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.

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.

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.

komnet — Plugin for Claude Code by Komdosh

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.

Clone the repo

git clone --depth 1 https://github.com/Komdosh/komnet

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/plugins/komdosh/komnet/claude/github.svg)](https://agentmods.dev/plugins/komdosh/komnet/claude)

Your own site

<a href="https://agentmods.dev/plugins/komdosh/komnet/claude"><img src="https://agentmods.dev/badge/plugins/komdosh/komnet/claude/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/plugins/komdosh/komnet/claude"><img src="https://agentmods.dev/badge/plugins/komdosh/komnet/claude.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

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

When invoked not measured The manifest loads nothing itself; its 7 skills, 1 command, 1 agent, 1 MCP server cost 940 tokens a session between them.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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 1mo 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"]
}

Contents

What it installs

The manifest is a name and a version. 7 skills, 1 command, 1 agent, 1 MCP server travel with it, and installing the plugin installs all of them — 940 tokens a session between them. Each is measured on its own page, and each can be installed alone.

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.

1mo 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 (8 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.

Building agents Claude Code Project management agent-communication agentic-ai ai-agents claude codex

before-you-build

Pre-build product risk review for founders, product teams, and AI-assisted builders before implementation starts.

wshobson/agents · not measured

agentrq-workspace

Workspace agent that executes tasks assigned by humans or supervisors, communicates progress via reply, and manages task lifecycle within a specific AgentRQ workspace.

agentrq/agentrq · not measured

giovanni

AI Chief of Staff runtime: 4-layer memory with hard limits, daily digest with drift detection, stakeholder trajectories, invisible shadow hypotheses, adversarial-default review, and a governance lint that fails the build on contradictions. State lives in your repo; the mechanism lives here.

jaroslavsoucek-art/Giovanni · not measured

g-forge

Educated, enforced project management for AI development - a PM layer, parallel implementation waves, and a git-hook commit gate that can't be skipped. Make any model ship like a senior team.

onlygian/G-Forge · not measured

ooda-loop marketplace

Plugin marketplace listing 1 plugin: ooda-loop.

mataeil/OODA-loop · not measured

asana

Asana project management integration. Connects Claude Code to Asana's V2 MCP server (https://mcp.asana.com/v2/mcp) to create and manage tasks, search projects, update assignments, and track progress. Requires a one-time setup of your own Asana OAuth app — run /asana-setup after installing.

mostwise/dot-claude · not measured