A local message system for AI agents to communicate across projects, with a web interface similar to a team chat.

It is for sending agent-to-agent messages, assigning and tracking tasks, coordinating projects, viewing inboxes and timelines, and using commands such as /main and /listen.

It helps agents exchange requests and updates asynchronously while keeping conversations, tasks, routing, and activity visible.

agent-bus — Plugin by MustaphaSteph

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Claude Code

/plugin marketplace add MustaphaSteph/agent-bus-plugins

agentmods

npx agentmods add plugins/mustaphasteph/agent-bus-plugins/agent-bus

Clone the repo

git clone --depth 1 https://github.com/MustaphaSteph/agent-bus-plugins

Made for: Claude Code.

Per session not measured What this adds to a session before it is invoked.

When invoked not measured Not applicable: nothing here is loaded into a session.

Security scan A 0 findings. Scan, not verified.

Origin original No closer match found in the catalogue.

Security

Grade A, and why

agent-bus scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

claude-code/plugins/agent-bus/.claude-plugin/plugin.json · 12 lines

What it actually says

{
  "name": "agent-bus",
  "version": "0.32.0",
  "description": "Local message bus for AI agent-to-agent communication. Adds 65 MCP tools and a Slack-style multi-project local web cockpit, including async asks, team-scoped routing, tracked tasks, truncation-safe inbox previews, activity timelines, the agent-bus coordinator skill, /main and /listen slash commands, and a Stop hook for listener resilience.",
  "author": {
    "name": "Mustapha Achtaou",
    "url": "https://github.com/MustaphaSteph"
  },
  "homepage": "https://github.com/MustaphaSteph/agent-bus",
  "license": "MIT"
}

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

yesterday First seen · 12 lines scan A aab701920d8a

Subscribe to this mod's changes

agent-bus is a plugin published in the GitHub repository MustaphaSteph/agent-bus-plugins (1 stars, last pushed 2mo ago), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Productivity agent-orchestration agent-skills agent-to-agent claude-code claude-code-plugin codex

agent-bus

Getting it into your agent

Grade A, and why

Nothing flagged

What it actually says

What this file has done since we first saw it

Other plugins, from other repositories

connector-claude-code

spacedock

teamctl

claude-md-management-hames

vibe-flow

refactoring-legacy