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.
git clone --depth 1 https://github.com/WYRE-AI/msp-claude-pluginsWrote 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/commands/wyre-ai/msp-claude-plugins/capacity-check)<a href="https://agentmods.dev/commands/wyre-ai/msp-claude-plugins/capacity-check"><img src="https://agentmods.dev/badge/commands/wyre-ai/msp-claude-plugins/capacity-check.svg" alt="Measured on agentmods" 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 | $0.00012 | $0.00694 |
| Opus 5 | $0.00006 | $0.00347 |
| Sonnet 5 | $0.00002 | $0.00139 |
| Haiku 4.5 | $0.00001 | $0.00069 |
Grade A, and why
capacity-check 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 4d 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.
How it starts
The opening of the file, as written. The whole thing — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Auvik Capacity Check
Pull interface statistics for a tenant and flag any link running hot. The output supports both incident response ("why is the network slow right now?") and capacity planning ("which links will we need to upgrade in the next quarter?").
Prerequisites
- Tools:
auvik_interfaces_list,auvik_statistics_interface,auvik_devices_get,auvik_statistics_device
Steps
-
Enumerate interfaces
Call
auvik_interfaces_listfor the tenant. Filter to interfaces that are admin-up and oper-up - down links produce no utilization signal. Prioritize uplinks, WAN interfaces, and trunks; deprioritize user-facing access ports unless the user specifically asked. -
Pull statistics
For each candidate interface call
auvik_statistics_interfaceoverwindow. Pull at minimumbandwidthInRateandbandwidthOutRate(or the equivalent fields the response exposes), plus error/discard counters if available. -
Compute utilization
For each sample, utilization = max(in, out) / linkSpeed. Track:
- Peak utilization in the window
- Sustained utilization at the 95th percentile (the standard MSP framing)
- Count of intervals above 70%
-
Classify each interface
- Saturated - p95 > 70%, or peak > 90% with > 5% of intervals above 70%. Flag for upgrade.
- Warm - p95 between 40% and 70%. Monitor; consider for upgrade if growth trend is upward.
- Cool - p95 < 40%. Healthy.
-
Surface error and discard hotspots separately
An interface that is not saturated but is dropping packets or seeing CRC errors is a different problem (cable, optic, duplex mismatch) - flag it in its own section.
-
Cross-reference device health
For each device owning a saturated interface, call
auvik_statistics_deviceto check CPU and memory in the same window. A saturated link on a CPU-bound device is a different conversation than a saturated link on a healthy device. -
Output
Sections:
- Saturated interfaces - table with device, interface, link speed, p95, peak, % time above 70%
- Warm interfaces - same table, watchlist
- Error/discard hotspots - device, interface, error count, error rate
- Devices with elevated CPU/memory that own saturated interfaces
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.
- 4d ago First seen · 75 lines · 12 tokens per session scan A 76b76c55328f
capacity-check is a command published in the GitHub repository WYRE-AI/msp-claude-plugins (45 stars, last pushed 5d ago), licensed Apache-2.0. It adds 12 tokens to every session and 694 once invoked, about $0.0001 per session on Opus 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 2026-09-04.
Other commands, from other repositories
device-info
A device-scanning command that identifies the connected chip and its VID:PID hardware identifiers. It also provides suggestions for the driver needed to use the device.
stm32-setup
Set up STM32 MCP documentation server - installs dependencies and configures your project.
get-organization-inventory-devices
Call the get-organization-inventory-devices tool from meraki-dashboard-api.
arduino-build
Compile an Arduino sketch for a target board.
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.