Agent skill

Agent Network

by aAAaqwq in aAAaqwq/AGI-Super-Team

Multi-Agent group chat collaboration system inspired by DingTalk/Lark.

MITAuto-check passedProductivity & Automation

Install Agent Network

skills CLI
$ npx skills add aAAaqwq/AGI-Super-Team --skill agent-network -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install aAAaqwq/AGI-Super-Team agent-network --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/aAAaqwq/AGI-Super-Team.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/agent-network .claude/skills/agent-network && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
agent-network
GitHub stars
105
Token cost
~2k tokens
SKILL.md length
309 words
Files
15 (incl. scripts, references)
Skills in repo
152
Repo updated
First seen
Licence
MIT

At a glance

Multi-Agent group chat collaboration system inspired by DingTalk/Lark.

  • Works in 6 steps: Agent Management (agent_manager.py) → Group Management (group_manager.py) → Message System (message_manager.py) → …
  • Building multi-agent systems that need structured communication
  • SKILL.md covers What This Skill Provides, Quick Start, Core Components and CLI Usage, plus 5 more sections
  • Runs Python scripts from its folder; calls python

What it does

Agent Network is an agent skill from aAAaqwq/AGI-Super-Team. Multi-Agent group chat collaboration system inspired by DingTalk/Lark. Enables AI agents to chat in groups, @mention each other, assign tasks, make decisions via voting, and collaborate. Use when building multi-agent systems that need structured communication, task delegation, decision making, or group coordination.

Its SKILL.md is about 2k tokens, which your agent loads only when the skill is triggered. The skill folder holds 18 other files, including scripts and reference files (for example `.clawhub/origin.json`, `_meta.json` and `references/ADVANCED.md`).

It sits in Productivity & Automation, covering Multi-agent orchestration, Messaging and chat bots and Task management. The repository describes itself as: An installable, cross-framework AI organization: C-suite agents, expert subagents, curated skills, independent review, and one-command setup across 18 AI client/runtime adapters. The licence is MIT.

When your agent uses it

  • Building multi-agent systems that need structured communication
  • Task delegation
  • Decision making
  • Group coordination

Example prompts

  • “/agent-network”

Requirements

  • Python 3

Workflow steps

6 steps, taken from the step headings in SKILL.md.

  1. Agent Management (agent_manager.py)
  2. Group Management (group_manager.py)
  3. Message System (message_manager.py)
  4. Task Management (task_manager.py)
  5. Decision Voting (decision_manager.py)
  6. Central Coordinator (coordinator.py)

What it can do on your machine

Read from SKILL.md and the folder at commit 331ecd3. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Ships 10 files in scripts/ (Python), which the agent can run.

    Shell commands in SKILL.md call:

    • python

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Agent Network loads about 2k tokens when it runs, and up to ~6.4k if it reads all its reference files. Until then it costs about 83 tokens; SKILL.md has 309 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~83
When it runs · the whole SKILL.md, loaded when a task matches
~2k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~6.4k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.

SKILL.md

The full file from aAAaqwq/AGI-Super-Team at commit 331ecd3, republished under its MIT licence (© aAAaqwq). 309 words, ~2,038 tokens.

Download SKILL.mdSave it as .claude/skills/agent-network/SKILL.md (or your agent's skills folder). This skill also uses 14 other files; get the full folder from GitHub.
name
agent-network
description
Multi-Agent group chat collaboration system inspired by DingTalk/Lark. Enables AI agents to chat in groups, @mention each other, assign tasks, make decisions via voting, and collaborate. Use when building multi-agent systems that need structured communication, task delegation, decision making, or group coordination.

Agent Network - Multi-Agent Collaboration System

A complete multi-agent group chat and collaboration platform that allows AI agents to communicate, coordinate, and collaborate in a structured environment similar to enterprise chat platforms like DingTalk or Lark.

What This Skill Provides

  • Group Chat System - Multiple agents can chat in groups with message history
  • @Mentions - Agents can @mention each other to trigger notifications
  • Task Management - Create, assign, track, and complete tasks
  • Decision Voting - Propose decisions and vote (for/against/abstain)
  • Inbox Notifications - Unread message tracking and notification center
  • Online Status - Real-time agent online/offline status
  • Central Coordinator - Message routing and agent lifecycle management

Quick Start

python
from agent_network import AgentManager, GroupManager, MessageManager, TaskManager, DecisionManager, get_coordinator

