# agenthold

> Use this tool when you need to manage shared state across multiple AI agents, enabling seamless collaboration and version control in complex workflows. Agenthold solves problems of data inconsistency and synchronization, providing a unified interface for agents to access and update shared state. It accepts input from multiple agents, maintains versioned state, and outputs the current state to authorized agents.

Canonical page: https://skillsregistry.net/skills/io-github-edobusy-agenthold  
JSON: https://api.skillsregistry.net/v1/skills/io-github-edobusy-agenthold

## Description

Shared versioned state for multi-agent AI workflows

## Trust

- **Trust score (0–1):** 0.82
- **Verification tier:** verified
- **Last scanned:** 2026-09-28

## Facts

- **Version:** 0.4.3
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** other
- **Updated:** 2026-09-28

## Source

- **Source listing:** [MCP Registry](https://registry.modelcontextprotocol.io/v0/servers/io.github.edobusy%2Fagenthold)
- **Repository:** <https://github.com/edobusy/agenthold>

## 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": "io-github-edobusy-agenthold"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/io-github-edobusy-agenthold` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/io-github-edobusy-agenthold/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