Agent skill

Cml Node Operations

by automateyournetwork in automateyournetwork/netclaw

CML node operations — start, stop, console access, CLI execution, config management, node details.

Apache-2.0Auto-check passed

Install Cml Node Operations

skills CLI
$ npx skills add automateyournetwork/netclaw --skill cml-node-operations -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install automateyournetwork/netclaw cml-node-operations --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/automateyournetwork/netclaw.git skills-src && mkdir -p .claude/skills && cp -r skills-src/workspace/skills/cml-node-operations .claude/skills/cml-node-operations && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
cml-node-operations
GitHub stars
675
Token cost
~2k tokens
SKILL.md length
691 words
Files
1
Skills in repo
120
Repo updated
First seen
Licence
Apache-2.0

At a glance

CML node operations — start, stop, console access, CLI execution, config management, node details.

  • Works in 6 steps: Check node state: get_node to see… → Set startup config: set_node_config with… → Start the node: start_node to boot it → …
  • Stopping a CML node
  • SKILL.md covers MCP Server, Available Tools, Node States and Workflow: Configure and Boot a…, plus 8 more sections
  • Needs CML_PASSWORD

What it does

Cml Node Operations is an agent skill from automateyournetwork/netclaw. CML node operations — start, stop, console access, CLI execution, config management, node details. Use when starting or stopping a CML node, running show commands on a lab router, setting startup configs, or reading console logs.

Its SKILL.md is about 2k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It works with Model Context Protocol. The repository describes itself as: An AI agent that claws through your network. The licence is Apache-2.0.

When your agent uses it

  • Stopping a CML node
  • Running show commands on a lab router
  • Setting startup configs
  • Reading console logs

Example prompts

  • “/cml-node-operations”

Workflow steps

6 steps, taken from the first numbered list in SKILL.md.

  1. Check node state: get_node to see current state
  2. Set startup config: set_node_config with the full configuration
  3. Start the node: start_node to boot it
  4. Wait for boot: Nodes take 30-120 seconds depending on type
  5. Verify: execute_command to run show version or show ip int brief
  6. Report: Tell the user the node is ready

What it can do on your machine

Read from SKILL.md and the folder at commit 95bb17e. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names these keys or tokens, usually read from environment variables:

    • CML_PASSWORD

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Cml Node Operations loads about 2k tokens when it runs. Until then it costs about 62 tokens; SKILL.md has 691 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~62
When it runs · the whole SKILL.md, loaded when a task matches
~2k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from automateyournetwork/netclaw at commit 95bb17e, republished under its Apache-2.0 licence (© automateyournetwork). 691 words, ~1,991 tokens.

Download SKILL.mdSave it as .claude/skills/cml-node-operations/SKILL.md (or your agent's skills folder).
name
cml-node-operations
description
CML node operations — start, stop, console access, CLI execution, config management, node details. Use when starting or stopping a CML node, running show commands on a lab router, setting startup configs, or reading console logs.
version
1.0.0
license
Apache-2.0
tags
cml, nodes, console, cli, config

CML Node Operations

MCP Server

  • Command: cml-mcp (pip-installed, stdio transport)
  • Requires: CML_URL, CML_USERNAME, CML_PASSWORD environment variables
  • Optional: cml-mcp[pyats] for CLI execution via pyATS

Available Tools

Node Lifecycle
ToolParametersWhat It Does
start_nodelab_id/lab_title, node_id/node_labelStart (boot) a single node
stop_nodelab_id/lab_title, node_id/node_labelStop (shutdown) a single node
get_nodelab_id/lab_title, node_id/node_labelGet node details: state, CPU, RAM, interfaces, config
get_nodeslab_id/lab_titleList all nodes with their current states
wipe_nodelab_id/lab_title, node_id/node_labelWipe a node's configuration (reset to default)
Configuration Management
ToolParametersWhat It Does
set_node_configlab_id/lab_title, node_id/node_label, configSet a node's startup configuration
get_node_configlab_id/lab_title, node_id/node_labelGet a node's current configuration
download_lab_configslab_id/lab_titleDownload all node configs from a running lab
Console & CLI Access
ToolParametersWhat It Does
get_node_consolelab_id/lab_title, node_id/node_labelGet console connection details (URL, protocol)
get_node_console_loglab_id/lab_title, node_id/node_label, lines?Retrieve console log output from a running node
execute_commandlab_id/lab_title, node_id/node_label, commandExecute a CLI command on a running node (requires pyATS)