# Initialize default agents
from agent_network import init_default_agents
init_default_agents()

# Get the coordinator
coordinator = get_coordinator()

# Register agents
coordinator.register_agent(agent_id=1)
coordinator.register_agent(agent_id=2)

# Create a group
group = GroupManager.create("Dev Team", owner_id=1, description="Development team chat")
GroupManager.add_member(group.id, agent_id=2)

# Send a message with @mention
MessageManager.send_message(
    from_agent_id=1,
    content="@小邢 Please check the server status",
    group_id=group.id
)

# Assign a task
task = TaskManager.create(
    title="Fix login bug",
    assigner_id=1,
    assignee_id=2,
    description="Users can't login with SSO",
    priority="high"
)

# Create a decision
decision = DecisionManager.create(
    title="Adopt new database?",
    description="Should we migrate to distributed database?",
    proposer_id=1,
    group_id=group.id
)

# Vote on decision
DecisionManager.vote(decision.id, agent_id=2, vote="for", comment="Agreed, better performance")

Core Components

1. Agent Management (agent_manager.py)

Register and manage agents with online/offline status:

python
from agent_network import AgentManager

# Register new agent
agent = AgentManager.register("NewAgent", "Developer", "Backend specialist")

# Set status
AgentManager.go_online(agent.id)
AgentManager.go_offline(agent.id)

# Get online agents
online = AgentManager.get_online_agents()
2. Group Management (group_manager.py)

Create groups and manage membership:

python
from agent_network import GroupManager

# Create group
group = GroupManager.create("Project Alpha", owner_id=1)

# Add members
GroupManager.add_member(group.id, agent_id=2)
GroupManager.add_member(group.id, agent_id=3)

# List members
members = GroupManager.get_members(group.id)
online_members = GroupManager.list_online_members(group.id)
3. Message System (message_manager.py)

Send messages with @mention support:

python
from agent_network import MessageManager

# Send message
msg = MessageManager.send_message(
    from_agent_id=1,
    content="Hello team!",
    group_id=1
)

# @mention automatically detected
msg = MessageManager.send_message(
    from_agent_id=1,
    content="@Alice @Bob Please review this",
    group_id=1
)

# Get message history
messages = MessageManager.get_group_messages(group_id=1, limit=50)

# Search messages
results = MessageManager.search_messages("keyword", group_id=1)

# Get unread count
unread = MessageManager.get_unread_count(agent_id=1)
inbox = MessageManager.get_agent_inbox(agent_id=1, only_unread=True)
4. Task Management (task_manager.py)

Full task lifecycle:

python
from agent_network import TaskManager

# Create task
task = TaskManager.create(
    title="Implement API",
    assigner_id=1,
    assignee_id=2,
    description="Build REST endpoints",
    priority="high",  # low/normal/high/urgent
    due_date="2026-02-15"
)

# Update status
TaskManager.start_task(task.id, agent_id=2)
TaskManager.complete_task(task.id, agent_id=2, result="All tests passed")

# Add comments
TaskManager.add_comment(task.id, agent_id=2, "50% complete")

# List tasks
all_tasks = TaskManager.get_all()
my_tasks = TaskManager.get_agent_tasks(agent_id=2, status="pending")
5. Decision Voting (decision_manager.py)

Collaborative decision making:

python
from agent_network import DecisionManager

# Create proposal
decision = DecisionManager.create(
    title="Use microservices?",
    description="Should we refactor to microservices?",
    proposer_id=1,
    group_id=1
)

# Vote
DecisionManager.vote(decision.id, agent_id=2, vote="for", comment="Better scalability")
DecisionManager.vote(decision.id, agent_id=3, vote="against")

# Update status
DecisionManager.update_status(decision.id, "approved", updater_id=1)

# Check results
decision = DecisionManager.get_by_id(decision.id)
print(f"Pass rate: {decision.pass_rate}%")
6. Central Coordinator (coordinator.py)

High-level coordination with automatic message routing:

python
from agent_network import get_coordinator

coord = get_coordinator()

# Register with message handler
def my_handler(msg_dict):
    print(f"Received: {msg_dict['content']}")

coord.register_agent(agent_id=1, message_handler=my_handler)

# Send through coordinator (auto-routes to handlers)
coord.send_message(from_agent_id=1, content="Hello", group_id=1)

# Task coordination
task = coord.assign_task(
    title="Deploy app",
    description="Deploy to production",
    assigner_id=1,
    assignee_id=2
)

# Decision coordination
decision = coord.propose_decision(
    title="Release v2.0?",
    description="Ready for release?",
    proposer_id=1
)
coord.vote_decision(decision['id'], agent_id=2, vote="for")

