New to Claude Skills? Learn how to install them →

Get Claude Skills
ruvnet on GitHub

Harness Genome

Free

Evaluate repo readiness with a detailed report.

by ruvnet67.6k stars on ruvnet/ruflo
Updated Aug 10, 2026
Get this skill

Free · Opens the source repo

What Harness Genome does

Harness Genome is a tool designed to provide a comprehensive readiness report for software repositories. By executing the command metaharness genome <path>, it generates a 7-section report that includes crucial metrics such as repo type, agent topology recommendations, risk score, MCP surface area, test confidence, and publish readiness. This tool is particularly useful for developers and teams looking to assess the viability of a repository before proceeding with further development or deployment.

The tool works by invoking the metaharness command-line utility, which analyzes the specified repository and returns data in either JSON or markdown format. The report includes a risk score ranging from 0 to 1, indicating the potential risks associated with the repository, and a publish readiness score that reflects how prepared the repo is for deployment. Additionally, it captures agent topology recommendations, which can guide teams in structuring their development efforts based on the repository's characteristics.

Harness Genome is ideal for pre-mint reviews, allowing teams to make informed decisions about whether to scaffold a custom harness from the repository. It also supports drift detection by enabling teams to capture snapshots of the repo's genome over time, facilitating the identification of changes in agent topology recommendations. Furthermore, it can serve as a continuous integration (CI) gate, where users can set thresholds for risk scores to automate build failures when risks exceed acceptable levels.

This skill is particularly suited for developers and DevOps teams who need a reliable method to evaluate repository readiness and manage risks effectively. By integrating with other tools like Harness Score and Harness MCP Scan, it enhances the overall assessment process, ensuring a robust development lifecycle.

When to use it

Use this skill when evaluating a repository's readiness for development or deployment, especially during pre-mint reviews or CI processes.

When not to use it

This tool may not be suitable for repositories that do not require detailed readiness assessments or for teams not using the metaharness framework.

What you can build with it

Pre-Mint Review

Use Harness Genome to evaluate whether to scaffold a custom harness from a repository before proceeding.

Drift Detection

Capture snapshots of the repository's genome over time to identify changes in agent topology recommendations.

CI Integration

Set up CI pipelines to fail builds automatically when the repository's risk profile exceeds a defined threshold.

How to install Harness Genome

View source

1. Install with the skills CLI

npx skills add ruvnet/ruflo/harness-genome --agent claude-code

2. Or install it manually

Download the skill folder and drop it into ~/.claude/skills/ for all projects, or .claude/skills/ to scope it to one repo. Restart Claude Code so it picks up the new skill.

Anthropic's agentic coding CLI, and the reference implementation of Agent Skills. Drop a skill folder into ~/.claude/skills and Claude Code loads it automatically whenever a task matches the skill's description. Claude Code docs

Inside SKILL.md

Written by ruvnet

Companion to harness-score. Where score is a 5-dimension numeric scorecard, genome is a 7-section categorical/numeric report covering repo type, agent topology recommendations, risk score (0-1), MCP surface area, test confidence (0-1), and publish readiness (0-1).

Algorithm

Implementation: scripts/genome.mjs.

  1. Shell out to npx metaharness genome <path> --json (60s hard timeout).
  2. Parse the shape: { repo_type, agent_topology[], risk_score, mcp_surface, test_confidence, publish_readiness }.
  3. Preserve upstream's readiness verdict as verdict and verdictExitCode. Upstream exits 1 for needs-work and 2 for blocked; these are valid reports, so the wrapper returns them successfully.
  4. If --alert-on-risk-above N: exit 1 when risk_score > N.
  5. Output JSON (default) or markdown.

Phase-0 baseline (ruflo, measured 2026-06-16)

{
  "repo_type": "node_mcp_ci",
  "agent_topology": ["maintainer", "tester", "security", "release"],
  "risk_score": 0.27,
  "mcp_surface": "remote",
  "test_confidence": 0.8,
  "publish_readiness": 0.9
}

Ruflo's risk_score: 0.27 is low (good). publish_readiness: 0.9 is high. The mcp_surface: "remote" reflects that ruflo's MCP servers are hosted, not bundled.

When to use

  • Pre-mint review: "before scaffolding a custom harness from this repo, should we?" — genome answers it categorically.
  • Drift detection: capture genome snapshots over time, diff via cost-diff-style tooling to spot when agent_topology recommendations drift away from a deliberate architecture choice.
  • CI gate: --alert-on-risk-above 0.5 fails the build when the repo's risk profile crosses a threshold.

Pairs with

  • harness-score — numeric readiness
  • harness-mcp-scan — static MCP security findings
  • harness-threat-model — enterprise-review-grade threat model

Frequently asked questions about Harness Genome

Similar skills

Quality Playbook Generator

Run comprehensive quality audits on any codebase.

PR Draft Summary

Automate PR summary generation for openai-agents-python.

Final Release Review

Streamline your release candidate audits with ease.

Unit Test Vue Pinia

Efficiently write and review unit tests for Vue 3 applications.

Slang Shader Expert

Optimize and integrate Slang shaders with ease.

Telemetry Standards

Ensure consistent event tracking in Supabase Studio.