How do I install the Full Infrastructure Discovery skill?

Run npx skillmds@latest add knuckles-team/full-infrastructure-discovery 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 Full Infrastructure Discovery 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 Full Infrastructure Discovery?

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 Full Infrastructure Discovery free to use?

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

Who published Full Infrastructure Discovery?

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

Full Infrastructure Discovery by knuckles-team

Name: Full Infrastructure Discovery
Author: Knuckles-Team

Full Infrastructure Discovery

Full self-hosted or enterprise infrastructure discovery pipeline. Scans an AgentConfig-managed inventory via tunnel-manager, discovers containers via configured runtime providers, maps networking and DNS, and ingests a privacy-safe topology snapshot into the Knowledge Graph. Use for a governed fleet topology refresh; do not use for ad hoc host probing.

Knuckles-Team a96a23a 2 files · 2.7 KB Updated Sep 17, 2026

File contents

full-infrastructure-discovery Workflow

Discover a self-hosted or enterprise deployment from AgentConfig connection references and ingest a privacy-safe topology snapshot. Environment topology stays in the configured providers rather than this workflow.

Step 0: discover-hosts [skill: tunnel-manager-mcp]

List all hosts from inventory and check SSH connectivity Expected: host, inventory, connectivity

Step 1: container-manager-mcp

List all containers across all discovered hosts with their images, status, ports, and networks Expected: container, image, status Depends On: Step 0

Step 2: portainer-mcp

List all Portainer environments and stacks with their deployment status Expected: environment, stack, endpoint

Step 3: scan-host-networks [skill: tunnel-manager-mcp]

Run network interface scan across all hosts to discover subnets, VLANs, and VPN tunnels Expected: network, interface, subnet Depends On: Step 0

Step 4: technitium-dns-mcp

List all DNS records to map domain-to-service routing Expected: record, domain

Step 5: graph-os

Ingest discovered topology into the Knowledge Graph as HardwareNode, Container, ContainerStack, NetworkSubnet, DNSRecord nodes with RUNS_ON, BELONGS_TO_STACK, RESOLVES_DNS_FOR relationships Expected: ingest, node, relationship Depends On: Step 1, Step 2, Step 3, Step 4

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 — discover-hosts; Step 1 — container-manager-mcp; Step 2 — portainer-mcp; Step 3 — scan-host-networks; Step 4 — technitium-dns-mcp; Step 5 — graph-os

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: full-infrastructure-discoverydescription: Full self-hosted or enterprise infrastructure discovery pipeline. Scans an AgentConfig-managed inventory via tunnel-manager, discovers containers via configured runtime providers, maps networking and DNS, and ingests a privacy-safe topology snapshot into the Knowledge Graph. Use for a governed fleet topology refresh; do not use for ad hoc host probing.---# full-infrastructure-discovery WorkflowDiscover a self-hosted or enterprise deployment from AgentConfig connectionreferences and ingest a privacy-safe topology snapshot. Environment topology staysin the configured providers rather than this workflow.### Step 0: discover-hosts [skill: tunnel-manager-mcp]List all hosts from inventory and check SSH connectivityExpected: host, inventory, connectivity### Step 1: container-manager-mcpList all containers across all discovered hosts with their images, status, ports, and networksExpected: container, image, statusDepends On: Step 0### Step 2: portainer-mcpList all Portainer environments and stacks with their deployment statusExpected: environment, stack, endpoint### Step 3: scan-host-networks [skill: tunnel-manager-mcp]Run network interface scan across all hosts to discover subnets, VLANs, and VPN tunnelsExpected: network, interface, subnetDepends On: Step 0### Step 4: technitium-dns-mcpList all DNS records to map domain-to-service routingExpected: record, domain### Step 5: graph-osIngest discovered topology into the Knowledge Graph as HardwareNode, Container, ContainerStack, NetworkSubnet, DNSRecord nodes with RUNS_ON, BELONGS_TO_STACK, RESOLVES_DNS_FOR relationshipsExpected: ingest, node, relationshipDepends On: Step 1, Step 2, Step 3, Step 4## 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 — discover-hosts; Step 1 — container-manager-mcp; Step 2 — portainer-mcp; Step 3 — scan-host-networks; Step 4 — technitium-dns-mcp; Step 5 — graph-os**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