Token导航 LogoToken导航TokenDH.com
研究检索敏感数据clawhub未标认证来源可访问clear审计提醒

bricks-clibricks CLI 搜索

Agent Skill

bricks-cli 用于查找、检索和筛选相关信息,适合在 OpenClaw 中需要根据关键词、任务场景或来源线索快速定位候选结果时使用。可结合来源仓库、安装命令和原始 README 继续核验具体用法。安装前建议确认权限范围、维护状态,以及是否会触发联网、命令执行或文件读写。

总安装

23,708

周安装

1,008

GitHub Stars

公开资料未说明

下载量

8,306
OpenClaw

安装说明

本站只整理中文说明和来源信息,不托管安装包,也不代用户安装。

GitHub

来源数

2

许可证

MIT-0

最后核验

2026-05-01

来源状态

来源可访问

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手,先确认命令和权限,再让它执行。

请帮我安装这个 Agent Skill:bricks-cli(bricks CLI 搜索)
来源仓库:https://github.com/jhen0409/bricks-cli
安装命令:
openclaw skills install bricks-cli
安装前请先检查当前环境是否支持对应 CLI,并向我确认将要执行的命令、安装目录、联网范围和文件读写权限;确认后再执行。

命令行安装

复制命令到本机终端执行。该命令会通过 OpenClaw 从第三方来源获取 Skill;本站只展示命令,不托管安装包,也不自动执行。

ClawHubOpenClaw
openclaw skills install bricks-cli

简介

通过 CLI 管理 BRICKS 工作区设备、组、应用程序、模块、媒体和项目,以进行控制、监控、更新和部署。

SKILL.md

name
bricks-cli
description
Manage BRICKS workspace via CLI. Use for device status, screenshots, control, monitoring, group operations, application management, module management, project initialization and deployment, scanning and connecting local BRICKS Foundation devices on LAN, and creating BRICKS applications via BRICKS Project Desktop agent through ACP. Triggers on: device management, digital signage control, BRICKS workspace tasks, app/module updates, project setup, LAN device discovery, ACP bridge, desktop agent.

BRICKS CLI

CLI for BRICKS Workspace API — manage devices, apps, modules, and media.

Scope note: This skill covers cloud API operations (device/app/module/media management) *and* local-network device interaction (LAN discovery, MCP bridging). The use-desktop-acp rule extends scope further to include bridging with the BRICKS Project Desktop agent, which shares sessions and can execute commands in project context. See the Security section below for details.

Installation (if not yet)

# Validate installed
which bricks

# npm (published by @fugood on npmjs.com — https://www.npmjs.com/package/@fugood/bricks-cli)
npm i -g @fugood/bricks-cli
# Bun
bun add -g @fugood/bricks-cli

Authentication

# Login with one-time passcode (get from https://control.bricks.tools)
bricks auth login <passcode>

# Check auth status
bricks auth status

# Switch profiles
bricks auth list
bricks auth use <profile>

Global --auth-profile Flag

Use -ap or --auth-profile to override the active profile for any command, without switching the stored profile:

# Run any command as a specific profile
bricks -ap staging device list
bricks --auth-profile production app list

# Also applies to login — saves token to the specified profile
bricks -ap staging auth login <passcode>

Priority: --auth-profile flag > BRICKS_PROFILE env > stored current profile.

