mcpField
H
harness-genome

harness-genome

github.com/ruvnetAgent workflows80.0k236 installsUpdated today
Repository

About harness-genome

harness-genome is a repository assessment skill that produces a categorical and numeric report, including repository type, agent-topology recommendations, risk, MCP surface, test confidence, and publish readiness. It is intended for repository review and CI checks, with JSON or Markdown output and an optional risk threshold.

Key features

  1. 01Reports repository type and agent topology
  2. 02Measures risk, test confidence, and publish readiness
  3. 03Describes MCP surface area
  4. 04Preserves upstream verdict and exit code
  5. 05Supports risk-threshold alerts and Markdown output

Use cases

  1. 01Assess a repository before scaffolding a harness
  2. 02Track changes in agent-topology recommendations
  3. 03Fail CI when risk exceeds a set threshold

MCP support

The report includes an MCP surface-area field; the skill does not state that it exposes MCP tools or manages MCP servers.

Install

Copy the command and run it in a terminal.

$npx skills add https://github.com/ruvnet/ruflo --skill harness-genome

After installing, type/harness-genomein Claude Code to confirm it loaded.

Details

From the project README

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

Comments

Markdown supported