OpenClaw

cerberus-agent-foundry

Production-ready multi-agent architecture kit for OpenClaw. Provides isolated per-agent workspaces, control-plane orchestration, structured task lifecycle, checksum-verified mailbox messaging, and auditable event logs. Use when implementing Team Lead + specialist agents with secure boundaries, async collaboration, and operational governance.

delibrately-cmyk0 来源安装数☆ 0 仓库 Stars

查看来源 ↗安装与使用 SKILL.md ↗

安装与使用

请根据来源仓库和你的 AI 工具说明安装此技能。先阅读技能文件和依赖要求，再添加到工作流。

SkillHub CLI

skillhub install delibrately-cmyk/cerberus-agent-foundry

打开来源仓库，查看说明和兼容环境后，按来源提供的命令或步骤安装。

将来源链接提供给你的 Agent，让它先读取说明、核对依赖，并向你说明将执行的安装步骤。

查看来源 ↗使用指南

技能说明

Cerberus Multi-Agent Control Plane

A professional blueprint for building, operating, and governing local multi-agent teams in OpenClaw. It ships a hardened protocol stack for role isolation, task orchestration, asynchronous handoffs, and auditability.

Quick Start

Install blueprint into target path:
- bash scripts/install_blueprint.sh /path/to/your/system
Verify task board:
- python3 /path/to/your/system/scripts/taskctl.py list
Verify mailbox:
- send: python3 /path/to/your/system/scripts/mailboxctl.py send --task-id TSK-000 --sender team-lead --receiver coder --correlation-id CORR-001 --body "ACK protocol"
- ack: python3 /path/to/your/system/scripts/mailboxctl.py status --message-id MSG-0001 --to ACK --actor coder

What This Blueprint Provides

Strict workspace isolation per agent (agents/*/workspace)
Unified control plane (control-plane/tasks, control-plane/mailbox, control-plane/logs)
Task state machine tooling (taskctl.py)
Mailbox protocol tooling with checksum and GC (mailboxctl.py)
Shared memory layer under control plane (control-plane/shared-memory)

Core Rules (must enforce)

Never use shared agent workspaces.
Use only control-plane/mailbox for agent-to-agent messaging.
Team Lead is sole mailbox garbage-collection authority.
Deploy actions require explicit human approval artifacts.

References

Read references/operations-checklist.md for rollout and audit checks.
Read assets/blueprint/docs/protocol-v1.md for protocol details.

来源信息

Source: github
Repository: openclaw/skills
Path: skills/delibrately-cmyk/cerberus-agent-foundry
Version: —
Commit: 244164e7399a33bb5585059bdfcf1b10769bb683
分类来源: rules
状态: active
可见性: public

这些信息来自收录时的来源分析，可能滞后；使用前请核对最新来源文件。

来源内容

SKILL.md

# Cerberus Multi-Agent Control Plane

A professional blueprint for building, operating, and governing local multi-agent teams in OpenClaw. It ships a hardened protocol stack for role isolation, task orchestration, asynchronous handoffs, and auditability.

## Quick Start

1. Install blueprint into target path:
   - `bash scripts/install_blueprint.sh /path/to/your/system`
2. Verify task board:
   - `python3 /path/to/your/system/scripts/taskctl.py list`
3. Verify mailbox:
   - send: `python3 /path/to/your/system/scripts/mailboxctl.py send --task-id TSK-000 --sender team-lead --receiver coder --correlation-id CORR-001 --body "ACK protocol"`
   - ack: `python3 /path/to/your/system/scripts/mailboxctl.py status --message-id MSG-0001 --to ACK --actor coder`

## What This Blueprint Provides

- Strict workspace isolation per agent (`agents/*/workspace`)
- Unified control plane (`control-plane/tasks`, `control-plane/mailbox`, `control-plane/logs`)
- Task state machine tooling (`taskctl.py`)
- Mailbox protocol tooling with checksum and GC (`mailboxctl.py`)
- Shared memory layer under control plane (`control-plane/shared-memory`)

## Core Rules (must enforce)

1. Never use shared agent workspaces.
2. Use only `control-plane/mailbox` for agent-to-agent messaging.
3. Team Lead is sole mailbox garbage-collection authority.
4. Deploy actions require explicit human approval artifacts.

## References

- Read `references/operations-checklist.md` for rollout and audit checks.
- Read `assets/blueprint/docs/protocol-v1.md` for protocol details.

搜索