Device Management

List & Info

# List all devices
bricks device list
bricks device list -j              # JSON output
bricks device list -k "lobby"      # Filter by keyword

# Get device details
bricks device get <device-id>
bricks device get <device-id> -j   # JSON output

Control

# Refresh device (reload app)
bricks device refresh <device-id>

# Clear device cache
bricks device clear-cache <device-id>

# Send control command
bricks device control <device-id> <type>
bricks device control <device-id> <type> -p '{"key":"value"}'

Screenshot

# Take and save screenshot
bricks device screenshot <device-id>
bricks device screenshot <device-id> -o /tmp/screen.png

# Fetch existing screenshot (no new capture)
bricks device screenshot <device-id> --no-take

Monitor (Interactive-tty needed)

# Monitor all devices (polls every 60s)
bricks device monitor

# Monitor specific group
bricks device monitor -g <group-id>

# Custom interval
bricks device monitor -i 30

Device Groups

# List groups
bricks group list

# Get group details
bricks group get <group-id>

# List devices in group with status
bricks group devices <group-id>

# Dispatch action to all devices in group
bricks group dispatch <group-id> <action>

# Refresh all devices in group
bricks group refresh <group-id>

# Monitor group
bricks group monitor <group-id>

Applications

# Create a new application
bricks app new -n "My App"
bricks app new -n "My App" -d "Description" --layout-width 192 --layout-height 108
bricks app new -n "My App" --example <key>     # Create from example template
bricks app new -n "My App" --init -y           # Create + initialize local project
bricks app new -n "My App" -j                  # JSON output

# List apps
bricks app list

# Get app details
bricks app get <app-id>

# Update app
bricks app update <app-id>

# Validate config against BRICKS schema
bricks app check-config ./config.json
bricks app check-config ./config.json -j       # JSON output

# Bind devices to app
bricks app bind <app-id>

# Quick property edit
bricks app short-edit <app-id>

# Pull source files
bricks app project-pull <app-id>

# Initialize local project from app
bricks app project-init <app-id>
bricks app project-init <app-id> -o ./my-app
bricks app project-init <app-id> -y          # Skip prompts, use defaults
bricks app project-init <app-id> --no-git    # Skip git init

Modules

# Create a new module
bricks module new -n "My Module"
bricks module new -n "My Module" --public --allow-modify
bricks module new -n "My Module" --init -y     # Create + initialize local project
bricks module new -n "My Module" -j            # JSON output

bricks module list
bricks module get <module-id>
bricks module update <module-id>
bricks module short-edit <module-id>
bricks module release <module-id>

# Initialize local project from module
bricks module project-init <module-id>
bricks module project-init <module-id> -o ./my-module -y

Project Init Options

Both app and module support these flags:

  • -o, --output <dir> — output directory
  • -y, --yes — skip prompts, use defaults
  • --no-git — skip git initialization
  • --no-install — skip bun install
  • --no-github-actions — skip GitHub Actions workflow
  • --no-agents — skip AGENTS.md
  • --no-claude — skip CLAUDE.md
  • --gemini — include GEMINI.md (off by default)

Media Flow

bricks media boxes              # List media boxes
bricks media box <box-id>       # Box details
bricks media files <box-id>     # Files in box (shows ready status)
bricks media file <file-id>     # File details (shows ready status)

# Upload files to a media box
bricks media upload <box-id> ./photo.jpg
bricks media upload <box-id> ./img1.jpg ./img2.png      # Multiple files
bricks media upload <box-id> ./photos/*.jpg -j           # JSON output

# Upload with tags and description
bricks media upload <box-id> ./file.pdf -t docs -t report -d "Monthly report"

# Upload with image processing options
bricks media upload <box-id> ./banner.jpg --image-version 250x250:FILL --image-version 800x600:BOUNDED
bricks media upload <box-id> ./logo.png --image-version-type png

# Upload with AI analysis
bricks media upload <box-id> ./photo.jpg --enable-ai-analysis
bricks media upload <box-id> ./photo.jpg --ai-instruction "Describe the scene"

# Control concurrency
bricks media upload <box-id> ./files/* --concurrency 5

Config

bricks config show              # Show current config
bricks config endpoint          # Show API endpoint
bricks config endpoint beta     # Switch to beta endpoint

Interactive Mode (Interactive-tty needed)

bricks interactive    # or: bricks i

DevTools (LAN Discovery)

# Scan LAN for DevTools servers via UDP broadcast
bricks devtools scan
bricks devtools scan -t 5000           # Custom timeout (ms)
bricks devtools scan -j                # JSON output
bricks devtools scan --verify          # Verify each server via HTTP

# Show connection URLs for a device
bricks devtools open <address>
bricks devtools open <address> -p 19853   # Custom port
bricks devtools open <address> --verify   # Verify reachable first

Devices must have "Enable LAN Discovery" turned on in Advanced Settings (on by default).

