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/ruvnet/rvcsiWrote 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/ruvnet/rvcsi/rvcsi-record)<a href="https://agentmods.dev/commands/ruvnet/rvcsi/rvcsi-record"><img src="https://agentmods.dev/badge/commands/ruvnet/rvcsi/rvcsi-record.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 | $0.00030 | $0.00498 |
| Opus 5 | $0.00015 | $0.00249 |
| Sonnet 5 | $0.00006 | $0.00100 |
| Haiku 4.5 | $0.00003 | $0.00050 |
Grade A, and why
rvcsi-record 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 7d 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
/rvcsi-record
Turn raw Nexmon CSI into a validated, replayable .rvcsi capture.
- Parse
$ARGUMENTS. Two source modes:--source nexmon(default):--inis a.binof "rvCSI Nexmon records" (the napi-c shim's compact self-describing format).--source nexmon-pcap:--inis a real libpcap capture, typicallytcpdump -i wlan0 dst port 5500 -w csi.pcapon a Raspberry Pi.--portoverrides the CSI UDP port (default 5500);--chip pi5(or another known chip) selects theAdapterProfile.
- Run:
rvcsi record --source <mode> --in <file> --out <file.rvcsi> [--chip …] [--port …](orcargo run -p rvcsi-cli -- record …in a checkout). - Each frame is run through
rvcsi_core::validate_frame; rejected frames are quarantined (dropped from the capture) — the command reports how many. The output.rvcsiis JSONL: line 1 is aCaptureHeader, every later line aCsiFrame. - Next:
/rvcsi-inspect <file.rvcsi>,/rvcsi-events <file.rvcsi>,/rvcsi-calibrate --in <file.rvcsi>.
If there is no .pcap yet, tell the user how to capture one: on the Pi (with the nexmon_csi firmware patch active), tcpdump -i wlan0 dst port 5500 -w csi.pcap. There is no ESP32 source crate yet — for an ESP32 .csi.jsonl recording, use scripts/esp32_jsonl_to_rvcsi.py to produce a .rvcsi, then continue with the same toolchain.
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.
- 7d ago First seen · 18 lines · 30 tokens per session scan A f8d89dd1ab93
rvcsi-record is a command published in the GitHub repository ruvnet/rvcsi (21 stars, last pushed 14d ago), licensed Apache-2.0. It adds 30 tokens to every session and 498 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.
Other commands, from other repositories
ruview-train
Train a RuView model — camera-free WiFlow pose, camera-supervised pose (92.9% PCK@20), RuVector embeddings, domain generalization, local SNN, with optional GPU on GCloud.
ruview-app
Run a RuView sensing application — presence, vitals, pose, sleep, environment mapping, MAT, point cloud, or a novel RF app.
verify-math
Verify a self-authored mathematical result end to end by routing claims across adversarial review, numerical falsification, symbolic or CAS checks, and Lean, then aggregating one report. Use when a theorem, proposition, conjecture, or paper-wide mathematical argument needs the appropriate combination of verification…
replication-package
Scaffold or audit a social-science replication package at a target directory, and audit the manuscript and its archived research objects against FAIR principles.
debug
Start GDB debug session with OpenOCD or probe-rs.
simulation-calibrator
Test and refine simulation accuracy with validation loops, bias detection, and continuous improvement frameworks.