# OpenHarness

> Use this tool when you need to enable seamless collaboration between AI coding agents without disrupting existing workflows. OpenHarness solves the problem of cross-referencing session files by discovering and sharing file paths locally, allowing agents to access and utilize each other's data. It takes in session file information as input and outputs shared file paths, making it ideal for use cases where multiple AI agents need to work together efficiently.

Canonical page: https://skillsregistry.net/skills/philo-kim-openharness  
JSON: https://api.skillsregistry.net/v1/skills/philo-kim-openharness

## Description

A local MCP server that discovers and shares session file paths between AI coding agents, enabling cross-referencing without modifying existing workflows.

## Trust

- **Trust score (0–1):** 0.70
- **Verification tier:** verified
- **Last scanned:** 2026-08-31

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** file-system
- **Updated:** 2026-08-31

## Source

- **Source listing:** [Glama](https://glama.ai/mcp/servers/ulbvna3v4q)
- **Repository:** <https://github.com/philo-kim/openharness>

## Use it

Resolve this record through the SkillsRegistry MCP server (no auth, read-only):

```
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp
```

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "get_skill",
    "arguments": {
      "slug": "philo-kim-openharness"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/philo-kim-openharness` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/philo-kim-openharness/pull`

---
SkillsRegistry indexes agent skills from public registries and GitHub. Skills we have analysed are scanned with Circle-IR and scored on six dimensions; each listing states its scan coverage. More: https://skillsregistry.net/llms.txt