New to Claude Skills? Learn how to install them →

Get Claude Skills
Hruvnet on GitHub

Harness Mint

Free

Easily scaffold custom AI agent harnesses.

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

Free · Opens the source repo

What Harness Mint does

Harness Mint is a command-line tool designed for developers looking to scaffold custom AI agent harnesses efficiently. By utilizing the metaharness command, users can create a new directory structure tailored to their specific needs with a simple command. The tool emphasizes safety and control, defaulting to a dry-run mode that allows users to preview actions before any changes are made. This ensures that users can verify their configurations and targets without risk of accidental modifications to their working directories.

The functionality is straightforward: users specify a name for their harness, choose a template from a variety of options, and define a host. The tool then validates these inputs and checks for safety conditions, such as ensuring that the target directory does not exist and is not within the current project root. If everything checks out, users can proceed with the actual scaffold by adding a confirmation flag, ensuring that destructive actions are only taken when explicitly authorized.

This skill is particularly useful for developers and designers who are creating AI agents across various domains, including coding, devops, legal, and more. With a wide range of templates available, users can quickly set up harnesses that fit their specific vertical needs, streamlining the initial setup process and allowing them to focus on the development of their AI functionalities.

Overall, Harness Mint serves as a reliable tool for those looking to efficiently scaffold AI agent harnesses while maintaining strict safety protocols, making it an essential addition for developers working within the AI landscape.

When to use it

Use Harness Mint when you need to quickly scaffold a new AI agent harness without risking changes to your current project.

When not to use it

This tool is not suitable for users who require in-process execution or those who need to overwrite existing directories, as it strictly avoids such operations.

What you can build with it

Setting Up a New AI Project

When starting a new AI project, use Harness Mint to quickly scaffold the necessary directory structure without risking your current work.

Creating Specialized AI Agents

If you need to create an AI agent for a specific domain, such as legal or education, Harness Mint allows you to select from various templates tailored to those fields.

Ensuring Safe Development Practices

Leverage Harness Mint's dry-run feature to ensure that your setup actions are safe and correct before executing any changes.

How to install Harness Mint

View source

1. Install with the skills CLI

npx skills add ruvnet/ruflo/harness-mint --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

The one write-capable skill in the plugin. Every other skill is pure-read. This one calls metaharness new, which writes a new directory tree.

Safety (load-bearing)

  1. Dry-run by default. Without --confirm, the script prints what it would do and exits 0 without touching disk.
  2. Refuses project root. If --target resolves to the current working directory OR any path inside it, the script errors out with exit 2. Target must be an absolute path OUTSIDE the calling repo (default is a fresh /tmp/ruflo-mint-<ts>-<name>/ dir).
  3. Refuses existing target. Won't overwrite — must scaffold into a non-existent dir.
  4. Subprocess + 60s timeout. No library import, no in-process execution. The mint stays sandboxed from ruflo's runtime.

Algorithm

Implementation: scripts/mint.mjs.

  1. Validate --name, --template. Default --host to claude-code.
  2. Resolve --target (default: temp dir).
  3. Run safety checks (no project-root writes; target must not exist).
  4. Without --confirm: emit dry-run plan, exit 0.
  5. With --confirm: shell npx metaharness new <name> --template <id> --host <id> --target <abs> --yes.

Templates

minimal, vertical:coding, vertical:devops, vertical:support, vertical:legal, vertical:research, vertical:trading, vertical:health, vertical:education, vertical:sales, vertical:business, vertical:crm, vertical:marketing, vertical:advertising, vertical:ai, vertical:agentics, vertical:ruview, vertical:gaming, vertical:repo-maintainer, vertical:exotic.

Hosts

claude-code, codex, pi-dev, hermes, openclaw, rvm, copilot, opencode, github-actions.

Example dry-run

$ node scripts/mint.mjs --name my-harness --template vertical:coding --host claude-code
# harness-mint (dry-run)

- action: metaharness new
- name: my-harness
- template: vertical:coding
- host: claude-code
- target: /tmp/ruflo-mint-1718560000-my-harness
- confirm: false
- willWrite: false

Re-run with `--confirm` to actually scaffold.

Why dry-run by default

Ruflo's behavioral rules say "executing actions with care" — destructive or repo-touching actions need confirmation. The dry-run output makes the WHAT visible before the WHEN. A human sees target, decides, then adds --confirm if happy.

Frequently asked questions about Harness Mint

Similar skills

Rhino 3D Scripting

Streamline your Rhinoceros 3D scripting tasks.

MVVM Toolkit

Streamline ViewModel development with source generators.

FreeCAD Scripts

Generate Python scripts for FreeCAD automation and modeling.

Azure Architecture Builder

Design and deploy Azure infrastructure using natural language.

Command Development

Streamline your command creation for Claude Code.

Create Cowork Plugin

Easily build and package plugins through guided sessions.