What is site-health-report?

A read-only workflow for writing a UniFi site health report from health checks, device and client inventory, internet-provider metrics, and fleet summaries. It separates reported facts from interpretation and records the time range used for metrics.

Use it to report overall site health, connected equipment, clients, internet metrics, fleet context, risks, and recommended checks.

A missing measurement does not necessarily mean an outage, and health data can cover different scopes or times. The workflow helps keep those limits visible in the report.

site-health-report — Skill for Claude Code by swkstudios

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent

npx skills add swkstudios/unifi-fabric-mcp-server --skill site-health-report

Clone the repo

git clone --depth 1 https://github.com/swkstudios/unifi-fabric-mcp-server

Made for: Claude Code.

Or install unifi-fabric, the plugin that ships this one along with the rest of its 6 skills.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/skills/swkstudios/unifi-fabric-mcp-server/site-health-report/github.svg)](https://agentmods.dev/skills/swkstudios/unifi-fabric-mcp-server/site-health-report)

Your own site

<a href="https://agentmods.dev/skills/swkstudios/unifi-fabric-mcp-server/site-health-report"><img src="https://agentmods.dev/badge/skills/swkstudios/unifi-fabric-mcp-server/site-health-report/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/skills/swkstudios/unifi-fabric-mcp-server/site-health-report"><img src="https://agentmods.dev/badge/skills/swkstudios/unifi-fabric-mcp-server/site-health-report.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 26 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 666 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5.1	$0.00026	$0.00666
Opus 5.5	$0.00010	$0.00266
Sonnet 5.5	$0.00005	$0.00133
Haiku 4.5	$0.00003	$0.00067

Measured 2d ago against content hash 17e94c3ce8f4, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

site-health-report scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

plugins/claude/skills/site-health-report/SKILL.md · 34 lines

How it starts

The opening of the file, as written. The whole thing — 34 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Site health report

This workflow is read-only. Keep each query's scope and time; a missing metric is not proof of an outage. In discovery mode (the default) run each tool below through call_read_tool with name and arguments; in full mode call it directly. For anything else use search_tools and describe_tool.

Call get_site_health_summary with {"site":"<site name or siteId>"}; read _healthSummary (allOk, notOk) and the per-subsystem data records.
Call get_site_inventory with site; optional device_filter and client_filter narrow the lists. Use _devices, _clients and their counts.
Call query_isp_metrics with interval ("5m" or "1h") and either host with site or sites, not both; start_time and end_time are ISO 8601 strings. Record the window and any partial result in data.status or data.message.
Call get_fleet_summary with no arguments, or key_label for one configured key.
Use this outline: Scope and timestamp; Overall health; Inventory and device state; ISP metrics and time window; Fleet context; Risks and anomalies; Recommended next checks. Separate source facts from interpretation, and report any incomplete or errors field.

Tool contracts checked against code (paths under `src/unifi_fabric/`)

Tool	Mode	Required arguments (optional)	Return shape and source
`get_site_health_summary`	read	`site`	`{meta, data}` verbatim plus `_healthSummary`; `server.py::get_site_health_summary` → `tools/site_manager.py::get_site_health_summary`; `readOnlyHint: true`
`get_site_inventory`	read	`site` (`device_filter`, `client_filter`)	`{_siteId, _devices, _deviceCount, _clients, _clientCount}`; `server.py::get_site_inventory` → `tools/site_manager.py::get_site_inventory`; `readOnlyHint: true`
`query_isp_metrics`	read	`interval` (`host`, `site`, `sites`, `start_time`, `end_time`)	`{data: {metrics}, httpStatusCode, traceId}` verbatim; `server.py::query_isp_metrics` → `tools/site_manager.py::query_isp_metrics`; `readOnlyHint: true`
`get_fleet_summary`	read	none (`key_label`)	`{hosts, sites, devices: {total, byStatus, byType}, _key_label}`; `tools/aggregation.py::get_fleet_summary`; `readOnlyHint: true`

Read the full file on GitHub · 34 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

2d ago First seen · 34 lines · 26 tokens per session scan A 17e94c3ce8f4

Subscribe to this mod's changes

site-health-report is a skill published in the GitHub repository swkstudios/unifi-fabric-mcp-server (6 stars, last pushed 4d ago), licensed MIT. It adds 26 tokens to every session and 666 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-11-04.

Analytics and metrics Hardware and IoT fastmcp mcp network-automation ubiquiti unifi

site-health-report next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
site-health-reportswkstudios/unifi-fabric-mcp-server	Skill	6	4d ago	MIT	A	26	Claude Code
unifi-protectsirkirby/unifi-mcp	Skill	1.0k	yesterday	MIT	A	112	Claude Code
unifi-accesssirkirby/unifi-mcp	Skill	1.0k	yesterday	MIT	A	70	Claude Code
network-health-checksirkirby/unifi-mcp	Skill	1.0k	yesterday	MIT	A	49	Claude Code
percepxion-oobautomateyournetwork/netclaw	Skill	715	yesterday	Apache-2.0	A	70	Claude Code
unifi-networksirkirby/unifi-mcp	Skill	1.0k	yesterday	MIT	A	83	Claude Code
unifi-access-supportsirkirby/unifi-mcp	Skill	1.0k	yesterday	MIT	A	31	Claude Code