commune-agent-network

commune-agent-network is a skill for Claude Code, Codex from black22345/commune-cookbook. It costs 0 tokens per session (1,096 once invoked), scanned A, original, MIT.

A service that lets AI agents communicate through permanent email inboxes. Agents can send one another tasks and receive replies with the full email thread preserved.

In plain words
What is it for?
Use it to create worker-agent inboxes, send research or other tasks to them, receive results, and keep the history of each task chain.
Why use it?
It allows agents to delegate work without sharing one central memory or building separate coordination infrastructure.

Skill for Claude CodeCodex

Which agent this was written for is unclear — built for openclaw. Also seen: built for openclaw.

Good fit Use it to create worker-agent inboxes, send research or other tasks to them, receive results, and keep the history of each task chain.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/black22345/commune-cookbook/commune-agent-network
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.

Any agent
npx skills add black22345/commune-cookbook --skill commune-agent-network
Clone the repo
git clone --depth 1 https://github.com/black22345/commune-cookbook

Made for: Claude Code, Codex.

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.

agentmods badge for commune-agent-network

README.md
[![agentmods](https://agentmods.dev/badge/skills/black22345/commune-cookbook/commune-agent-network/github.svg)](https://agentmods.dev/skills/black22345/commune-cookbook/commune-agent-network)
Your own site
<a href="https://agentmods.dev/skills/black22345/commune-cookbook/commune-agent-network"><img src="https://agentmods.dev/badge/skills/black22345/commune-cookbook/commune-agent-network/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.

agentmods 80×15 button for commune-agent-network

Your own site · 80×15
<a href="https://agentmods.dev/skills/black22345/commune-cookbook/commune-agent-network"><img src="https://agentmods.dev/badge/skills/black22345/commune-cookbook/commune-agent-network.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 0 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,096 The whole file, excluding the scripts and references it only reads on demand.
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.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00000 $0.01096
Opus 5 $0.00000 $0.00548
Sonnet 5 $0.00000 $0.00219
Haiku 4.5 $0.00000 $0.00110

Measured 9d ago against content hash 3fce735ef85e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

commune-agent-network 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 9d 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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

openclaw-email-sms/skills/commune-agent-network/SKILL.md · 163 lines

How it starts

The opening of the file, as written. The whole thing — 163 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Skill: commune-agent-network

Every OpenClaw agent can become a node in an agent network. Each agent gets a permanent email address. Agents send tasks to each other, receive results as email replies, and maintain full thread history — without shared state or coordination infrastructure.

Authentication

Requires COMMUNE_API_KEY environment variable. Get one at commune.email.

Base URL: https://api.commune.email
Auth header: Authorization: Bearer $COMMUNE_API_KEY

Core Concept

You (WhatsApp)  →  OpenClaw Agent ([email protected])
                         ↓  sends task email
               Researcher Agent ([email protected])
                         ↓  replies with result
               OpenClaw Agent reads full thread
                         ↓
               Reports result back to you

Each agent has one inbox address. Addresses are permanent. The email thread preserves the full task chain.


Operations

Provision a worker agent inbox

POST /v1/inboxes
Body: { "localPart": "researcher" }
Response: { "id": "inbox_xxx", "address": "[email protected]" }

Save the id as COMMUNE_WORKER_INBOX_ID and address as COMMUNE_WORKER_ADDRESS.


Send a task to another agent

POST /v1/messages/send
Body: {
  "to": "[email protected]",
  "subject": "Research task: cloud database pricing",
  "text": "Please compare pricing for Neon, Supabase, and Railway Postgres. Return as a comparison table.",
  "inboxId": "COMMUNE_ORCHESTRATOR_INBOX_ID",
  "idempotencyKey": "research-db-pricing-2026"
}
Response: { "thread_id": "thread_xxx" }

Save thread_id. It is the unique identifier for this task. The idempotency key ensures the task is sent exactly once even if retried.


Read the full task chain

GET /v1/threads/THREAD_ID/messages

Returns every message in the thread in order:

  • direction: "outbound" = sent by your agent
  • direction: "inbound" = received from the worker

Read the full file on GitHub · 163 lines

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. 9d ago First seen · 163 lines · 0 tokens per session scan A 3fce735ef85e

Subscribe to this mod's changes

commune-agent-network is a skill published in the GitHub repository black22345/commune-cookbook (2 stars, last pushed today), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,096 tokens. 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.