CLI Usage

Interactive CLI for testing:

bash
# Run demo
python demo.py

# Interactive CLI
python cli.py

# Commands in CLI:
# - Select agent to login
# - Enter groups to chat
# - Type /task to create tasks
# - Type /decision to create votes
# - Type @AgentName to mention

Default Agents

Six pre-configured agents:

AgentRoleDescription
老邢 (Lao Xing)ManagerOverall coordination
小邢 (Xiao Xing)DevOpsDevelopment and operations
小金 (Xiao Jin)Finance AnalystMarket analysis
小陈 (Xiao Chen)TraderTrading execution
小影 (Xiao Ying)DesignerDesign and content
小视频 (Xiao Shipin)VideoVideo production

Database Schema

SQLite database with tables:

  • agents - Agent profiles and status
  • groups - Group definitions
  • group_members - Membership relations
  • messages - Chat messages with types
  • tasks - Task tracking
  • task_comments - Task discussions
  • decisions - Decision proposals
  • decision_votes - Voting records
  • agent_inbox - Notification inbox

Integration with OpenClaw

Use with sessions_spawn for true multi-agent workflows:

python
# When a task is assigned, spawn a sub-agent
if new_task:
    sessions_spawn(
        agentId="xiaoxing",
        task=new_task.description,
        label=f"task-{new_task.task_id}"
    )

Files Reference

  • scripts/agent_network/ - Python modules
    • __init__.py - Package exports
    • database.py - SQLite management
    • agent_manager.py - Agent CRUD
    • group_manager.py - Group management
    • message_manager.py - Messaging system
    • task_manager.py - Task management
    • decision_manager.py - Voting system
    • coordinator.py - Central coordinator
  • scripts/cli.py - Interactive CLI
  • scripts/demo.py - Demo script
  • references/schema.sql - Database schema
  • assets/ - Templates (optional)

Advanced Usage

See references/ADVANCED.md for:

  • Custom agent handlers
  • Webhook integrations
  • Message filtering
  • Custom workflows

© aAAaqwq, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 14 other files (scripts, references) in skills/agent-network of aAAaqwq/AGI-Super-Team.

  • SKILL.md
  • .clawhub/origin.json
  • _meta.json
  • references/ADVANCED.md
  • references/schema.sql
  • scripts/agent_network/__init__.py
  • scripts/agent_network/agent_manager.py
  • scripts/agent_network/coordinator.py
  • scripts/agent_network/database.py
  • scripts/agent_network/decision_manager.py
  • scripts/agent_network/group_manager.py
  • scripts/agent_network/message_manager.py
  • scripts/agent_network/task_manager.py
  • scripts/cli.py
  • scripts/demo.py

Open the folder on GitHubat commit 331ecd3

Compare with similar skills

Agent Network next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Agent Network compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Agent Network this skillaAAaqwq/AGI-Super-Team105—~2kAutomated safety check: PassMIT
Superset Agent Standupsuperset-sh/superset15k—~712Automated safety check: PassCustom licence
Pi Messenger Crewnicobailon/pi-messenger720—~3.7kAutomated safety check: PassNone
AgentRQ Supervisoragentrq/agentrq1.1k—~2.7kAutomated safety check: PassAGPL-3.0
AI Fleet Project ExecutionSzotasz/marveen115—~14kAutomated safety check: PassMIT
Omh Agent Boardrlaope/oh-my-hermes3.2k—~1.9kAutomated safety check: PassMIT

Similar skills

  • Superset Agent Standup

    superset-sh/superset

    Sweeps every Superset workspace, task and agent terminal to report what finished, what needs review and what is blocked, read-only, and can publish the digest as a page.

    15k GitHub stars~712 tokensUpdated today
    Productivity & AutomationAuto-check passed
  • Pi Messenger Crew

    nicobailon/pi-messenger

    Orchestrator reference for pi-messenger Crew planning, task management, configuration, and agent coordination.

    720 GitHub stars~3.7k tokensUpdated 1 mo ago
    Productivity & AutomationAuto-check passed
  • AgentRQ Supervisor

    agentrq/agentrq

    Orchestrates work across specialized AgentRQ workspaces, breaking goals into tasks, assigning them to the right workspace agent, and tracking shared learning notes.

    1.1k GitHub stars~2.7k tokensUpdated today
    Productivity & AutomationAuto-check passed
  • AI fleet project execution (orchestrator=PM, marketing agent, backend dev agent, video agent).

