Skill2k estrellas del repoactualizado 5d ago

msg

The msg tool enables inter-agent communication between Claude Code sessions and Codex CLI instances running in tmux panes. Use it to register agents, send targeted messages to one or multiple recipients, reply to conversations, and manage an inbox of received messages when coordinating work across multiple coding agent sessions.

Ver fuente Repositorio: claude-code-tools

Instalar en Claude Code

Copiar

git clone --depth 1 https://github.com/pchalasani/claude-code-tools /tmp/msg && cp -r /tmp/msg/plugins/msg/skills/msg ~/.claude/skills/msg

Después abre una sesión nueva de Claude Code; el skill carga automáticamente.

Definición

SKILL.md

# msg: Inter-Agent Communication

You can communicate with other coding agent sessions
(Claude Code or Codex CLI) using the `msg` CLI tool.

## Registration

Before sending or receiving messages, register yourself:

```bash
msg register <your-name>
```

This auto-detects your tmux pane. You only need to do
this once per session.

## Sending Messages

Send a message directly to another agent:

```bash
msg send <agent-name> "Your message here"
```

Send to multiple agents:

```bash
msg send agent1,agent2 "Message for both of you"
```

## Replying

```bash
msg reply <agent-name> "Your reply here"
```

## Receiving Messages

Check your inbox:

```bash
msg inbox
```

This shows all unread messages grouped by thread and
marks them as read.

## Other Commands

```bash
msg list          # List registered agents
msg threads       # List active threads
msg status        # Check system health
```

## Guidelines

- Keep messages concise -- they consume context in the
  receiving agent's session.
- When replying, include enough context that the
  recipient understands without re-reading the full
  thread.
- If you need to share code or file paths, reference
  them in the message text rather than pasting large
  blocks.

Del mismo repositorio

add-patternSkill

Use this skill when you learn one or more design pattern(s) in the

agent-styleSkill

Literature-backed English technical-prose writing rules (agent-style, 21 rules). Its lane is FORMAL technical prose (papers, design docs, proposals, READMEs, commit messages). Use ONLY when the user explicitly asks for agent-style by name (e.g. "apply agent-style", "write/revise this per agent-style rules", "iterate until agent-style clean"). NOT for de-AI-ing casual or voiced text — use remove-ai-patterns for that. Do not auto-trigger for ordinary prose or documentation tasks.

avoid-ai-writingSkill

Audit and rewrite content to remove AI writing patterns ("AI-isms"). Use this skill when asked to "remove AI-isms," "clean up AI writing," "edit writing for AI patterns," "audit writing for AI tells," or "make this sound less like AI." Supports a detect-only mode, an edit-in-place mode for files, an optional voice profile (casual / professional / technical / warm / blunt), and an iterate-to-convergence pass.

code-walk-thruSkill

Use this when user wants you to walk through (code or text) files in a EDITOR to either explain how some code works, or to show the user what changes you made, etc. You would typically use this repeatedly to show the user your changes or code files one by one, sometimes with specific line-numbers. This way the user is easily able to follow along in their favorite EDITOR as you point at various files possibly at specific line numbers within those files.

dynamic-workflowSkill

github-wakeSkill

log-workSkill

Log the work segment that you did after the last work log until now in a

make-issue-specSkill

Create a markdown document that describes a specific task along with