← 返回 Skills 市场

ActivityClaw Plugin Usage

Name: ActivityClaw Plugin Usage
Author: rmruss2022

作者 rmruss2022 · GitHub ↗ · v1.0.0

cross-platform ⚠ suspicious

668

总下载

当前安装

版本数

在 OpenClaw 中安装

/install activityclaw-usage

功能描述

Monitors and reports agent activities including file operations, command executions, web actions, messages, and sub-agent sessions via dashboard and status c...

使用说明 (SKILL.md)

ActivityClaw Plugin Usage

When to Use

Use this skill when the user asks about:

Recent agent activities or actions
What the agent has been doing
Tool usage tracking or monitoring
File operations history (reads, writes, edits)
Command execution history
Web searches or fetches performed
Message sending activity
Sub-agent spawning

Prerequisites

The ActivityClaw plugin must be installed:

npm install -g @rmruss2022/activityclaw
openclaw plugins install @rmruss2022/activityclaw

Quick Start

Check if ActivityClaw is installed and running:

openclaw activityclaw status

Commands

View Dashboard

Open the visual activity dashboard in browser:

openclaw activityclaw dashboard

This opens http://localhost:18796 with real-time activity feed.

Check Status

Show current status and configuration:

openclaw activityclaw status

Start/Stop

Manually control the service:

openclaw activityclaw start
openclaw activityclaw stop

Configuration

Reconfigure port or database location:

openclaw activityclaw setup

What ActivityClaw Tracks

📝 File Operations - Creates, edits, reads
⚡ Commands - Shell executions via exec
🔍 Web Activity - Searches and fetches
💬 Messages - Outbound messages to channels
🚀 Sub-agents - Spawned agent sessions

Dashboard Features

The dashboard at http://localhost:18796 provides:

Real-time activity feed - Live stream of all agent actions
Activity filters - View by type (files, commands, web, messages)
Statistics - Total activities, last hour count, active agents
Auto-refresh - Updates every 5 seconds

Example Usage

User asks: "What files have I been working on today?"

Response:

openclaw activityclaw dashboard

Then check the "📝 Create" and "✏️ Edit" filters in the dashboard to see recent file operations.

User asks: "Show me recent command executions"

Response:

openclaw activityclaw dashboard

Filter by "⚡ Exec" to see command history.

User asks: "What has the agent been doing?"

Response:

openclaw activityclaw status

This shows a summary, then suggest opening the dashboard for details:

openclaw activityclaw dashboard

Troubleshooting

If activities aren't showing:

Check plugin status: openclaw plugins list
Verify service is running: openclaw activityclaw status
Start if stopped: openclaw activityclaw start
Check dashboard URL: http://localhost:18796

If port is in use:

openclaw activityclaw setup
# Choose a different port

Technical Details

Port: 18796 (default, configurable)
Database: SQLite at ~/.openclaw/activity-tracker/activities.db
Tracking: Real-time via tool_result_persist hook
Storage: All data stays local

Repository

GitHub: https://github.com/rmruss2022/ActivityClaw npm: @rmruss2022/activityclaw

安全使用建议

This skill appears to be a coherent local activity-tracking plugin, but it asks you to install a third-party npm/openclaw package whose code is not bundled in the skill. Before installing: 1) Inspect the GitHub repository and npm package (@rmruss2022/activityclaw) — review code, recent commits, maintainer identity, and issues. 2) Verify package integrity (checksums, signed releases) if available. 3) Understand that the plugin logs file operations and shell commands to a local SQLite DB (~/.openclaw/activity-tracker/activities.db) — that may include sensitive data; consider retention/rotation policies and encryption. 4) Prefer installing in an isolated environment (VM/container) or review the package offline first. 5) Confirm what permissions openclaw plugins install grants and whether the plugin spawns processes or reads broad file paths. If you cannot review the package or verify the maintainer, treat the install as potentially unsafe and avoid installing it on systems with sensitive data.

功能分析

Type: OpenClaw Skill Name: activityclaw-usage Version: 1.0.0 The skill instructs the agent to install a third-party npm package (`@rmruss2022/activityclaw`) globally via `npm install -g` in SKILL.md. While this action is presented as a prerequisite for the skill's stated purpose, `npm install -g` is a shell command that fetches and executes arbitrary code from a remote registry. This constitutes a significant 'risky capability' due to potential supply chain vulnerabilities (e.g., RCE if the npm package itself were compromised or malicious), even though the skill bundle itself does not exhibit explicit malicious intent like data exfiltration or prompt injection, and explicitly states 'All data stays local'.

能力评估

ℹ Purpose & Capability

The name/description match the SKILL.md: this is a local activity-tracking/dashboard plugin that logs file ops, commands, web actions, messages, and sub-agents. However the registry metadata claims 'no install spec' while the runtime instructions explicitly instruct installing an npm package and an openclaw plugin — a small inconsistency between declared requirements and runtime steps.

✓ Instruction Scope

The SKILL.md limits actions to installing/controlling the ActivityClaw service and opening a local dashboard at http://localhost:18796. It references only the local SQLite DB (~/.openclaw/activity-tracker/activities.db) and local control commands (start/stop/status/dashboard). It does not instruct reading unrelated system files or exfiltrating data to external endpoints.

⚠ Install Mechanism

Although the skill is instruction-only (no install spec), it tells users/agents to run 'npm install -g @rmruss2022/activityclaw' and 'openclaw plugins install @rmruss2022/activityclaw'. Installing a global npm package from a third-party namespace and an external plugin command is potentially risky because the package code is not included for review here and the registry metadata lists 'Source: unknown' and no homepage in the registry. This is the primary risk vector.

✓ Credentials

The skill declares no required environment variables or credentials, and the instructions do not request secrets or unrelated credentials. The plugin's stated scope (tracking commands, files, messages) explains why it needs access to agent actions — the declared environment/credential footprint is minimal and proportionate.

✓ Persistence & Privilege

The skill is not always-enabled, has no elevated platform privileges in the registry metadata, and does not ask to modify other skills' configs. It does persist data locally to an SQLite DB under the user's home (~/.openclaw/activity-tracker/activities.db), which is expected for an activity tracker.

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 activityclaw-usage
安装完成后，直接呼叫该 Skill 的名称或使用 /activityclaw-usage 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

v1.0.0

Initial release: Skill for using ActivityClaw plugin

元数据

Slug activityclaw-usage

版本 1.0.0

许可证 —

累计安装 0

当前安装数 0

历史版本数 1

常见问题