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.
npx agentmods add skills/commune-dev/commune-cookbook/commune-agent-networknpx skills add commune-dev/commune-cookbook --skill commune-agent-networkgit clone --depth 1 https://github.com/commune-dev/commune-cookbookWrote 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.
[](https://agentmods.dev/skills/commune-dev/commune-cookbook/commune-agent-network)<a href="https://agentmods.dev/skills/commune-dev/commune-cookbook/commune-agent-network"><img src="https://agentmods.dev/badge/skills/commune-dev/commune-cookbook/commune-agent-network.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00000 | $0.01096 |
| Opus 5 | $0.00000 | $0.00548 |
| Sonnet 5 | $0.00000 | $0.00219 |
| Haiku 4.5 | $0.00000 | $0.00110 |
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 4d 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.
This is a copy
100% identical to commune-agent-network — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
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 agentdirection: "inbound"= received from the worker
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.
- 4d ago First seen · 163 lines · 0 tokens per session scan A 3fce735ef85e
commune-agent-network is a skill published in the GitHub repository commune-dev/commune-cookbook (2 stars, last pushed 2mo ago), 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. It is 100% identical to commune-agent-network, differing in 0 lines, and is treated as a copy.
Other skills, from other repositories
commune-email
I give you a real email inbox and let you send, receive, search, and manage email threads programmatically via the Commune API. Every inbox I create is RFC 5322 compliant — replies thread correctly in any email client, including Gmail, Apple Mail, and Outlook.
commune-sms
I give you a real phone number and let you send and receive SMS messages programmatically via the Commune API. You can send texts to any number, read conversation threads, and list all your SMS conversations — all from within your OpenClaw agent.
commune-agent-network
Requires COMMUNEAPIKEY environment variable. Get one at commune.email.
research
Evidence-backed web research with citations and confidence scores. Use when the user needs researched, verified answers backed by real sources — not LLM hallucinations.
email-drafting
Professional email drafting — structure, tone, and templates for common business contexts.
email-management
Inbox management workflow — triage, batching, folder strategy, and inbox zero maintenance.