servosity/msp-skills/liongard

Claude Code and agent skill by servosity/msp-skills

Trust tier 3
  • community
Source check pending

Checking that the SKILL.md file is still in the repository.

Every Liongard endpoint, plus an offline copy of your whole MSP estate you can join, search, and drift-check from one command. Trigger phrases: `what changed across my Liongard environments`, `show stale Liongard launchpoints`, `which Liongard agents are offline`, `pivot a Liongard metric across all systems`, `Liongard drift report`, `use liongard`, `run liongard`.

Install

npx vskill@latest install servosity/msp-skills/liongard

SKILL.md

Liongard - Claude Code Skill

Prerequisites: Install the CLI

This skill drives the liongard-cli binary. You must verify the CLI is installed before invoking any command from this skill. If it is missing, install it first:

  1. macOS / Linux:

``bash bash <(curl -fsSL https://raw.githubusercontent.com/Servosity/msp-skills/main/skills/liongard/install.sh) ``

  1. Windows (PowerShell):

``powershell iwr -useb https://raw.githubusercontent.com/Servosity/msp-skills/main/skills/liongard/install.ps1 | iex ``

  1. Verify: liongard-cli --version
  2. Ensure ~/.local/bin (macOS / Linux) or %LOCALAPPDATA%\Programs\msp-skills (Windows) is on $PATH.

The installer downloads the liongard-cli and liongard-mcp binaries into ~/.local/bin (macOS / Linux) or %LOCALAPPDATA%\Programs\msp-skills (Windows). It does not register the skill with your agent and writes no MCP client config - see mcp-install.md for that wire-up.

If --version reports "command not found" after install, the runtime cannot see the binary directory on $PATH. Do not proceed with skill commands until verification succeeds.

Liongard's API answers one environment at a time and only through the web UI or per-instance REST calls. This CLI syncs every environment, system, launchpoint, inspector, agent, detection, metric, and timeline entry into a local SQLite store, then runs cross-estate joins the live API never returns: drift since a window, stale launchpoints, offline agents, monitoring-coverage gaps, and metric pivots. Agent-native throughout - --json, --select, --csv, and typed exit codes.

When to Use This CLI

Reach for this CLI when an agent needs whole-estate Liongard answers - what changed across all clients, which collectors are stale, which agents are offline, where monitoring coverage is missing, or one metric pivoted across every system. It is the right tool for scripted MSP health sweeps and QBR/SLA reporting where the per-environment web UI and one-call-at-a-time API are too slow. Prefer it over raw API calls whenever the question spans more than one environment or needs offline, structured, composable output.

Unique Capabilities

Whole-estate visibility
  • `drift` - Every change detected across all your client environments within a time window, joined to the owning environment and system.

_Reach for this when an agent needs the whole-estate 'what changed overnight' answer instead of paging the per-environment detections endpoint._

``bash liongard-cli drift --since 24h --agent ``

  • `environments overview` - One client's complete picture in a single command: its systems, each system's launchpoints, agent, latest inspection, open detections, and key metrics.

_Use when an agent is asked about a specific client and needs the joined picture rather than five separate endpoint calls._

``bash liongard-cli environments overview 42 --full --agent ``

  • `systems history` - The full chronological change history of one system: every detection and inspection entry in time order.

_Reach for this when an agent needs 'when did this system change / break' instead of paging timeline and detections endpoints separately._

``bash liongard-cli systems history 4821 --agent ``

Inspection health
  • `launchpoints stale` - Every launchpoint whose newest inspection is older than a threshold, with the owning environment and system named.

_Use to find collectors that silently stopped reporting before a client notices their data is old._

``bash liongard-cli launchpoints stale --older-than 7d --agent ``

  • `agents offline` - Every offline agent across the estate, joined to the environment it serves.

_Use for the daily 'is everything still collecting' health sweep across all clients at once._

``bash liongard-cli agents offline --agent ``

  • `coverage` - Monitoring gaps: systems with no launchpoint bound, and environments with no systems at all.

