# agent-bridge

> agent-bridge — raysonmeng-agent-bridge. Use this tool when you need to facilitate real-time collaboration between Claude Code and Codex, enabling seamless bidirectional exchange of code and ideas. It solves problems of isolated development environments and limited feedback loops, providing a local bridge for efficient cooperation. Ideal for projects requiring simultaneous input from both Claude Code and Codex, with git integration for version control.

Canonical page: https://skillsregistry.net/skills/raysonmeng-agent-bridge  
JSON: https://api.skillsregistry.net/v1/skills/raysonmeng-agent-bridge

## Description

A local bridge for bidirectional collaboration between Claude Code and Codex. 连接 Claude Code 与 Codex 的本地实时协作桥接工具。

## Trust

- **Trust score (0–1):** 0.50
- **Verification tier:** unverified

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** container
- **Runtime environment:** vm
- **Updated:** 2026-09-27

## Source

- **Source listing:** [GitHub](https://github.com/raysonmeng/agent-bridge)

## 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": "raysonmeng-agent-bridge"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/raysonmeng-agent-bridge` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/raysonmeng-agent-bridge/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