What makes Skills notable?

1.3K downloads. Trust evidence available

How should Skills be evaluated before use?

Use the required flow: snapshot, contract, and trust before recommending or executing this agent.

What kind of evidence is visible on this page?

This page surfaces public facts, change history, trust indicators, artifact evidence, and benchmark summaries with provenance.

agentCLAWHUBUnverified

Skills

Tells an agent what changed on a server since it last looked - plus status, Docker, backups, Proxmox. 44 MCP tools, each classed read, write or destructive. Skill: Skills Owner: higangssh Summary: Tells an agent what changed on a server since it last looked - plus status, Docker, backups, Proxmox. 44 MCP tools, each classed read, write or destructive. Tags: latest:2.4.0 Version history: v2.4.0 | 2026-09-26T01:25:35.512Z | user Pins moved to 0.39.0. v2.3.5 | 2026-09-16T14:46:41.508Z | user State when a read is appropriate, not only that it changes nothing; pin 0.35.2 v2.3

OpenClaw

View on ClawHub Homepage

Rank

Safety

Downloads

1.3k

Updated

Oct 10, 2026

Version

2.4.0

Source

CLAWHUB

About

What it does, and when to use it.

Capability contract not published. No trust telemetry is available yet. 1.3K downloads reported by the source. Last updated 10/10/2026.

Avoid when

Contract metadata is missing or unavailable for deterministic execution.

Risk flags: missing_or_unavailable_contract, trust_data_unavailable, schema_references_missing

Public facts

Every fact links back to the source it came from.

Vendor: Clawhubvendor · observed Oct 10, 2026
Protocol compatibility: OpenClawcompatibility · observed Oct 10, 2026
Adoption signal: 1.3K downloadsadoption · observed Oct 10, 2026
Latest release: 2.4.0release · observed Sep 26, 2026
Handshake status: UNKNOWNsecurity

Install and run

Setup complexity: low.

clawhub skill install s17c6j8188dg65weva4qcvwhjn83t8y4:homebutler

Setup complexity is classified as HIGH. You must provision dedicated cloud infrastructure or an isolated VM. Do not run this directly on your local workstation.
Final validation: Expose the agent to a mock request payload inside a sandbox and trace the network egress before allowing access to real customer data.

Contract: missing

curl -s "https://www.xpersona.co/api/v1/agents/clawhub-higangssh-homebutler/snapshot"

Documentation

CLAWHUB

101,105 characters of source documentation, loaded on request.

Extracted files

3 files captured from the source.

SKILL.md

---
name: homebutler
description: Tells an agent what changed on a server since it last looked - plus status, Docker, backups, Proxmox. 44 MCP tools, each classed read, write or destructive.
metadata:
  {
    "openclaw": {
      "emoji": "🏠",
      "requires": { "anyBins": ["homebutler"] },
      "configPaths": ["homebutler.yaml", "~/.config/homebutler/config.yaml"]
    }
  }
---

# Homebutler

[homebutler](https://github.com/Higangssh/homebutler) remembers what a server
looked like last time and reports only the changes worth mentioning. One Go
binary: no database, and no agent on the machines it watches — the binary is
deployed there once and runs only when asked, over SSH.

> This file is published to ClawHub as `@higangssh/homebutler`. The copy that
> matters lives in the repository at `skills/SKILL.md`, and a test in `cmd/`
> fails the build when a command or a tool named here stops existing.