_Use during onboarding QA to catch clients you provisioned but never pointed an inspector at._

``bash liongard-cli coverage --agent ``

  • `launchpoints run-stale` - Find stale launchpoints and trigger an inspection run on each, in one guarded command.

_Use to re-kick every collector that fell behind, instead of clicking run on each launchpoint in the UI._

``bash liongard-cli launchpoints run-stale --older-than 7d ``

  • `detections failures` - Every inspection that ran but failed or errored across the estate, joined to the owning environment.

_Reach for this to find inspections that ran but errored - a different failure mode from collectors that silently stopped reporting (launchpoints stale)._

``bash liongard-cli detections failures --since 7d --agent ``

  • `inspectors coverage` - Which environments are missing a given inspector type - the estate-wide rollout-gap view.

_Reach for this when an agent needs 'who is missing the M365 inspector' instead of paging launchpoints per environment._

``bash liongard-cli inspectors coverage --inspector "Microsoft 365" --agent ``

  • `health` - One estate-wide health scorecard: stale launchpoints, offline agents, failed inspections, and coverage gaps as a single summary with a typed exit code.

_Reach for this for a single-command daily health check with a typed exit code, instead of running each sweep separately._

``bash liongard-cli health --agent ``

Reporting and SLA
  • `metrics pivot` - One RoarPath metric across every system it covers, CSV-ready for reports; the value column is filled only where the local store carries an evaluated value.

_Use to assemble a single metric across the whole estate for an SLA or QBR deck in one command._

``bash liongard-cli metrics pivot "MFA Enabled Count" --csv ``

  • `metrics breach` - Every system whose RoarPath metric value crosses a numeric threshold. It refuses until every covered system has an evaluated value in the local store; the synced metric definitions carry none (Liongard evaluates them per system: liongard-cli metrics evaluation).

_Use for SLA-breach and security-posture checks across all clients without N per-system calls._

``bash liongard-cli metrics breach "Patch Age Days" --op gt --value 30 --agent ``

Command Reference

access-keys - Manage access keys

  • liongard-cli access-keys create - Create an Access Token with the permission of user or with only 'Add Agent' permission
  • liongard-cli access-keys delete - Delete Access Token created by user
  • liongard-cli access-keys get - Returns a List of Access Tokens created by user
  • liongard-cli access-keys get-count - Return a count of all Access Tokens created by user

agents - Agents can be installed in the Cloud or On-Premise and are responsible for running inspections.

  • liongard-cli agents delete - Remove an agent
  • liongard-cli agents get - List all agents.
  • liongard-cli agents get-agentid - Get a specific Agent.
  • liongard-cli agents get-count - Returns a count of all the agents in your service provider.
  • liongard-cli agents update - Edits a deployed liongard agent, cannot update On-Demand agents.

authentication - Manage authentication

  • liongard-cli authentication log-in - Returns a session token as well as additional information about logged-in user
  • liongard-cli authentication verify-token - Verify token with MFA authentication code

detections - A Detection is a Change that was detected on a system.

  • liongard-cli detections detections - Returns a list of all detection events.
  • liongard-cli detections detectionsby-id - Gets a specific detection.
  • liongard-cli detections get-count1234 - Returns count of all detection events.

environments - An environment in Roar represents a single end customer for your MSP. An environment will contain Agents, Launchpoints (configured inspections), and Systems (data that has landed as a result of an inspection).

  • liongard-cli environments count - Returns a count of all environments in your Service Provider.
  • liongard-cli environments create - Creates a single Liongard Environment.
  • liongard-cli environments create-bulk - Create many environments at once.
  • liongard-cli environments delete - Delete an environment.
  • liongard-cli environments get - Fetch all environments in your Service Provider.
  • liongard-cli environments get-environmentid - Get a single environment.
  • liongard-cli environments update - Update a single environment, If you want to update a child environment, set the Parent Environment, if not set to null

groups - A Group represents a combined set of permissions that can be assigned to Users

  • liongard-cli groups - Returns a List of available Assignable Roles for a user

inspector - An Inspector represents the system type and used for building the config templates for launchpoints

inspectors - An Inspector represents the system type and used for building the config templates for launchpoints

  • liongard-cli inspectors - Lists all avaialble Inspectors in Liongard

launchpoints - A Launchpoint is a configured Inspection. As an example, if you set up a domain inspector to run on liongard.com, that would be considered a Launchpoint.

