How do I install the Hardware Sweep skill?

Run npx skillmds@latest add knuckles-team/hardware-sweep in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Hardware Sweep safe to use?

This skill has not completed SkillMD's automated safety review yet. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Hardware Sweep?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Hardware Sweep free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Hardware Sweep?

Knuckles-Team (@knuckles-team) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Hardware Sweep by knuckles-team — Agent Skill

Name: Hardware Sweep
Author: Knuckles-Team

Hardware Sweep

OS and hardware information sweep across all inventory hosts. Collects CPU, memory, disk, GPU, and OS details for each machine and ingests them into the Knowledge Graph for troubleshooting and service designation decisions.

Knuckles-Team dd7fb51 2 files · 2.9 KB Updated Sep 17, 2026

File contents

Hardware Sweep Workflow

CONCEPT:INFRA-001

Steps

Step 0: Tunnel Manager Mcp

Agent: discovery-agent Tools: tun_tm_system, tun_tm_hosts

List all hosts from inventory with their connectivity status Expected: host, inventory

Step 1: collect-host-hardware [skill: systems-manager-mcp]

Agent: deployer-agent Tools: pt_stack, cnt_cm_compose_operations

For each reachable host, collect CPU model and core count, total and available RAM, disk partitions and usage, OS distribution and kernel version Expected: cpu, memory, disk, os

Step 2: collect-accelerators [skill: systems-manager-mcp]

Agent: verifier-agent Tools: pt_docker, cnt_cm_container_operations

For each reachable host, detect GPU/accelerator hardware via lspci or nvidia-smi and collect driver versions Expected: gpu, accelerator, driver

Step 3: Graph Os

Agent: dns-configurator Tools: adg_rewrites, td_zones

Update HardwareNode entries in the KG with collected hardware metadata and create GPUAccelerator nodes with HAS_ACCELERATOR relationships Expected: update, hardware, gpu

Step 4: KG Persistence [depends_on: graph-os]

Agent: dns-configurator Tools: graph_write

Persist workflow results as nodes and edges in the Knowledge Graph. Create appropriate typed nodes with metadata and link to existing domain entities.

Output

Hardware Sweep results persisted in KG
Structured report (MD/PDF)
Audit trail with timestamps and agent attributions

Execution

Run this workflow as a dependency-ordered DAG. Steps with no unmet depends_on run in parallel; dependents run after their prerequisites complete.

Run first (in parallel): Step 0 — Tunnel Manager Mcp; Step 1 — collect-host-hardware; Step 2 — collect-accelerators; Step 3 — Graph Os
After level 0: Step 4 — KG Persistence

Execution: If graph-os is reachable, offload the whole DAG via graph_orchestrate action=execute_workflow (or the kg-delegate skill) for true parallel/swarm execution. Otherwise execute the steps natively in dependency order: run steps with no unmet depends_on in parallel, then their dependents.

---name: hardware-sweepdescription: OS and hardware information sweep across all inventory hosts. Collects CPU, memory, disk, GPU, and OS details for each machine and ingests them into the Knowledge Graph for troubleshooting and service designation decisions.---# Hardware Sweep Workflow**CONCEPT:INFRA-001**OS and hardware information sweep across all inventory hosts. Collects CPU, memory, disk, GPU, and OS details for each machine and ingests them into the Knowledge Graph for troubleshooting and service designation decisions.## Steps### Step 0: Tunnel Manager Mcp**Agent**: `discovery-agent`**Tools**: `tun_tm_system, tun_tm_hosts`List all hosts from inventory with their connectivity statusExpected: `host, inventory`### Step 1: collect-host-hardware [skill: systems-manager-mcp]**Agent**: `deployer-agent`**Tools**: `pt_stack, cnt_cm_compose_operations`For each reachable host, collect CPU model and core count, total and available RAM, disk partitions and usage, OS distribution and kernel versionExpected: `cpu, memory, disk, os`### Step 2: collect-accelerators [skill: systems-manager-mcp]**Agent**: `verifier-agent`**Tools**: `pt_docker, cnt_cm_container_operations`For each reachable host, detect GPU/accelerator hardware via lspci or nvidia-smi and collect driver versionsExpected: `gpu, accelerator, driver`### Step 3: Graph Os**Agent**: `dns-configurator`**Tools**: `adg_rewrites, td_zones`Update HardwareNode entries in the KG with collected hardware metadata and create GPUAccelerator nodes with HAS_ACCELERATOR relationshipsExpected: `update, hardware, gpu`### Step 4: KG Persistence [depends_on: graph-os]**Agent**: `dns-configurator`**Tools**: `graph_write`Persist workflow results as nodes and edges in the Knowledge Graph.Create appropriate typed nodes with metadata and link to existing domain entities.## Output- Hardware Sweep results persisted in KG- Structured report (MD/PDF)- Audit trail with timestamps and agent attributions## ExecutionRun this workflow as a dependency-ordered DAG. Steps with no unmet `depends_on` run in parallel; dependents run after their prerequisites complete.- **Run first (in parallel):** Step 0 — Tunnel Manager Mcp; Step 1 — collect-host-hardware; Step 2 — collect-accelerators; Step 3 — Graph Os- **After level 0:** Step 4 — KG Persistence**Execution:** If graph-os is reachable, offload the whole DAG via `graph_orchestrate action=execute_workflow` (or the `kg-delegate` skill) for true parallel/swarm execution. Otherwise execute the steps natively in dependency order: run steps with no unmet `depends_on` in parallel, then their dependents.

Frequently asked questions