Node States

StateMeaning
DEFINED_ON_CORENode exists but is not running
BOOTINGNode is in the process of booting
BOOTEDNode has finished booting and is reachable
STOPPEDNode has been shut down

Workflow: Configure and Boot a Node

When a user wants to configure a specific node:

  1. Check node state: get_node to see current state
  2. Set startup config: set_node_config with the full configuration
  3. Start the node: start_node to boot it
  4. Wait for boot: Nodes take 30-120 seconds depending on type
  5. Verify: execute_command to run show version or show ip int brief
  6. Report: Tell the user the node is ready

Workflow: Collect Running Configs

When a user wants to back up or review configs:

  1. Ensure lab is running: get_lab to check state
  2. Download all configs: download_lab_configs gets everything at once
  3. Or target specific nodes: get_node_config for individual nodes
  4. Optionally commit to GitHub: Use github-ops skill to commit configs to a repo

Workflow: Console Log Troubleshooting

When a user needs to see what happened during boot or troubleshoot a node:

  1. Check node state: get_node — node must be BOOTED or BOOTING
  2. Get console log: get_node_console_log to retrieve recent console output
  3. Analyze output: Look for error messages, boot failures, config errors
  4. Common issues to spot:
    • %PARSER-4-BADCFG — invalid configuration commands
    • %LINK-3-UPDOWN — interface state changes
    • %OSPF-5-ADJCHG — OSPF adjacency changes
    • %BGP-5-ADJCHANGE — BGP neighbor state changes
    • %SYS-5-RESTART — system restart messages
    • Boot failures, license errors, memory allocation errors
  5. Report: Summarize the console log findings
Show full SKILL.md (285 more words)Show less

Workflow: Execute CLI Commands

When a user wants to run show commands or make live changes:

  1. Verify node is BOOTED: get_node to check state
  2. Execute command: execute_command with the CLI command
  3. Parse output: Present the results in a readable format
  4. Multiple commands: Run them sequentially, one execute_command per command

Common commands to execute:

show ip interface brief
show ip ospf neighbor
show ip bgp summary
show running-config
show cdp neighbor
show version
show ip route
show interfaces status

Workflow: Reset and Reconfigure

When a user wants to start fresh with a node:

  1. Stop the node: stop_node
  2. Wipe the config: wipe_node resets to factory default
  3. Set new config: set_node_config with the new startup configuration
  4. Start the node: start_node
  5. Verify: Execute show commands to confirm the new config took effect

Startup Configuration Templates

IOSv Router (Basic OSPF)
hostname {HOSTNAME}
!
interface Loopback0
 ip address {LOOPBACK_IP} 255.255.255.255
!
interface GigabitEthernet0/0
 ip address {MGMT_IP} {MASK}
 no shutdown
!
interface GigabitEthernet0/1
 ip address {P2P_IP} {MASK}
 no shutdown
!
router ospf 1
 router-id {LOOPBACK_IP}
 network {LOOPBACK_IP} 0.0.0.0 area 0
 network {P2P_NETWORK} {WILDCARD} area 0
!
line con 0
 logging synchronous
line vty 0 4
 login local
 transport input ssh
!
end
IOSv Router (Basic BGP)
hostname {HOSTNAME}
!
interface Loopback0
 ip address {LOOPBACK_IP} 255.255.255.255
!
interface GigabitEthernet0/1
 ip address {PEER_IP} {MASK}
 no shutdown
!
router bgp {LOCAL_AS}
 bgp router-id {LOOPBACK_IP}
 bgp log-neighbor-changes
 neighbor {NEIGHBOR_IP} remote-as {REMOTE_AS}
 !
 address-family ipv4
  network {LOOPBACK_IP} mask 255.255.255.255
  neighbor {NEIGHBOR_IP} activate
 exit-address-family
!
end
NX-OS Switch (Basic VXLAN Leaf)
hostname {HOSTNAME}
!
feature ospf
feature bgp
feature nv overlay
feature vn-segment-vlan-based
!
interface loopback0
  ip address {LOOPBACK_IP}/32
!
interface Ethernet1/1
  description To-Spine1
  no switchport
  ip address {P2P_IP}/30
  no shutdown
!
router ospf 1
  router-id {LOOPBACK_IP}
!
router bgp {AS}
  router-id {LOOPBACK_IP}
  neighbor {SPINE_IP} remote-as {AS}
    update-source loopback0
    address-family l2vpn evpn
      send-community extended
!
end
IOS-XR Router (Basic IS-IS)
hostname {HOSTNAME}
!
interface Loopback0
 ipv4 address {LOOPBACK_IP} 255.255.255.255
!
interface GigabitEthernet0/0/0/0
 ipv4 address {P2P_IP} {MASK}
 no shutdown
!
router isis CORE
 is-type level-2-only
 net 49.0001.{SYSTEM_ID}.00
 address-family ipv4 unicast
  metric-style wide
 !
 interface Loopback0
  passive
  address-family ipv4 unicast
  !
 !
 interface GigabitEthernet0/0/0/0
  address-family ipv4 unicast
  !
 !
!
end

