Skills
.Work. You
Rest

harness-governance

Community

Enforce trust tiers and governance gates.

Legal & Compliance#ai governance#human approval#trust tier#companion rules#CI validators#documentation artifacts#sensitive paths
Authorunclenate
Version1.0.0
Installs0

System Documentation

What problem does it solve?

It prevents AI-assisted development from skipping required human approval, documentation, and validation when changes touch sensitive or lifecycle-critical areas.

Core Features & Use Cases

  • Trust Tier Enforcement: Classifies actions into six tiers (read-only to remote/production) so higher-risk work requires authorization and appropriate sign-off.
  • Companion Rule Requirements: Ensures sensitive trigger changes also include required companion documentation in the same PR/commit.
  • Lifecycle Controls & Validator Workflow: Defines what “Bootstrap Complete” and “Harness Ready” mean and provides the expected validator chain and exit-contract behavior.
  • Operational Guidance for Governance Entrypoints: Covers when to update harness entry files and how to validate skill content, documentation drift, and sensitive path coverage.

Quick Start

Use the harness-governance skill to determine whether your proposed change is Tier 4 or Tier 5 and what companion artifact(s) are required before you commit or open a PR.

Dependency Matrix

Required Modules

None required

Components

Standard package

💻 Claude Code Installation

Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.

Please help me install this Skill:
Name: harness-governance
Download link: https://github.com/unclenate/auto-harness/archive/main.zip#harness-governance

Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
View Source Repository

Agent Skills Search Helper

Install a tiny helper to your Agent, search and equip skill from 471,000+ vetted skills library on demand.