Agents Msger — AI skill for Claude Code
Cross-machine, cross-network message passing between AI coding-agent sessions — connect context, talk, and reach the agent responsible for a project.
How to install Agents Msger
This entry records only its repository, not the path inside it, so there is no
exact command to give. Open GeojoL/agents-msger and copy the folder into
~/.claude/skills/, or the file into ~/.claude/agents/.
What Agents Msger does
Cross-machine, cross-network message passing between AI coding-agent sessions — connect context, talk, and reach the agent responsible for a project. Built on Claude Code's own cross-session messaging, exposed as MCP tools.
Alternatives in AI
- Cursor Talk To Figma MCP — TalkToFigma: MCP integration between AI Agent (Cursor, Claude Code, Codex) and Figma, allowing Agentic AI to c 7k ★
- Agmsg — Cross-vendor messaging for CLI AI coding agents — let Claude Code, Codex, Gemini & Copilot talk to each other 1.5k ★
- DontFeedTheAI — Transparent anonymization proxy for AI-assisted pentesting 654 ★
README
agents-msger
**A shared line for AI agents — connect context, talk to each other, and reach whoever owns a project. Across machines, across networks.**
[](LICENSE) [](#requirements) [-brightgreen.svg)](#requirements) [](#requirements) [](#project-status) [](#supported-agents)
The problem
Claude Code already has **cross-session messaging**: sessions on the *same machine* can deliver messages to each other through Claude Code's own messaging socket. But that stops at the edge of one machine. The moment your agents live on different machines — or on different networks — there is no path between them: no way to hand context across, no way to ask and get an answer back, and no way to reach *the* agent that owns a project running somewhere else.
**`agents-msger` extends Claude Code's own messaging across machines and networks.** It does not reinvent agent messaging — it reuses Claude Code's native cross-session delivery and adds the one missing piece: a hub + per-machine shim that carries those same messages between machines, over any network that can reach the hub.
What it does
- 🔗 Connect context. Any agent session can send its context — a summary, a decision, a hand-off — directly into another agent's session, on the same machine or a different one. The receiving agent picks it up on its next turn.
- 💬 Communicate. Every delivered message carries who sent it — persona, machine, window, and pid. So a back-and-forth is natural: the recipient knows exactly which agent (and which session) t
Related Skills
Agents Can Communicate
Let your AI coding sessions talk to each other. Coordinate parallel work, exchange reviews, and hand off unfin
Neo Agent Brain
Point a cross-model AI engineering team at your own codebases. The Agent OS keeps named AI maintainers' identi
Cc Connect
Bridge local AI coding agents (Claude Code, Cursor, Gemini CLI, Codex) to messaging platforms (Feishu/Lark, Di
Pollen
peer messaging between AI agents, with a human at the gate — one file, zero dependencies.
V1claw
V1Claw is a self-hosted AI assistant that runs on your Mac, Linux, Windows, or Android via Termux. Connect any
AgentBBS
A multiplayer ai community where humans hang out in a web app and agents connect over SSH or MCP — sharing the
Related Agents
Architecture Risk Simulator
Architecture Risk Simulator for the team-agents workflow — responsible for analyzing architecture under stress
Actor Model
Domain knowledge for the actor architecture, message passing, and connection handling
Bridge Specialist
Bridge-specific specialist. Native bridges, optimistic bridges, validator-set bridges, LayerZero/CCIP/Wormhole