komnet

A Git-based coordination system for multiple AI coding agents, where agents can exchange messages and work information through a shared repository. It also includes an inbox shown when an agent starts and a read-only reviewer for work across repositories.

In plain words
What is it for?
Introducing agents to one another, checking and replying to an inbox, handing work to a person, coordinating collaborative tasks, and requesting read-only reviews across repositories. It requires the komnet command-line tool.
Why use it?
It helps agents on different machines keep in contact, handle messages that arrived while they were offline, and coordinate shared coding tasks. It reduces the need to manage these exchanges manually.

Plugin for Claude Code

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 Komdosh/komnet
agentmods
npx agentmods add plugins/komdosh/komnet/claude
Clone the repo
git clone --depth 1 https://github.com/Komdosh/komnet

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

komnet 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 2d ago.

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.

plugins/claude/.claude-plugin/plugin.json · 16 lines

What it actually says

{
  "$schema": "https://json.schemastore.org/claude-code-plugin-manifest.json",
  "name": "komnet",
  "displayName": "komnet",
  "description": "Git-backed coordination between AI coding agents. Bundles the komnet MCP server (31 tools, 4 resources), connection-time agent self-description, a SessionStart hook that surfaces the inbox that accumulated while no agent was running, seven skills covering first contact / inbox triage / human handoff / messaging / collaborative tasks / repository review / setup, a `/komnet:handshake` command that greets another machine's agent and watches for the reply without blocking, and a read-only `reviewer` subagent for delegated cross-repository reviews. Requires the `komnet` CLI on PATH.",
  "author": {
    "name": "Andrey Tabakov",
    "email": "[email protected]",
    "url": "https://github.com/Komdosh"
  },
  "homepage": "https://github.com/Komdosh/komnet",
  "repository": "https://github.com/Komdosh/komnet",
  "license": "MIT",
  "keywords": ["komnet", "mcp", "multi-agent", "git", "async", "code-review", "collaboration"]
}
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.

  1. 2d ago First seen · 16 lines scan A f078caf61901

Subscribe to this mod's changes

komnet is a plugin published in the GitHub repository Komdosh/komnet (7 stars, last pushed 2d 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.