harness-doctor

Diagnose structural health, complexity, drift, and pattern issues in Claude Code project harnesses.

7|Updated May 26, 2026
One-click install
npx skills add https://github.com/chrono-meta/forge-harness --skill harness-doctor-chrono-meta
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: harness-doctor
Source: https://github.com/chrono-meta/forge-harness/tree/main/plugins/fh-meta/skills/harness-doctor
Command: npx skills add https://github.com/chrono-meta/forge-harness --skill harness-doctor-chrono-meta

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Manually auditing a Claude Code project's harness structure for missing files, outdated rules, broken references, and complexity bloat is time-consuming and error-prone. This skill automates that diagnosis across 5 key layers, giving you a clear, prioritized list of issues to fix so your AI project setup stays lean and functional.

Core Features & Use Cases

  • 5-Layer Structural Diagnosis: Checks for required file existence, complexity thresholds, drift between rules and actual usage, connection consistency for Forge Harness environments, and skill activity/pattern appropriateness.
  • Optional Language Lint Mode: Scans skill and agent documentation for self-marketing language, cushion words, version brags, and missing "Done When" sections to improve documentation quality.
  • Prescription Reports & Integrations: Generates prioritized M/S/R (Immediate/Strongly Recommended/Recommended) fix reports, integrates with weekly harvest-loop audits, and includes regression guards and PR change consistency checks to prevent harness modifications from breaking existing functionality.
  • Use Case: If your Claude Code project's setup has grown bloated, rules are outdated, or skills aren't triggering as expected, run this skill to get an actionable list of exactly what to adjust first.

Quick Start

Request a harness structure diagnosis for your current Claude Code project to receive a prioritized list of structural issues and actionable improvement prescriptions.

Frequently Asked Questions about harness-doctor

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

FAQPage Schema
How do I audit Claude Code project harnesses for structural drift and complexity bloat?

You can diagnose Claude Code harness health by running an automated 5-layer structural diagnosis that checks file existence, complexity thresholds, drift between rules and usage, and connection consistency, producing a prioritized fix report.

Why are my Claude Code skills not triggering and how can I fix the agent configurations?

Skills may not trigger due to structural health issues, outdated rules, or pattern drift in agent configurations. Running a harness diagnosis identifies these specific pattern appropriateness and connection consistency issues, providing actionable prescriptions to restore functionality.

Does this tool work with Forge Harness environments for connection analysis?

Yes, the harness diagnosis applies to Forge Harness (FH) environment projects for connection and pattern analysis, and also supports standard Claude Code projects for core structural and drift checks.

How do I prevent harness modifications from breaking existing functionality during PRs?

You can prevent breaking changes by running regression guards and PR change consistency checks that validate harness modifications against operational functionality, ensuring structural updates do not break existing rules or agent configurations.

What is the best way to prioritize fixes for a bloated Claude Code project setup?

The best way to prioritize fixes is to generate a prescription report that categorizes structural issues into M (Immediate), S (Strongly Recommended), and R (Recommended) priorities, giving you a clear order of operations to lean out the harness.