Important Rules

  • Check node state before operations — don't start an already-booted node or stop an already-stopped one
  • Wait for boot — IOSv takes ~60s, NX-OS ~90s, IOS-XR ~120s to boot
  • execute_command requires pyATS — the cml-mcp[pyats] extra must be installed
  • Set configs BEFORE starting — set_node_config sets the startup config; apply it before boot
  • Use labels not IDs — labels like "R1" are more human-readable than UUIDs
  • Record in GAIT — log all configuration changes and CLI commands for audit trail

Environment Variables

  • CML_URL — CML server URL
  • CML_USERNAME — CML username
  • CML_PASSWORD — CML password
  • CML_VERIFY_SSL — Verify SSL certificate (true/false)

Failure Behavior

  • On a tool error (timeout, unreachable host, malformed response), report the failure and its error message directly to the user rather than fabricating or guessing at results.
  • Do not automatically retry a write/mutating operation after a failure — surface the error and get explicit confirmation before retrying, since a blind retry on a partially-applied change can leave state inconsistent.

© automateyournetwork, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in workspace/skills/cml-node-operations of automateyournetwork/netclaw.

Open the folder on GitHubat commit 95bb17e

Compare with similar skills

Cml Node Operations next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Cml Node Operations compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Cml Node Operations this skillautomateyournetwork/netclaw675—~2kAutomated safety check: PassApache-2.0
MCP Server Builderanthropics/skills180k64 repos~2.3kAutomated safety check: PassApache-2.0
MCP Server BuildershareAI-lab/learn-claude-code78k5 repos~1.2kAutomated safety check: PassMIT
MCP Integration for Pluginsanthropics/claude-plugins-official38k11 repos~3.1kAutomated safety check: PassApache-2.0
Figma use_figma Plugin API Ruleswarpdotdev/warp65k4 repos~4.4kAutomated safety check: PassAGPL-3.0
Stitch to Remotion Walkthrough Videosgoogle-labs-code/stitch-skills8.4k6 repos~3.2kAutomated safety check: NotesApache-2.0

Similar skills

  • MCP Server Builder

    anthropics/skills

    Official

    Guides the design and implementation of Model Context Protocol servers in TypeScript or Python, from tool naming and error messages to evaluation.

    180k GitHub starsUsed in 64 repos~2.3k tokens
    Agent WorkflowsAuto-check passed
  • MCP Server Builder

    shareAI-lab/learn-claude-code

    Walks through building MCP servers in Python or TypeScript that expose tools, resources and prompts to Claude, with templates, registration and testing.

    78k GitHub starsUsed in 5 repos~1.2k tokens
    Agent WorkflowsAuto-check passed
  • MCP Integration for Plugins

    anthropics/claude-plugins-official

    Official

    Explains how to bundle Model Context Protocol servers in a Claude Code plugin, covering config files, stdio, SSE, HTTP and WebSocket server types, and authentication.

    38k GitHub starsUsed in 11 repos~3.1k tokens
    Agent WorkflowsAuto-check passed
  • Required groundwork before any use_figma call: the rules and reference files for running JavaScript in a Figma file through the Plugin API without common failures.

    65k GitHub starsUsed in 4 repos~4.4k tokens
    Frontend & DesignAuto-check passed
  • Stitch to Remotion Walkthrough Videos

    google-labs-code/stitch-skills

    Official

    Builds walkthrough videos from Stitch design projects using Remotion, with transitions, zoom effects and text overlays on each screen.

