Real Skill packageSource verifiedClawHub registry

OpenClaw agent hosting: spawn a swarm on confidential VPS

Deploy OpenClaw subagents to their own cloud server: start another OpenClaw agent on a confidential virtual machine (CVM, a sealed Intel TDX VM) for agents that hold keys or money, or on a cheap plain VM for workers with nothing secret, one per agent, for trading swarms or any swarm, by the hour, paid in USDC from a prepaid Agentgates balance. Its model is Agentgates inference.

Identity and source

Publisher attributionAgentgatesregistry owner unverified by skillvetai
Functional categoryAgent Engineering, Security & Governanceautomatically inferred · 61% rule confidence
Package forminstruction with code4 recorded files
Canonical sourceClawHub registryclawhub:agentgates:agentgates-swarm
Open canonical source ↗

Platform declarations

These states come from the source or distribution context. None of the entries below are SkillVetAI compatibility test results.

OpenClawnative officialProvenance: registry distribution

Independent structural checks

These checks parse the fixed package against dated platform rules. They do not execute the Skill or verify task behavior.

Claude Codepasses structure
Checker 0.1.0 · agent-skills-2026-08-13+claude-code-docs-2026-08-13 · 11/12/2026.claude/skills/agentgates-swarm

Runtime, accounts, dependencies, permissions, network behavior and task quality remain untested.

OpenAI Codexpasses with warnings
Checker 0.1.0 · agent-skills-2026-08-13+codex-docs-2026-08-13 · 11/12/2026.agents/skills/agentgates-swarm
1 structural issue
  • warning: Codex portability follows Agent Skills, where allowed-tools is a space-separated string. SKILL.md

Runtime, accounts, dependencies, permissions, network behavior and task quality remain untested.

OpenClawpasses with warnings
Checker 0.1.0 · agent-skills-2026-08-13+openclaw-docs-2026-08-13 · 11/12/2026skills/agentgates-swarm
1 structural issue
  • warning: OpenClaw portability follows Agent Skills, where allowed-tools is a space-separated string. SKILL.md

Runtime, accounts, dependencies, permissions, network behavior and task quality remain untested.

Installation and inspection

This command is recorded from the source ecosystem and resolves the registry's latest release. The fixed release shown on this page should be inspected before adoption.

clawhub install @agentgates/agentgates-swarm
clawhub inspect @agentgates/agentgates-swarm --version 1.0.5

Security evidence

SkillVetAI static result: no findings detected

This automated, non-executing scan is bound to this release hash. It is not a safety certification and may contain false positives or false negatives.

Status
completed
Coverage
full text content
Files
4 / 4 inspected as text
Checked
11/12/2026, 7:10:43 AM
Scanner
0.1.3
Policy
1.0.3
5 inferred permission indicators
  • network access — automatically inferred
  • filesystem read — automatically inferred
  • filesystem write — automatically inferred
  • credential access — automatically inferred
  • external write action — automatically inferred
3 dependency and API indicators
  • api: api.agentgates.ai
  • api: clawhub.ai
  • api: github.com
External clawhub result: suspicious

This is registry-supplied evidence for the recorded release, not an independent SkillVetAI scan. Check the canonical source for the full report, scanner versions, scope, and current moderation state.

Evidence checked
11/12/2026, 6:16:17 AM
Release binding
Matches this record
  • skillspector: suspicious
  • llm: suspicious

Recorded files

The catalog stores hashes and an inventory summary for change detection. It does not republish the package contents.

Package content hashsha256:74496fa9a884df8bb52015c5c51cfe4f6be691e84e733bbbacf94ac7638f6b57
Show up to 4 recorded paths
  • compose.yml
  • scripts/openclaw-machine.mjs
  • skill-card.md
  • SKILL.md

Source changelog

Cheap workers on plain VMs: start --plan compute.vm.standard for a worker with nothing secret on it (its host can read it). The script waits for a plain VM's https name and sends the proxy range OpenClaw needs to answer through it. The compose merges its settings into OpenClaw's own file at every boot, so a model sent by update takes effect. SKILL.md declares the one tool it uses (exec).

Release security diff

mediumCompared fixed releases 1.0.3 and 1.0.5; 0 finding and 0 permission indicators were added.

Both fixed releases were scanned under the current scanner and policy, so finding, permission and dependency changes are available.

Change reasons and limitations
  • content hash changed

Observed release history

These older immutable releases were observed by prior successful syncs. They remain recorded when a newer release becomes current.

1.0.311/6/2026sha256:d373ed6a348e231468438ddd3b3a11ca7b7891665e748fdc570f62899e9fbe8d
1.0.011/6/2026sha256:69fcd85bfe5b6445274290c5992425ba2f0f23c8a6232805fc20fe795e064688