rvcsi-nexmon

rvcsi-nexmon is a command for Claude Code from ruvnet/rvcsi. It costs 36 tokens per session (474 once invoked), scanned A, original, Apache-2.0.

A set of commands for examining Nexmon CSI data, where CSI is a record of how Wi-Fi signals change across frequencies. It can inspect packet captures, decode Broadcom channel settings, and list supported chips and Raspberry Pi models.

In plain words
What is it for?
Use it to inspect a Nexmon .pcap file, check channels and signal data, translate a Broadcom chanspec, or look up supported Nexmon hardware.
Why use it?
It removes the need to decode capture details and hardware-specific channel values by hand.

Command for Claude Code

Written for Claude Code: argument-hint in frontmatter.

Part of the rvcsi plugin — 5 commands, 1 agent shipped together

Good fit Use it to inspect a Nexmon .pcap file, check channels and signal data, translate a Broadcom chanspec, or look up supported Nexmon hardware.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/ruvnet/rvcsi/rvcsi-nexmon
View source ↗ ruvnet/rvcsi
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.

Clone the repo
git clone --depth 1 https://github.com/ruvnet/rvcsi

Made for: Claude Code.

Or install rvcsi, the plugin that ships this one along with the rest of its 5 commands, 1 agent.

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.

agentmods badge for rvcsi-nexmon

README.md
[![agentmods](https://agentmods.dev/badge/commands/ruvnet/rvcsi/rvcsi-nexmon/github.svg)](https://agentmods.dev/commands/ruvnet/rvcsi/rvcsi-nexmon)
Your own site
<a href="https://agentmods.dev/commands/ruvnet/rvcsi/rvcsi-nexmon"><img src="https://agentmods.dev/badge/commands/ruvnet/rvcsi/rvcsi-nexmon/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.

agentmods 80×15 button for rvcsi-nexmon

Your own site · 80×15
<a href="https://agentmods.dev/commands/ruvnet/rvcsi/rvcsi-nexmon"><img src="https://agentmods.dev/badge/commands/ruvnet/rvcsi/rvcsi-nexmon.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 36 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 474 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00036 $0.00474
Opus 5 $0.00018 $0.00237
Sonnet 5 $0.00007 $0.00095
Haiku 4.5 $0.00004 $0.00047

Measured 9d ago against content hash d523ef125ca3, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

rvcsi-nexmon 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 9d 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/rvcsi/commands/rvcsi-nexmon.md · 15 lines

What it actually says

/rvcsi-nexmon

Three Nexmon-side helpers, dispatched on $ARGUMENTS:

  • <file.pcap>rvcsi inspect-nexmon <file.pcap> (add a note for --json, --port <p>): link type, CSI frame count, channels, bandwidths, subcarrier counts, chip versions, RSSI range, time span. This parses the libpcap container in pure Rust and decodes each CSI UDP payload (18-byte magic 0x1111 · rssi · fctl · src_mac · seq · core/stream · chanspec · chip_ver header + nsub int16 I/Q samples) via the napi-c shim.
  • decode-chanspec <hex|dec>rvcsi decode-chanspec 0xe024 — Broadcom d11ac chanspec word → channel (chanspec & 0xff), bandwidth (bits [13:11], cross-checked against the FFT size), band (bits [15:14], cross-checked against the channel number).
  • chips (or empty) → rvcsi nexmon-chips — the chip / Raspberry-Pi-model registry: BCM43455c0 (Raspberry Pi 3B+ / 4 / 400 / 5, and the standalone Pi-less BCM43455c0), 4358, 4366c0, BCM43436b0 (Pi Zero 2 W) — with the AdapterProfile each one builds (channels, bandwidths, subcarrier counts, capabilities).

In a checkout, prefix with cargo run -p rvcsi-cli -- …. To produce a .pcap to inspect: on a Raspberry Pi with the nexmon_csi firmware patch active, tcpdump -i wlan0 dst port 5500 -w csi.pcap.

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.

  1. 9d ago First seen · 15 lines · 36 tokens per session scan A d523ef125ca3

Subscribe to this mod's changes

rvcsi-nexmon is a command published in the GitHub repository ruvnet/rvcsi (23 stars, last pushed 16d ago), licensed Apache-2.0. It adds 36 tokens to every session and 474 once invoked, about $0.0002 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 2026-08-30.