    8.4k GitHub starsUsed in 6 repos~3.2k tokens
    Media & CreativeAuto-check: notes
  • MCP Development

    coollabsio/coolify

    A skill your agent uses for Laravel MCP development. An agent skill from coollabsio/coolify.

    63k GitHub starsUsed in 1 repo~949 tokens
    Frontend & DesignAuto-check passed

More from automateyournetwork/netclaw

All 120 skills in this repo
  • EVE-NG Lab Topology Design

    automateyournetwork/netclaw

    Entry point for designing EVE-NG network labs: classifies the request, gathers missing requirements, proposes options and validates the resulting topology.

    675 GitHub stars~612 tokensUpdated 2 days ago
    Auto-check passed
  • ACI Policy Change Deployment

    automateyournetwork/netclaw

    Deploys Cisco ACI policy changes only behind an approved ServiceNow Change Request, capturing pre and post-change fault baselines and rolling back automatically on a fault delta.

    675 GitHub stars~4.2k tokensUpdated 2 days ago
    Auto-check passed
  • Cisco ACI Fabric Health Audit

    automateyournetwork/netclaw

    Runs a phased health audit of a Cisco ACI fabric through MCP tools: node status, links, tenant and policy review, faults and endpoint learning.

    675 GitHub stars~2.9k tokensUpdated 2 days ago
    Auto-check passed
  • Anta Validation

    automateyournetwork/netclaw

    Validate Arista EOS network state against ANTA's pre-built 208-test catalogue, with structured pass/fail verdicts.

    675 GitHub stars~1.2k tokensUpdated 2 days ago
    Auto-check passed
  • Arista Cvp

    automateyournetwork/netclaw

    Arista CloudVision Portal (CVP) automation via REST API — device inventory, events, connectivity monitoring, tag management (4 tools).

    675 GitHub stars~2.2k tokensUpdated 2 days ago
    Auto-check: notes
  • AWS Cloud Monitoring

    automateyournetwork/netclaw

    AWS CloudWatch monitoring — metrics, alarms, log queries, VPC flow log analysis, network performance.

    675 GitHub stars~1k tokensUpdated 2 days ago
    Auto-check passed

Questions about Cml Node Operations

What does Cml Node Operations do?

CML node operations — start, stop, console access, CLI execution, config management, node details. Cml Node Operations is an agent skill from automateyournetwork/netclaw. CML node operations — start, stop, console access, CLI execution, config management, node details.

When should I use Cml Node Operations?

Cml Node Operations fits situations like: stopping a CML node; running show commands on a lab router; setting startup configs; reading console logs.

How do I install Cml Node Operations in Claude Code?

Run `npx skills add automateyournetwork/netclaw --skill cml-node-operations -a claude-code`. Or copy the skill folder (workspace/skills/cml-node-operations in automateyournetwork/netclaw) into .claude/skills/cml-node-operations in your project. Claude Code loads it when a task matches its description.

How do I install Cml Node Operations in Codex?

Run `npx skills add automateyournetwork/netclaw --skill cml-node-operations -a codex`. Or copy the skill folder (workspace/skills/cml-node-operations in automateyournetwork/netclaw) into .agents/skills/cml-node-operations in your project. Codex loads it when a task matches its description.

Can I use Cml Node Operations in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add automateyournetwork/netclaw --skill cml-node-operations -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/cml-node-operations, .gemini/skills/cml-node-operations, .github/skills/cml-node-operations and .opencode/skills/cml-node-operations in your project.

What does Cml Node Operations need to run?

Going by SKILL.md and its folder, Cml Node Operations needs credentials named CML_PASSWORD.

Does Cml Node Operations access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Cml Node Operations safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Cml Node Operations use?

Cml Node Operations is published under the Apache-2.0 licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Cml Node Operations use?

About 2k tokens (SKILL.md is roughly 8k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Cml Node Operations?

Skills that share tags, products or a category with Cml Node Operations: MCP Server Builder (anthropics/skills, 180k stars), MCP Server Builder (shareAI-lab/learn-claude-code, 78k stars), MCP Integration for Plugins (anthropics/claude-plugins-official, 38k stars) and Figma use_figma Plugin API Rules (warpdotdev/warp, 65k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Cml Node Operations?

automateyournetwork (a GitHub user) maintains it in automateyournetwork/netclaw, which has 675 GitHub stars. The repository holds 120 skills in this directory. The repository was last updated on October 5, 2026.

Source: automateyournetwork/netclaw on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.