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.
npx skills add swkstudios/unifi-fabric-mcp-server --skill network-vlan-read-modify-writegit clone --depth 1 https://github.com/swkstudios/unifi-fabric-mcp-serverWrote 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.
[](https://agentmods.dev/skills/swkstudios/unifi-fabric-mcp-server/network-vlan-read-modify-write)<a href="https://agentmods.dev/skills/swkstudios/unifi-fabric-mcp-server/network-vlan-read-modify-write"><img src="https://agentmods.dev/badge/skills/swkstudios/unifi-fabric-mcp-server/network-vlan-read-modify-write/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.
<a href="https://agentmods.dev/skills/swkstudios/unifi-fabric-mcp-server/network-vlan-read-modify-write"><img src="https://agentmods.dev/badge/skills/swkstudios/unifi-fabric-mcp-server/network-vlan-read-modify-write.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00039 | $0.00527 |
| Opus 5.5 | $0.00016 | $0.00211 |
| Sonnet 5.5 | $0.00008 | $0.00105 |
| Haiku 4.5 | $0.00004 | $0.00053 |
Grade A, and why
network-vlan-read-modify-write 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.
What it actually says
Network and VLAN change
Change one network at a time and never invent fields the read did not return. In
discovery mode (the default) run each tool below through call_read_tool or
call_write_tool with name and arguments; in full mode call it directly. For
anything else, such as finding the network id, use search_tools and describe_tool.
- Call
get_networkwith{"host":"<console>","site":"<site>","network_id":"<network uuid>"}and keep the returned object as the baseline. - Copy the baseline and apply only the requested delta. The update is a full
replacement (PUT) and omitted fields reset, so keep every unrelated field. The server
itself drops the top-level
id,default,metadataandindexand the empty strings padding lists. - Show the operator the changed fields and the complete
network_config, and wait for approval.update_networkhas no per-call preview, so this is the preview. - Call
update_networkwithhost,site,network_idand the approvednetwork_config. Astatus: "dry_run"result means the server runs in dry-run mode and nothing changed. - Call
get_networkagain. Compare the requested fields and the untouched fields with the baseline, and report controller normalization separately.
Tool contracts checked against code (paths under src/unifi_fabric/)
| Tool | Mode | Required arguments (optional) | Return shape and source |
|---|---|---|---|
get_network |
read | host, site, network_id |
network object verbatim; server.py::get_network → tools/network.py::get_network; readOnlyHint: true |
update_network |
write | host, site, network_id, network_config |
upstream body verbatim, or {status, dryRun, message, preview}; server.py::update_network → tools/network.py::update_network; readOnlyHint: false |
Responses can include secrets such as passphrases; never copy them into a report.
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 · 36 lines · 39 tokens per session scan A c101915ce874
network-vlan-read-modify-write is a skill published in the GitHub repository swkstudios/unifi-fabric-mcp-server (6 stars, last pushed 4d ago), licensed MIT. It adds 39 tokens to every session and 527 once invoked, about $0.0002 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.
network-vlan-read-modify-write compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| network-vlan-read-modify-writeswkstudios/unifi-fabric-mcp-server | Skill | 6 | 4d ago | MIT | A | 39 | 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 |