skills.rest
jh941213
jh941213COMMUNITY
Explore all skills by this author →
WebsiteGitHub

harness-audit

Diagnose Claude Code harness health across eight evaluation dimensions.

125|35|Updated Jan 21, 2026
Search Tags:#automation#audit#metrics#governance#health#claude-code#harness
One-click install
npx skills add https://github.com/jh941213/my-cc-harness --skill harness-audit-jh941213
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: harness-audit
Source: https://github.com/jh941213/my-cc-harness/tree/main/skills/harness-audit
Command: npx skills add https://github.com/jh941213/my-cc-harness --skill harness-audit-jh941213

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Diagnose the overall health of the Claude Code harness across eight evaluation dimensions to surface weaknesses and improvement opportunities.

Core Features & Use Cases

  • Eight-dimension health scoring across CLAUDE.md quality, Skills coverage, Agents architecture, Hooks automation, Rules structure, MCP capabilities, Eval pipeline, and Team/Mult-Agent readiness.
  • Generates per-dimension scores (0-3) and an overall grade, with actionable recommendations for tightening governance and automation.
  • Useful during harness configuration reviews, audits, and system health checks to drive maintenance and risk mitigation.

Quick Start

Run the harness-audit command to generate a health report for your Claude Code harness and apply recommended improvements.

Frequently Asked Questions about harness-audit

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I audit Claude Code harness health and configuration?▼

To audit Claude Code harness health, run the harness-audit command to generate a structured health report. It evaluates eight dimensions including CLAUDE.md quality, Skills coverage, and Hooks automation, producing per-dimension scores and an overall grade.

What is evaluated in a Claude Code harness health check?▼

A Claude Code harness health check evaluates eight dimensions: CLAUDE.md quality, Skills coverage, Agents architecture, Hooks automation, Rules structure, MCP capabilities, Eval pipeline, and Team/Multi-Agent readiness. Each dimension receives a deterministic score from 0 to 3.

How do I improve Claude Code governance and automation metrics?▼

You can improve Claude Code governance and automation metrics by running a harness audit to identify weak dimensions. The resulting health report provides actionable recommendations to tighten configuration, enhance risk mitigation, and drive system maintenance.

Can I use a structured health report for Claude Code risk mitigation?▼

Yes, you can use a structured health report for Claude Code risk mitigation. The audit generates standardized output formats with per-dimension scores and an overall grade, making it suitable for governance reviews and identifying configuration weaknesses.

Does the Claude Code audit support multi-agent readiness evaluation?▼

Yes, the Claude Code audit supports multi-agent readiness evaluation. Team and Multi-Agent readiness is one of the eight evaluation dimensions scored during the harness health check to determine if your architecture supports collaborative agents.

Related Skills

Explore More Software Engineering Skills→
Growthub-aiGrowthub-ai
48

growthub-t3code-harness

Manage T3 Code harness health checks, prompts, and sessions within Growthub.

Official
Advanced
henryavilahenryavila

codeguard-health

Assess CodeGuard health in PHP-Laravel projects without making changes.

Community
Advanced
rodmena-limitedrodmena-limited
3

moai-foundation-claude

Create, configure, and manage Claude Code Skills with templates and tools.

Official
Advanced
robertzengcnrobertzengcn

health

Aggregate code quality metrics from multiple tools into a weighted 0-10 composite score.

Community
Advanced