What makes vmware-storage notable?

5.3K downloads. Trust evidence available

How should vmware-storage 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.

Claim this agent

agentCLAWHUBUnverified

vmware-storage

Use this skill whenever the user needs to manage VMware storage — datastores, iSCSI targets, and vSAN clusters. Directly handles: browse datastores, scan for deployable images (OVA/ISO), configure iSCSI adapters and targets, check vSAN health and capacity, read-only Fibre Channel HBA/WWPN inventory and multipath path state. Always use this skill for "list datastores", "add iSCSI target", "check vSAN health", "browse datastore files", "scan for OVA images", "dead paths", "FC HBA WWPN", or any storage-related VMware task. Do NOT use for VM lifecycle operations (use vmware-aiops), NSX networking (use vmware-nsx), or Kubernetes clusters (use vmware-vks). For load balancing/AVI/AKO use vmware-avi.

OpenClaw

View on ClawHub Homepage

Rank

Safety

Downloads

5.3k

Updated

Oct 9, 2026

Version

1.12.0

Source

CLAWHUB

About

What it does, and when to use it.

Capability contract not published. No trust telemetry is available yet. 5.3K downloads reported by the source. Last updated 10/9/2026.

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 9, 2026
Protocol compatibility: OpenClawcompatibility · observed Oct 9, 2026
Adoption signal: 5.3K downloadsadoption · observed Oct 9, 2026
Latest release: 1.12.0release · observed Sep 20, 2026
Handshake status: UNKNOWNsecurity

Install and run

Setup complexity: low.

clawhub skill install s171xgnmqse0nqvgqvqnaq5f9183kyre:vmware-storage

Install using `clawhub skill install s171xgnmqse0nqvgqvqnaq5f9183kyre:vmware-storage` in an isolated environment before connecting it to live workloads.
No published capability contract is available yet, so validate auth and request/response behavior manually.
Review the upstream CLAWHUB listing at https://clawhub.ai/zw008/vmware-storage before using production credentials.

Contract: missing

curl -s "https://www.xpersona.co/api/v1/agents/clawhub-zw008-vmware-storage/snapshot"

Documentation

CLAWHUB

152,105 characters of source documentation, loaded on request.

Extracted files

5 files captured from the source.

SKILL.md

---
name: vmware-storage
description: >
  Use this skill whenever the user needs to manage VMware storage — datastores, iSCSI targets, and vSAN clusters.
  Directly handles: browse datastores, scan for deployable images (OVA/ISO), configure iSCSI adapters and targets, check vSAN health and capacity, read-only Fibre Channel HBA/WWPN inventory and multipath path state.
  Always use this skill for "list datastores", "add iSCSI target", "check vSAN health", "browse datastore files", "scan for OVA images", "dead paths", "FC HBA WWPN", or any storage-related VMware task.
  Do NOT use for VM lifecycle operations (use vmware-aiops), NSX networking (use vmware-nsx), or Kubernetes clusters (use vmware-vks).
  For load balancing/AVI/AKO use vmware-avi.
installer:
  kind: uv
  package: vmware-storage
allowed-tools:
  - Bash
metadata: {"openclaw":{"requires":{"anyBins":["vmware-storage","uvx"]},"optional":{"env":["VMWARE_STORAGE_CONFIG","VMWARE_<TARGET>_PASSWORD","VMWARE_<TARGET>_USERNAME","VMWARE_AUDIT_APPROVED_BY"],"bins":["vmware-policy"]},"homepage":"https://github.com/vmware-skills/VMware-Storage","emoji":"🗄️","os":["macos","linux"]}}
compatibility: >
  vmware-policy auto-installed as Python dependency (provides @vmware_tool decorator and audit logging). All write operations audited to ~/.vmware/audit.db.
  Credentials: Each vCenter/ESXi target requires a per-target password env var in ~/.vmware-storage/.env following the pattern VMWARE_<TARGET_NAME_UPPER>_PASSWORD (e.g., target "my-vcenter" → VMWARE_MY_VCENTER_PASSWORD). No webhooks or outbound network calls — this skill is local-only (stdio MCP + vSphere API). Audit logs written to ~/.vmware/audit.db (SQLite WAL, local only).
---

# VMware Storage

> **Disclaimer**: This is a community-maintained open-source project and is **not affiliated with, endorsed by, or sponsored by VMware, Inc. or Broadcom Inc.** "VMware" and "vSphere" are trademarks of Broadcom. Source code is publicly auditable at [github.com/vmware-skills/VMware-Storage](https://github.com/vmware-skills/VMware-Storage) under the MIT license.

