agent-mail

Enables asynchronous messaging between agents via on-disk mailboxes.

5|Updated Jun 3, 2026
One-click install
npx skills add https://github.com/vinceferro/claude-kickoff --skill agent-mail-vinceferro
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: agent-mail
Source: https://github.com/vinceferro/claude-kickoff/tree/main/plugin/skills/agent-mail
Command: npx skills add https://github.com/vinceferro/claude-kickoff --skill agent-mail-vinceferro

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires python3, bash, jq, and includes scripts (resource) components.

What problem does it solve?

This skill removes the human bottleneck when multiple autonomous agents on the same machine need to share findings, bugs, or cross-repo intelligence without manual relaying.

Core Features & Use Cases

  • Agent-to-Agent Transport: Enables direct, file-based communication between separate project directories.
  • Context Preservation: Allows agents to send actionable findings with evidence and citations without interrupting their primary workflow.
  • Use Case: When an agent discovers a bug in shared tooling that affects a sibling project, it uses this skill to drop a structured report into the recipient's inbox for their next re-ground check.

Quick Start

Use the agent-mail skill to send a report about the identified dependency issue to the sibling project directory named core-utils.

Frequently Asked Questions about agent-mail

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I share bug reports between autonomous agents working in different local project directories?

Agent-to-agent messaging shares bug reports between local project directories by writing structured markdown messages to local mailboxes, allowing autonomous agents to exchange findings without manual human relaying.

Can I use asynchronous messaging to hand off tasks between independent agent workspaces on the same machine?

Yes, asynchronous messaging supports task handoffs between independent agent workspaces by delivering structured markdown messages to local mailboxes, enabling cross-repo intelligence sharing on the same machine.

Do I need python3 and bash to set up inter-process communication for autonomous agents?

Yes, you need standard python3 and bash execution capabilities to manage inter-process communication, message delivery, and status tracking for autonomous agents operating within a local environment.

What is the best way to preserve context and citations when an agent reports a dependency issue to a sibling project?

The best way to preserve context is using file-based communication to send actionable findings with evidence and citations directly to a recipient's inbox, ensuring the receiving agent processes the report during its next re-ground check.

How does file-based messaging work for cross-repo intelligence sharing without interrupting an agent's primary workflow?

File-based messaging works by writing structured markdown messages to local mailboxes, allowing agents to drop intelligence reports without interrupting their primary workflow, which the recipient retrieves asynchronously.

When should I not use local mailboxes for agent-to-agent communication?

You should not use local mailboxes for agent-to-agent communication when autonomous agents operate across different machines or remote environments, as this approach relies on a single local environment and file-based transport.