# On_Board

> On_Board — swisspra-on-board. Use this tool when you need to enable seamless collaboration between multiple AI agents, such as Claude, Cursor, Codex, and AntiGravity, by providing a shared memory server that allows them to pick up where the last one left off. On_Board solves the problem of interrupted workflows by storing agent outputs in a local `.agent-mem/` folder, ensuring continuity between agents. It is particularly useful in multi-agent projects that require sequential processing and git integration.

Canonical page: https://skillsregistry.net/skills/swisspra-on-board  
JSON: https://api.skillsregistry.net/v1/skills/swisspra-on-board

## Description

Shared memory MCP server for multi-agent projects. Agents (Claude, Cursor, Codex, AntiGravity) write to a local `.agent-mem/` folder so the next agent picks up where the last one died.

## Trust

- **Trust score (0–1):** 0.89
- **Verification tier:** verified
- **Last scanned:** 2026-09-28

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** container
- **Runtime environment:** vm
- **Category:** file-system
- **Updated:** 2026-09-28

## Source

- **Source listing:** [GitHub](https://github.com/swisspra/On_Board)

## 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": "swisspra-on-board"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/swisspra-on-board` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/swisspra-on-board/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