VMware vSphere storage management — 14 MCP tools for datastores, iSCSI, vSAN, and Fibre Channel / multipath diagnostics.

> Split from vmware-aiops for lighter context and local model compatibility.
> **Companion skills**: [vmware-aiops](https://github.com/vmware-skills/VMware-AIops) (VM lifecycle), [vmware-monitor](https://github.com/vmware-skills/VMware-Monitor) (read-only monitoring), [vmware-vks](https://github.com/vmware-skills/VMware-VKS) (Tanzu Kubernetes), [vmware-nsx](https://github.com/vmware-skills/VMware-NSX) (NSX networking), [vmware-nsx-security](https://github.com/vmware-skills/VMware-NSX-Security) (DFW/firewall), [vmware-aria](https://github.com/vmware-skills/VMware-Aria) (metrics/alerts/capacity), [vmware-avi](https://github.com/vmware-skills/VMware-AVI) (AVI/ALB/AKO), [vmware-harden](https://github.com/vmware-skills/VMware-Harden) (compliance baselines).
> | [vmware-pilot](../vmware-

_meta.json

{
  "ownerId": "kn7b067awq2s97bn3d7p5qfhw5827pxc",
  "slug": "vmware-storage",
  "version": "1.12.0",
  "publishedAt": 1789915968885
}

references/agent-guardrails.md

# Operating vmware-storage with a local / small model

Claude-class models drive this skill without special instruction. Smaller and
locally-hosted models — Llama 3.3 70B, Qwen, Mistral, and similar, served
through Goose, Ollama, or OpenShift AI — need explicit operating rules to call
tools reliably.

This page exists because an operator wrote those rules by hand first. The
guardrails below are adapted, with thanks, from the working configuration
[@juanpf-ha](https://github.com/juanpf-ha) developed while running
vmware-monitor and vmware-aria against a production vSphere estate with Llama
3.3 70B FP8 on an on-prem H100
([VMware-AIops#31](https://github.com/vmware-skills/VMware-AIops/issues/31)). The
cross-skill rules are identical across this family; the parts below marked
vmware-storage are specific to this skill.

vmware-storage exposes 14 MCP tools, 4 of which change state. The write
surface is small but sharp: removing an iSCSI send target can make LUNs — and
every VM living on them — inaccessible.

> **Disclaimer**: This is a community-maintained open-source project and is
> **not affiliated with, endorsed by, or sponsored by VMware, Inc. or Broadcom
> Inc.** "VMware" and "vSphere" are trademarks of Broadcom.

---

## First: the rules you no longer need to write

Several guardrails from the original configuration are now enforced by the
skill itself. Prompt instructions are advisory — a model can ignore them.
These are structural, so it cannot.

| Guardrail you would otherwise prompt for | Now enforced by |
|---|---|
| "Preview the change before applying it" | **`confirm` defaults to false.** A call to any of the 4 write tools without `confirm: true` changes nothing and returns `blast_radius`. Previewing is the default path, not a convention the model has to remember to honour. |
| "Don't cut off storage that is in use" | **Refusal.** `storage_iscsi_remove_target` with `confirm: true` is refused when a datastore would lose every path, or when any path or static target behind the send target cannot be attributed. |
| "Use explicit limits for queries that may return large amounts of data" | **The list envelope.** The four datastore read tools return `{items, returned, limit, total, truncated, hint}`, so the model reads truncation instead of guessing at it. All four enumerate their collection in full, so `total` is the real count and `truncated` is always `false`. |
| "If a listing came back empty, say so rather than claiming the call failed" | Same envelope. Empty `items` with `truncated: false` means checked-and-none — a stated result, not a silence the model has to interpret. |
| "Log every state change you make" | **The `@vmware_tool` decorator.** Every operation is recorded to `~/.vmware/audit.db` before the model sees the result, and policy rules are evaluated ahead of execution. `storage_iscsi_remove_target` is classified `risk:high` and goes through the policy confirmation gate. |

---

## The system prompt

Everything below still benef

references/capabilities.md

# VMware Storage Capabilities

All 11 MCP tools exposed by `vmware-storage-mcp`, organized by category.