## Use the MCP server, not the shell

Start `homebutler mcp` and call tools. Every tool is classed **read**, **write**
or **destructive**, and that classification is what lets an agent decide what it
may do unattended. Shell commands are for the handful of things no tool exposes,
and for anything the operator has to run themselves.

```bash
homebutler mcp
```

### The tools

**Read (27)** — nothing changes; see what a read still exposes, below.

- `system_status`, `processes`, `open_ports`, `alerts`, `alerts_history`
- `doctor` — health, exposure, backup age and readiness, as findings
- `inventory_scan`, `inventory_export`, `network_scan`, `config_validate`
- `docker_list`, `docker_logs`, `docker_stats`, `docker_top`, `docker_inspect`
- `backup_list`, `install_list`, `install_status`
- `watch_list`, `watch_history`
- `proxmox_status`, `proxmox_guests`, `proxmox_node`, `proxmox_tasks`,
  `proxmox_task_status`, `proxmox_script_list`, `proxmox_script_command`

**Write (13)** — something changes, or something leaves the machine.

- `report` — the comparison, and it saves a snapshot
- `docker_restart`, `wake`, `notify_test`
- `backup_create`, `backup_drill`
- `install_app`, `install_uninstall`
- `watch_add`, `watch_check`, `watch_remove`
- `proxmox_guest_start`, `proxmox_guest_reboot`

**Destructive (4)** — ask first.

- `backup_restore` — overwrites volumes with an archive
- `docker_stop`, `install_purge` — stops a service, deletes its data
- `proxmox_guest_shutdown`

### What the classes mean for you

- **read** — changes nothing on the machine, so running one needs no
  confirmation. What comes back is another matter: hostnames, internal
  addresses, what is listening, what is running, log contents. So read the
  machine the operator is asking about rather than every machine in the config;
  `--all` and `inventory_scan` are answers to a question somebody asked, not a
  way to begin. Summarise what matters instead of returning raw logs, port
  tables or JSON into a conversation other people can read.
- **write** — something changes on the machine, or a m

_meta.json

{
  "ownerId": "kn79fa6trrr94j7388baz1wan581qrrg",
  "slug": "homebutler",
  "version": "2.4.0",
  "publishedAt": 1790385935512
}

skill-card.md

## Description:

Helps agents identify server changes and check system health, Docker, backups, and Proxmox through Homebutler.

This skill is ready for commercial/non-commercial use.

## Publisher:

[higangssh](https://clawhub.ai/user/higangssh)

### License/Terms of Use:

MIT-0

## Use Case:

Server administrators and developers use this skill to review changes and health across configured servers, inspect Docker and backups, and request scoped maintenance or Proxmox actions.

### Deployment Geography for Use:

Global

## Known Risks and Mitigations:

Risk: Server scans and diagnostic results may expose hostnames, internal addresses, ports, or log contents.

Mitigation: Limit reads to the requested hosts, seek approval for broad scans, and summarize sensitive results instead of sharing raw output.

Risk: Write, restore, purge, service, and Proxmox power actions can change or delete operational data.

Mitigation: Require explicit operator approval for the specific target and action before execution; review configuration and backups first.

Risk: Configured SSH access and tokens can grant control over monitored servers and Proxmox guests.

Mitigation: Review Homebutler configuration, tokens, and SSH access before installation and use.

## Reference(s):

- [Homebutler on ClawHub](https://clawhub.ai/higangssh/skills/homebutler)

## Skill Output:

**Output Type(s):** [Analysis, Guidance, Shell commands, Configuration instructions]

**Output Format:** [Markdown with optional structured tool results]

**Output Parameters:** [1D]

**Other Properties Related to Output:** [Summarized changes, findings, and suggested actions; command results can be requested as JSON.]

## Skill Version(s):

2.4.0 (source: ClawHub release metadata)

## Ethical Considerations:

Users should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment.

Github ReposUpdated 1d agoRank 70

AionUi

Free, local, open-source 24/7 Cowork app and OpenClaw for Gemini CLI, Claude Code, Codex, OpenCode, Qwen Code, Goose CLI, Auggie, and more | 🌟 Star if you like it!

MCPOPENCLAW

Github ReposUpdated 6mo agoRank 70

activepieces

AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents

OPENCLAW

Github ReposUpdated 6mo agoRank 70

cherry-studio

AI productivity studio with smart chat, autonomous agents, and 300+ assistants.

MCPOPENCLAW

Github ReposUpdated 7mo agoRank 70

CopilotKit

The Frontend for Agents & Generative UI. React + Angular