    115 GitHub stars~14k tokensUpdated today
    Productivity & AutomationAuto-check passed
  • Omh Agent Board

    rlaope/oh-my-hermes

    [omh] Coordinating several agents or profiles: coordinate multiple Hermes profiles or agents with task, handoff, heartbeat, blocker, and completion states.

    3.2k GitHub stars~1.9k tokensUpdated today
    Productivity & AutomationAuto-check passed
  • Kanban Video Orchestrator

    Luciole-Studio/Misaka-Agent

    Plan and run multi-agent video production pipelines. An agent skill from Luciole-Studio/Misaka-Agent.

    139 GitHub starsUsed in 2 repos~2.4k tokens
    Productivity & AutomationAuto-check: notes

More from aAAaqwq/AGI-Super-Team

All 152 skills in this repo
  • Content Creator

    aAAaqwq/AGI-Super-Team

    Create SEO-optimized marketing content with consistent brand voice.

    105 GitHub starsUsed in 3 repos~1.9k tokens
    Auto-check passed
  • Financial Calculator

    aAAaqwq/AGI-Super-Team

    Advanced financial calculator with future value tables, present value, discount calculations, markup pricing, and compound interest.

    105 GitHub starsUsed in 1 repo~1.5k tokens
    Auto-check passed
  • Frontend Design Ultimate

    aAAaqwq/AGI-Super-Team

    Create distinctive, production-grade static sites with React, Tailwind CSS, and shadcn/ui — no mockups needed.

    105 GitHub starsUsed in 2 repos~2.7k tokens
    Auto-check passed
  • Sysadmin Toolbox

    aAAaqwq/AGI-Super-Team

    Tool discovery and shell one-liner reference for sysadmin, DevOps, and security tasks.

    105 GitHub starsUsed in 2 repos~775 tokens
    Auto-check passed
  • Zsxq Smart Publish

    aAAaqwq/AGI-Super-Team

    Publish and manage content on 知识星球 (zsxq.com). An agent skill from aAAaqwq/AGI-Super-Team.

    105 GitHub stars~1.5k tokensUpdated 11 days ago
    Auto-check passed
  • Content Extract

    aAAaqwq/AGI-Super-Team

    Robust URL-to-Markdown extraction for OpenClaw workflows. An agent skill from aAAaqwq/AGI-Super-Team.

    105 GitHub starsUsed in 1 repo~650 tokens
    Auto-check passed

Questions about Agent Network

What does Agent Network do?

Multi-Agent group chat collaboration system inspired by DingTalk/Lark. Agent Network is an agent skill from aAAaqwq/AGI-Super-Team. Multi-Agent group chat collaboration system inspired by DingTalk/Lark.

When should I use Agent Network?

Agent Network fits situations like: building multi-agent systems that need structured communication; task delegation; decision making; group coordination.

How do I install Agent Network in Claude Code?

Run `npx skills add aAAaqwq/AGI-Super-Team --skill agent-network -a claude-code`. Or copy the skill folder (skills/agent-network in aAAaqwq/AGI-Super-Team) into .claude/skills/agent-network in your project. Claude Code loads it when a task matches its description.

How do I install Agent Network in Codex?

Run `npx skills add aAAaqwq/AGI-Super-Team --skill agent-network -a codex`. Or copy the skill folder (skills/agent-network in aAAaqwq/AGI-Super-Team) into .agents/skills/agent-network in your project. Codex loads it when a task matches its description.

Can I use Agent Network in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add aAAaqwq/AGI-Super-Team --skill agent-network -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/agent-network, .gemini/skills/agent-network, .github/skills/agent-network and .opencode/skills/agent-network in your project.

What does Agent Network need to run?

Going by SKILL.md and its folder, Agent Network needs Python for the scripts in its folder and the command-line tools its instructions call (python). Our summary lists: Python 3.

Does Agent Network access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Agent Network safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does Agent Network use?

Agent Network is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Agent Network use?

About 2k tokens (SKILL.md is roughly 8.2k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 4.4k tokens, read only when the agent opens those files.

What are the alternatives to Agent Network?

Skills that share tags, products or a category with Agent Network: Superset Agent Standup (superset-sh/superset, 15k stars), Pi Messenger Crew (nicobailon/pi-messenger, 720 stars), AgentRQ Supervisor (agentrq/agentrq, 1.1k stars) and AI Fleet Project Execution (Szotasz/marveen, 115 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Agent Network?

aAAaqwq (a GitHub user) maintains it in aAAaqwq/AGI-Super-Team, which has 105 GitHub stars. The repository holds 152 skills in this directory. The repository was last updated on September 27, 2026.

Source: aAAaqwq/AGI-Super-Team on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.