  • liongard-cli launchpoints bulk-delete - Remove all launchpoints.
  • liongard-cli launchpoints bulk-run - Kick off many inspections.
  • liongard-cli launchpoints delete - Remove a single launchpoint.
  • liongard-cli launchpoints get - Lists all launchpoints.
  • liongard-cli launchpoints get-count - Returns a count of all launchpoints.
  • liongard-cli launchpoints launchpoint - Create a launchpoint.
  • liongard-cli launchpoints launchpointsby-id - Return a specific launchpoint by ID.
  • liongard-cli launchpoints update - Edit a single inspector launchpoint.
  • liongard-cli launchpoints update-bulk - Update many launchpoints to run on the same schedule.

logs - Manage logs

  • liongard-cli logs - Return the logs for a specific inspection.

metrics - Manage metrics

  • liongard-cli metrics create - Creates a Single Metrics for a system requires valid JMESPath in the Query field
  • liongard-cli metrics delete - Deletes only Custom Created Metrics, Liongard Created Metrics can not be deleted
  • liongard-cli metrics evaluation - For each system ID passed
  • liongard-cli metrics evaluation-post - For each system ID passed
  • liongard-cli metrics metrics - Returns a list of metrics that have been created.
  • liongard-cli metrics update - Updates a Metric requires valid JMESPath in the Query field

systems - A System in Roar represents a system that has been inspected by a Launchpoint. When the inspection completes for the first time, a system is completed and a corresponding timeline entry is created each time the inspection lands.

  • liongard-cli systems get-count - Count of all systems in your service provider.
  • liongard-cli systems systems - List all systems.

tasks - Manage tasks

  • liongard-cli tasks get-alert - Returns a single alert that has been raised.
  • liongard-cli tasks get-count12345 - Returns a count of all alerts.
  • liongard-cli tasks list-alerts - Returns a list of alerts that have been raised.

timeline - A Timeline entry represents a single inspection event. It links a System to it's configuration at that point in time.

  • liongard-cli timeline get-count123 - Return count of all timeline entries.
  • liongard-cli timeline timeline - Fetch all timeline entries.
  • liongard-cli timeline timelineby-id - Fetch a specific timeline.

users - Create and manage users in your Liongard instance

This is the start of the file. Read the full SKILL.md on GitHub.

Security

  • Security scanPassed, 90 of 100Pattern checks on the skill's files.
  • Model reviewPassed

Quality evaluation

  • Task evaluationNot runNo evaluation yet. Run one in Skill Studio.

Source

Popularity

Repository stars
44
Repository forks
11
7-day trend score
19

Stars and forks are for the whole GitHub repository, not this skill alone. Not refreshed yet.

Works with

Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.

  • Claude Code
  • Cursor
  • GitHub Copilot
  • Windsurf
  • Codex
  • Gemini CLI
  • Cline
  • Amp
  • Roo Code
  • Goose
  • Continue
  • Kilo Code
  • Junie
  • Trae
  • OpenHands
  • Qwen Code
  • AI Agent
  • Tabnine Chat
  • Sourcegraph Cody
  • Amazon Q
  • Firebase Genkit
  • Sweep
  • Devin
  • Phind
  • Mentat
  • Claude Desktop
  • Aider
  • GPT Pilot
  • Plandex
  • bolt.new
  • v0
  • Replit Agent
  • Anse
  • TypingMind
  • BetterChatGPT
  • LibreChat
  • Warp AI
  • Pieces
  • Fig AI
Embed badge
vskill VERIFIED badge
[![vskill VERIFIED](https://verified-skill.com/api/v1/skills/servosity/msp-skills/liongard/badge)](https://verified-skill.com/skills/servosity/msp-skills/liongard)

Something wrong with this skill or its page? Tell us.