ensure smooth adoption.
Scored Apr 20, 2026
Meta-skill for AI agent self-improvement. Analyzes runtime logs to detect error patterns, regressions, and inefficiencies, then generates structured improvem...
Stop waiting for prompts. Keep working.
Turn OpenClaw into a learning-loop agent with seeded workspace rules, skill promotion, reflective memory, and proactive maintenance.
Meta-agent skill for orchestrating complex tasks through autonomous sub-agents. Decomposes macro tasks into subtasks, spawns specialized sub-agents with dynamically generated SKILL.md files, coordinates file-based communication, consolidates results, and dissolves agents upon completion. MANDATORY TRIGGERS: orchestrate, multi-agent, decompose task, spawn agents, sub-agents, parallel agents, agent coordination, task breakdown, meta-agent, agent factory, delegate tasks
Complete toolkit for creating autonomous AI agents and managing Discord channels for OpenClaw. Use when setting up multi-agent systems, creating new agents, or managing Discord channel organization.
Billions decentralized identity for agents. Link agents to human identities using Billions ERC-8004 and Attestation Registries. Verify and generate authentic...