## Automation Level Reference

Each operation is classified by autonomy level per the Enterprise Harness Engineering framework:

| Level | Meaning | Agent autonomy | Examples in this skill |
|:-:|---|---|---|
| **L1** | Read-only, raw data | Always auto-run | `list_all_datastores`, `browse_datastore`, `scan_datastore_images`, `list_cached_images`, `storage_iscsi_status`, vSAN status queries |
| **L2** | Read + analysis / recommendation | Always auto-run | datastore capacity analysis, image registry queries, iSCSI target health correlation |
| **L3** | Single write — user must approve | Only after explicit confirmation; high-risk ops require double-confirm + `--dry-run` (see Confirm column) | `storage_iscsi_enable`, `storage_iscsi_add_target`, `storage_iscsi_remove_target`, vSAN cluster ops |
| **L4** | Multi-step plan / apply workflow | Plan generation auto; apply gated by user approval | *(roadmap — multi-host iSCSI rollout, vSAN expansion plans)* |
| **L5** | Auto-remediation from learned pattern | Pattern library only; requires `risk:low` + `reversible:true` + `repeatable:true` + signed approval | **PoC pattern (v1.5.16+)**: [`patterns/iscsi-target-stale-rescan.yaml`](../../../patterns/iscsi-target-stale-rescan.yaml) — scans for stale iSCSI devices (`devices_inaccessible_count > 0`, missing expected devices, or `last_rescan_age_minutes > 60`); action: invoke `storage_rescan` on the affected `(host, target)`; classified low-risk because the rescan is idempotent and non-destructive (no data, config, or VM state is modified). Schema only — **not yet enforced by the runtime**. |

**Notes**:
- L1/L2 tools are always safe for agents to call without confirmation.
- L3 tools always pass through the `@vmware_tool` decorator: connection check → policy check → audit log → double-confirm.
- L5 PoC pattern (`patterns/iscsi-target-stale-rescan.yaml`, v1.5.16+) is a **reference design**: it documents the candidate trigger / action / validation / circuit-breaker shape under `schema_version: 1` (see [vmware-policy auto-remediation pattern docs](https://github.com/vmware-skills/VMware-Policy/blob/main/docs/auto-remediation-patterns.md)). The pattern is `approval.status: poc_unsigned` and will only become live after `success_count_required: 5` + `failure_count_max: 0` + `distinct_operators_required: 2` + `days_observed: 90` are met and the pattern is signed.

## Datastore (4 tools)

| Tool | Description | Parameters | Risk | Confirm |
|------|-------------|------------|:----:|:-------:|
| `list_all_datastores` | List datastores with capacity, usage %, VM count | `target` (string, optional) | Low | No |
| `browse_datastore` | Browse files with optional path and glob pattern | `datastore` (string, **required**), `path` (string, optional), `pattern` (string, optional), `target` (string, optional) | Low | No |
| `scan_datastore_images` | Find OVA/ISO/OVF/VMDK dep

references/cli-reference.md

# CLI Reference

Complete command reference for `vmware-storage` CLI.

## Global Options

All commands accept these options:

| Option | Description |
|--------|-------------|
| `--target <name>` | Target name from `~/.vmware-storage/config.yaml` (defaults to first target) |
| `--config <path>` | Override config file path |
| `--help` | Show command help |

## Datastore Commands

### `datastore list`

List all datastores with capacity, usage, and VM count.

```bash
vmware-storage datastore list
vmware-storage datastore list --target my-vcenter
```

Output columns: Name, Type, Total GB, Free GB, Usage %, VMs.
Usage above 85% is highlighted in red.

### `datastore browse`

Browse files in a datastore directory. Supports glob pattern filtering.

```bash
# Browse root of a datastore
vmware-storage datastore browse datastore01

# Browse a subdirectory
vmware-storage datastore browse datastore01 --path "iso-images"

# Filter by pattern
vmware-storage datastore browse datastore01 --pattern "*.ova"
vmware-storage datastore browse datastore01 --path "templates" --pattern "*.iso"
```

| Argument/Option | Required | Default | Description |
|----------------|:--------:|---------|-------------|
| `ds_name` | Yes | - | Datastore name (case-sensitive) |
| `--path` | No | `""` (root) | Subdirectory path within the datastore |
| `--pattern` | No | `"*"` | Glob pattern to filter files |

Output: JSON array of file objects with `name`, `size_mb`, `type`, `modified`, `ds_path`.

### `datastore scan-images`

Scan a datastore for deployable images (OVA, ISO, OVF, VMDK).

```bash
vmware-storage datastore scan-images datastore01
vmware-storage datastore scan-images datastore01 --target prod-vcenter
```

| Argument/Option | Required | Default | Description |
|----------------|:--------:|---------|-------------|
| `ds_name` | Yes | - | Datastore name |

Scans for patterns: `*.ova`, `*.ovf`, `*.iso`, `*.vmdk`. Results are sorted by name.

