agentic-governance

---
name: agentic-governance
version: 1.3.0
description: Keep your constraints healthy — lifecycle management with automatic staleness detection
author: Live Neon <hello@liveneon.ai>
homepage: https://github.com/live-neon/skills/tree/main/agentic/governance
repository: leegitw/agentic-governance
license: MIT
tags: [agentic, governance, lifecycle, maintenance, health-checks, observability, compliance, staleness]
layer: governance
status: active
alias: gov
metadata:
  openclaw:
    requires:
      config:
        - .openclaw/governance.yaml
        - .claude/governance.yaml
      workspace:
        - output/governance/
        - output/constraints/
        - agentic/INDEX.md
---

# governance (治理)

Unified skill for constraint governance state, periodic reviews, index generation,
round-trip verification, and schema migration. Consolidates 6 granular skills.

**Trigger**: 定期保守 (periodic maintenance) or HEARTBEAT

**Source skills**: constraint-reviewer, index-generator, round-trip-tester, governance-state, slug-taxonomy, adoption-monitor (from safety)

## Installation

```bash
openclaw install leegitw/governance
```

**Dependencies**:
- `leegitw/constraint-engine` (for constraint data)
- `leegitw/failure-memory` (for observation data)

```bash
# Install full governance stack
openclaw install leegitw/context-verifier
openclaw install leegitw/failure-memory
openclaw install leegitw/constraint-engine
openclaw install leegitw/governance
```

**Standalone usage**: Index generation and round-trip verification work independently.
Full governance features require constraint-engine and failure-memory integration.

**Data handling**: This skill operates within your agent's trust boundary. When triggered,
it uses your agent's configured model for governance analysis and review. No external APIs
or third-party services are called. Results are written to `output/governance/` in your workspace.

## What This Solves

Constraints that never get reviewed become stale. Rules that never g