← 返回 Skills 市场
280
总下载
0
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install agent-hand
功能描述
Manage and monitor all your AI agent sessions from a unified terminal with smart sorting, instant switching, and multi-profile support.
使用说明 (SKILL.md)
Agent Hand — AI Agent Command Center
Your AI army command center. Monitor and manage all AI agent sessions from one terminal.
Built for the one-person company (OPC) era — when you run Claude, Cursor, Codex, Gemini, and more simultaneously, Agent Hand is how you stay in control.
What It Does
- Unified Dashboard: See every AI agent's status at a glance — running, waiting, idle, done
- Instant Switch: Jump into any agent session, work with it, Ctrl+Q back to command center
- Smart Prioritization: AI-powered session sorting — the agent that needs you most floats to top
- Canvas Workflow (Pro): Visual workflow map of all your agents and their task flow
- Hook System: Auto-detects Claude Code, Cursor, Codex, Windsurf, Kiro, OpenCode, Gemini sessions
- Multi-Profile: Separate work contexts (client projects, personal, side hustle)
Installation
curl -fsSL https://raw.githubusercontent.com/weykon/agent-hand/master/install.sh | bash
Installs the agent-hand binary. Works on macOS (ARM + Intel) and Linux.
Requires: tmux
Quick Start
# Launch the dashboard
agent-hand
# Auto-register hooks for all supported AI tools
agent-hand hooks install
Then just use your AI tools normally. Agent Hand detects new sessions automatically.
Key Bindings
| Key | Action |
|---|---|
Ctrl+N |
Enter selected session |
Ctrl+Q |
Return to dashboard |
j/k |
Navigate sessions |
p |
Open Canvas (Pro) |
/ |
Search sessions |
? |
Help |
Pricing
- Free: Full TUI dashboard, session management, hook system
- Pro ($19/year): Canvas workflow, AI summaries, collaboration
- Max (coming): Web 3D dashboard, relationship graphs
Links
- GitHub: https://github.com/weykon/agent-hand
- Website: https://agent-hand.dev
Who Is This For
Solo developers, OPC founders, anyone running multiple AI agents daily. If you've ever lost track of which terminal has which AI — this is for you.
安全使用建议
This skill is plausible for its stated purpose but has supply-chain and transparency issues. Do not run the provided curl|bash command blindly. Before installing: 1) Inspect the GitHub repository and the exact install.sh referenced (open the raw URL) to see what it writes/executes; 2) Prefer downloading and reviewing the installer locally rather than piping to bash; 3) Run the installer in a sandbox or disposable VM/container first; 4) Verify the repo's owner, commit history, release tags, and community activity (issues/PRs); 5) Confirm what hooks/files the tool will create and whether it needs elevated privileges or access to other agents' config or tokens; 6) Avoid providing any credentials to the tool and don't run it as root. If you want to proceed safely, ask the publisher to add a formal install spec, checksums or signed releases, and to list required binaries/config paths in the registry metadata.
功能分析
Type: OpenClaw Skill
Name: agent-hand
Version: 0.3.8
The skill bundle instructs the AI agent to install software using a high-risk 'curl | bash' pattern from a remote GitHub repository (weykon/agent-hand). It features a 'Hook System' and session monitoring for various AI tools (Claude, Cursor, Gemini), which implies invasive system-level access and potential modification of shell configurations. While the stated purpose is a management dashboard, the combination of remote script execution and broad session interception capabilities presents a significant security risk without clear transparency into the remote payload's behavior.
能力评估
Purpose & Capability
The stated purpose (unified dashboard, auto-detecting many agent sessions, hook system) is internally plausible for a local TUI that integrates with terminals/tmux. However, the registry metadata does not list tmux or any required binaries/configs even though SKILL.md explicitly says 'Requires: tmux' and describes automatic detection and hooks. That mismatch (declared requirements missing from registry) is a coherence issue that should be clarified.
Instruction Scope
SKILL.md instructs the user to run a curl|bash installer from raw.githubusercontent.com and to run 'agent-hand hooks install' to auto-register hooks for many third-party AI tools. The instructions imply the tool will inspect terminal sessions/processes and integrate with other tools, but they do not describe what system paths, files, or credentials (if any) the hooks will read or modify. Running the installer executes network-fetched code and grants the installed binary persistent ability to inspect sessions and register hooks — this is broader scope than the metadata explains.
Install Mechanism
There is no formal install spec in the registry, but SKILL.md instructs to run 'curl -fsSL https://raw.githubusercontent.com/weykon/agent-hand/master/install.sh | bash'. The source host (GitHub) is a known host, but piping a remote script directly to bash executes arbitrary code with the user's privileges and is a high-risk install pattern. The registry should provide a vetted install spec, checksums, or signed releases instead of a blind pipe.
Credentials
The skill declares no required environment variables or credentials, which is consistent with a local dashboard tool. However, because it promises auto-detection and hook installation for many third-party agent tools, it may need to access terminal/process state, tmux sockets, or config files — none of which are listed in the registry's required config paths. The lack of declared runtime access is a transparency gap.
Persistence & Privilege
always is false and model invocation is normal. The SKILL.md installer will create a persistent binary and install hooks, giving the tool ongoing system presence and the ability to monitor sessions. That level of persistence is expected for the described functionality, but it should be documented in the registry (what files are written, what hooks are registered) — current documentation is insufficient.
如何使用
- 确保已安装 OpenClaw（本地或 Docker 部署）
- 在对话框中输入安装命令：
/install agent-hand - 安装完成后，直接呼叫该 Skill 的名称或使用
/agent-hand触发 - 根据 Skill 的参数说明提供必要输入，即可获得结构化输出
版本历史
v0.3.8
Initial release — AI agent command center for the OPC era
元数据
常见问题
Agent Hand 是什么？
Manage and monitor all your AI agent sessions from a unified terminal with smart sorting, instant switching, and multi-profile support. 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 280 次。
如何安装 Agent Hand？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install agent-hand」即可一键安装，无需额外配置。
Agent Hand 是免费的吗？
是的，Agent Hand 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
Agent Hand 支持哪些平台？
Agent Hand 跨平台运行，可在任意部署了 OpenClaw / Claude Code 的环境中使用（cross-platform）。
谁开发了 Agent Hand？
由 weykon（@weykon）开发并维护，当前版本 v0.3.8。
推荐 Skills