Harness Score
FreeEvaluate repository readiness for harness adoption.
Free · Opens the source repo
What Harness Score does
Harness Score is a skill designed to assess the readiness of a repository for harness adoption by leveraging the metaharness score command-line interface. It provides a comprehensive scorecard that includes metrics such as harness fit, compile confidence, task coverage, tool safety, and memory usefulness. By running the command metaharness score <path>, users can obtain a detailed JSON output that helps them understand the viability of implementing harness in their projects. This skill is particularly useful for developers and teams looking to make informed decisions about adopting harness frameworks in their workflows.
The skill operates by invoking a subprocess to execute the metaharness score command, with a hard timeout of 60 seconds to ensure responsiveness. It gracefully handles scenarios where the metaharness tool is not available, providing a clear message and exit code, which allows Ruflo to continue functioning without disruption. This feature is crucial for maintaining workflow continuity, especially in environments with limited network access.
The output includes several key dimensions that provide insight into the repository's readiness. For example, the harness fit score indicates how well the repository aligns with harness requirements, while compile confidence reflects the likelihood of successful builds. Additionally, the estimated cost per run and scaffold readiness are valuable for project planning and resource allocation. Developers can integrate this skill into their continuous integration pipelines, enabling automated checks that can fail builds based on predefined thresholds for harness fit.
Overall, Harness Score is an essential tool for developers who want to ensure their repositories are primed for harness adoption, facilitating smoother transitions and more efficient project management.
When to use it
Use this skill when you need to evaluate a repository's readiness for harness adoption before initializing or minting a harness project.
When not to use it
Avoid using this skill if you do not have access to the `metaharness` tool, as it relies on it for functionality and will not provide meaningful results without it.
What you can build with it
Pre-Adoption Assessment
Before adopting harness, use this skill to evaluate the repository's readiness and identify potential issues.
Continuous Integration Checks
Integrate the skill into your CI pipeline to automatically check harness fit and enforce build quality.
Resource Planning
Utilize the estimated cost per run metric to inform resource allocation and budgeting for harness-related projects.
How to install Harness Score
View source1. Install with the skills CLI
npx skills add ruvnet/ruflo/harness-score --agent claude-code2. 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 ruvnetSurfaces the upstream metaharness score CLI as a ruflo skill. Use when
Claude Code needs to assess whether a repo is ready for harness adoption
before recommending the user run npx ruflo init or harness-mint.
Algorithm
Implementation: scripts/score.mjs.
- Shell out to
npx metaharness score <path> --json(single subprocess, 60s hard timeout). - Parse the JSON shape:
{ harnessFit, compileConfidence, taskCoverage, toolSafety, memoryUsefulness, estCostPerRunUsd, recommendedMode, archetype, template, scaffoldReady, hardConstraints }. - If
--alert-on-fit-below N: exit 1 whenharnessFit < N. - Output JSON (default) or markdown table.
Phase-0 baseline (ruflo's own scorecard, measured 2026-06-16)
| Dimension | Value |
|---|---|
| harnessFit | 82/100 |
| compileConfidence | 100 |
| taskCoverage | 79 |
| toolSafety | 100 |
| memoryUsefulness | 40 |
| estCostPerRunUsd | $0.048 |
| recommendedMode | CLI + MCP |
| archetype | typescript-sdk-harness |
| template | vertical:coding |
| scaffoldReady | true |
Ruflo passes its own readiness check. memoryUsefulness: 40 is the
weakest dimension — track this as a leading indicator for future memory
work in the AgentDB layer.
CI integration
node plugins/ruflo-metaharness/scripts/score.mjs --alert-on-fit-below 70 --format json
Exit 1 fails the build. Pair with harness-genome for the full
7-section view.
Graceful degradation (ADR-150 architectural constraint rule #3)
When metaharness is not installed and npx can't fetch it (offline,
no network, registry unreachable), the script emits:
{
"degraded": true,
"reason": "metaharness-not-available",
"hint": "Install with `npm i -D metaharness@~0.3.0` (pinned range — this plugin never fetches @latest) or verify network access for the one-time cache install."
}
and exits 0. Ruflo continues to function — this is the architectural constraint in action.
Frequently asked questions about Harness Score
Similar skills
Turborepo
Optimized build system for JavaScript/TypeScript monorepos.
Azure Pipelines Validation
Streamline your Azure DevOps pipeline changes locally.
Azure Developer CLI
Streamline your Azure project workflows with best practices.
Azure Container Registry CLI
Manage Azure Container Registry resources with ease.
Aspire
Build and orchestrate polyglot distributed applications seamlessly.
Vercel CLI
Manage and deploy Vercel projects from the command line.