MCP Server

bricks mcp start      # Start MCP server (STDIO mode)

Bridging Device MCP to Local CLI

Use mcporter to bridge a device's MCP endpoint as a local MCP server (STDIO), so tools like Claude Code can connect to it:

# Bridge a device's MCP endpoint (requires passcode as Bearer token)
npx mcporter --url http://<device-ip>:19851/mcp --header "Authorization: Bearer <passcode>"

ACP Bridge (BRICKS Project Desktop)

Connect external ACP clients to the running BRICKS Project Desktop (docs).

# Start the bridge (requires BRICKS Project Desktop running with ACP enabled in Settings)
bricks desktop-acp-bridge

The bridge pipes ACP JSON-RPC over stdio ↔ the app's Unix socket (~/.bricks-project-desktop/acp.sock). It shares the app's sessions and MCP state.

Security: Commands executed through the ACP bridge run in the project's working directory. Only enable ACP when actively needed, and prefer --deny-all over --approve-all when automating. See the Security section and rule use-desktop-acp for details.

See rule use-desktop-acp for full usage with acpx and OpenClaw.

Rules

  • connect-local-device — Deploy the current app to a local LAN device, then monitor status, debug, and run automations via MCP
  • use-desktop-acp — Connect to the BRICKS Project Desktop agent via ACP for headless prompting, session management, and multi-agent orchestration

Security

  • Auto-approve risk: Running acpx --approve-all allows the bridged agent to execute bash commands without confirmation. Prefer explicit approval or --deny-all for untrusted prompts. Never combine --approve-all with persistent config in unattended/shared environments.
  • Persistent config: Creating ~/.acpx/config.json enables future ACP sessions without re-specifying the agent. This is convenient but means any process that invokes acpx bricks can start a session with project file access. Remove the config when not actively needed.
  • Device passcodes: LAN device MCP bridging (mcporter) requires passing device passcodes as Bearer tokens. Treat passcodes as secrets — do not log or commit them.
  • LAN discovery: bricks devtools scan broadcasts on the local network. Only run on trusted networks.

Tips

  • Use -j or --json on most commands for JSON output
  • Device IDs are UUIDs — use device list to find them
  • Get workspace token from: https://control.bricks.tools → Workspace Settings → API Token

适合场景

01

OpenClaw 用户查找和安装 Skill 时

02

用户想查找某类 Agent Skill 时

03

需要根据任务场景推荐可安装能力包时

04

需要对比不同来源的安装命令和来源信息时

能力概览

能力 1

按任务关键词查找相关 Skills

能力 2

展示可复制的安装命令

能力 3

保留来源站点、仓库和原始说明,方便继续核验

能力 4

补充不同宿主或平台的使用分布数据

能力 5

展示第三方安全扫描或审计结果

安装后应在对应宿主中按原始 README 的触发条件使用;具体调用方式请以来源页面和 README 为准。

平台分布

OpenClaw

73.5%
按下载量换算6,105

安全审计

VirusTotal

通过

ClawScan

可疑

Static analysis

通过

权限和风险

敏感数据

该 Skill 可能接触密钥、Token、环境变量或敏感配置,应进入高风险复核队列,默认不自动发布。

安装前确认

本站仅展示第三方公开信息,不托管安装包,不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。来源安全扫描存在 warning/failed 结果,不能写成本站确认安全。当前只有一个来源,正式发布前建议补源仓库或其他目录站核验。

来源信息

继续浏览同类 Skills