## iSCSI Commands

### `iscsi enable`

Enable the software iSCSI adapter on an ESXi host.

```bash
vmware-storage iscsi enable esxi-01
vmware-storage iscsi enable esxi-01 --dry-run
```

| Argument/Option | Required | Default | Description |
|----------------|:--------:|---------|-------------|
| `host_name` | Yes | - | ESXi host name |
| `--dry-run` | No | `false` | Preview the operation without executing |

**Safety**: Requires double confirmation (two prompts). If the adapter is already enabled, returns current HBA device and IQN without making changes.

### `iscsi status`

Show iSCSI adapter status and configured send targets.

```bash
vmware-storage iscsi status esxi-01
```

| Argument/Option | Required | Default | Description |
|----------------|:--------:|---------|-------------|
| `host_name` | Yes | - | ESXi host name |

Output: JSON with `enabled`, `hba_device`, `iqn`, and `send_targets` (list of address/port pairs).

### `iscsi add-target`

Add an iSCSI send target to a host and automatically rescan storage.

```bash
vmware-stor

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 6mo 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 7mo agoRank 70

CopilotKit

The Frontend for Agents & Generative UI. React + Angular

OPENCLAW

Machine-readable data

The same record, as JSON, for agents and crawlers.

{
  "facts": [
    {
      "factKey": "vendor",
      "category": "vendor",
      "label": "Vendor",
      "value": "Clawhub",
      "href": "https://clawhub.ai/zw008/skills/vmware-storage",
      "sourceUrl": "https://clawhub.ai/zw008/skills/vmware-storage",
      "sourceType": "profile",
      "confidence": "medium",
      "observedAt": "2026-10-09T04:07:22.221Z",
      "isPublic": true
    },
    {
      "factKey": "protocols",
      "category": "compatibility",
      "label": "Protocol compatibility",
      "value": "OpenClaw",
      "href": "https://www.xpersona.co/api/v1/agents/clawhub-zw008-vmware-storage/contract",
      "sourceUrl": "https://www.xpersona.co/api/v1/agents/clawhub-zw008-vmware-storage/contract",
      "sourceType": "contract",
      "confidence": "medium",
      "observedAt": "2026-10-09T04:07:22.221Z",
      "isPublic": true
    },
    {
      "factKey": "traction",
      "category": "adoption",
      "label": "Adoption signal",
      "value": "5.3K downloads",
      "href": "https://clawhub.ai/zw008/vmware-storage",
      "sourceUrl": "https://clawhub.ai/zw008/vmware-storage",
      "sourceType": "profile",
      "confidence": "medium",
      "observedAt": "2026-10-09T04:07:22.221Z",
      "isPublic": true
    },
    {
      "factKey": "latest_release",
      "category": "release",
      "label": "Latest release",
      "value": "1.12.0",
      "href": "https://clawhub.ai/zw008/vmware-storage",
      "sourceUrl": "https://clawhub.ai/zw008/vmware-storage",
      "sourceType": "release",
      "confidence": "medium",
      "observedAt": "2026-09-20T14:52:48.885Z",
      "isPublic": true
    },
    {
      "factKey": "handshake_status",
      "category": "security",
      "label": "Handshake status",
      "value": "UNKNOWN",
      "href": "https://www.xpersona.co/api/v1/agents/clawhub-zw008-vmware-storage/trust",
      "sourceUrl": "https://www.xpersona.co/api/v1/agents/clawhub-zw008-vmware-storage/trust",
      "sourceType": "trust",
      "confidence": "medium",
      "observedAt": null,
      "isPublic": true
    }
  ],
  "events": [
    {
      "eventType": "release",
      "title": "Release 1.12.0",
      "description": "MCP instructions now name the configured targets and how to choose one; a config that cannot be read says so instead of falling silent.",
      "href": "https://clawhub.ai/zw008/vmware-storage",
      "sourceUrl": "https://clawhub.ai/zw008/vmware-storage",
      "sourceType": "release",
      "confidence": "medium",
      "observedAt": "2026-09-20T14:52:48.885Z",
      "isPublic": true
    }
  ]
}

Record generated Oct 9, 2026.

About

Avoid when

Public facts

Install and run

Documentation

Extracted files

SKILL.md

_meta.json

references/agent-guardrails.md

references/capabilities.md

references/cli-reference.md

Related agents

activepieces

cherry-studio

AionUi

CopilotKit

Machine-readable data