AnastasiyaW

Mclaude — Communication skill for Claude Code

Communication community

Multi-session collaboration for Claude Code: atomic locks, handoffs, memory graph, messaging, hub server, bridge, voice I/O. 166 tests.

How to install Mclaude

This entry records only its repository, not the path inside it, so there is no exact command to give. Open AnastasiyaW/mclaude and copy the folder into ~/.claude/skills/, or the file into ~/.claude/agents/.

What Mclaude does

Multi-session collaboration for Claude Code: atomic locks, handoffs, memory graph, messaging, hub server, bridge, voice I/O. 166 tests. Zero core deps.

Alternatives in Communication

HolaOS — Open-source agentic workspace enterprises can make their own 10.9k ★
Hermes Bot Mode — Bot Mode for the Hermes desktop: a roster of named agents with their own chats, avatars, routines, and bot-to 650 ★
Claude Skill Social Post — A Claude Code skill by Hao (駱君昊) that learns your Facebook voice and auto-posts to FB / IG / Threads / X with 625 ★

README

mclaude

**Multi-session collaboration for Claude Code and other AI coding agents.**

When you have two Claude chats open on the same project - or two teammates running Claude Code at the same time, or yourself switching between laptops - you eventually hit the same problem: *whose turn is it, what has already been done, and how do I find out without interrupting?*

mclaude is a small, file-based system that answers those questions. It does not replace your agent. It gives your agents a shared notebook, a shared lock box, a shared memory shelf, and a shared address book - all living as plain markdown and JSON inside your project.

Seven file-based layers (zero dependencies) plus optional network, desktop, and audio extensions.

The problem in one scene

**Monday, 10:04 AM.** You ask Claude to fix a bug in `auth/middleware.py`.

**Monday, 10:07 AM.** Your teammate, on their own laptop, asks their Claude to do the same thing. Neither Claude knows about the other.

**Monday, 10:12 AM.** Both PRs open. Both delete the same function. Your merge conflicts, their test fails, and nobody understands why because the "decisions" live in two separate chat histories nobody has permission to read.

mclaude turns this into:

**Monday, 10:04 AM.** Your Claude claims work on `fix-auth-middleware-race`. A lock file appears in `.claude/locks/`.

**Monday, 10:07 AM.** Your teammate's Claude tries to claim the same slug, sees the lock, reads the `description`, and tells your teammate: *"ani is already working on this since 10:04, description says 'race condition in session write'. Want to wait, help, or pick another task?"*

**Monday, 10:12 AM.** Your Claude finishes, releases the lock with a summary, writes a handoff. Teammate's Claude reads the handoff, continues the work on a different file, extends the fix with tests.

No merge conflicts. No lost context. No "wait, why did they do it this way?" - the decisions are in the handoff.