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-calibrate)<a href="https://agentmods.dev/commands/ruvnet/rvcsi/rvcsi-calibrate"><img src="https://agentmods.dev/badge/commands/ruvnet/rvcsi/rvcsi-calibrate/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/commands/ruvnet/rvcsi/rvcsi-calibrate"><img src="https://agentmods.dev/badge/commands/ruvnet/rvcsi/rvcsi-calibrate.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 | $0.00020 | $0.00318 |
| Opus 5 | $0.00010 | $0.00159 |
| Sonnet 5 | $0.00004 | $0.00064 |
| Haiku 4.5 | $0.00002 | $0.00032 |
Grade A, and why
rvcsi-calibrate 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.
What it actually says
/rvcsi-calibrate
Learn a baseline from a (preferably quiet / empty-room) capture.
- Run
rvcsi calibrate --in <file.rvcsi> [--out baseline.json](no--out→ prints to stdout) — orcargo run -p rvcsi-cli -- calibrate …in a checkout. - It scans frames at the dominant subcarrier count and emits the element-wise mean amplitude as the baseline, with a
versionlike<source>@auto-<n>(n = frames used), the subcarrier count, and the frame count. Versioned calibration (ADR-095 D14) means event outputs can reference exactly which baseline they ran against. - Use it: feed the
baseline_amplitudearray into aSignalPipeline(with_baseline_amplitude(Some(vec))) so DC is removed per subcarrier, not just the scalar mean — this is what makes/rvcsi-eventsbehave well on real CSI (otherwise a hot DC/pilot subcarrier dominates the window vector and the drift detector over-triggers). - Capture hygiene: record the baseline from a known-quiet period (empty room, stable environment). Re-calibrate when
/rvcsi-eventsemitsCalibrationRequiredor frequentBaselineChanged.
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.
- 9d ago First seen · 14 lines · 20 tokens per session scan A 738ef261de39
rvcsi-calibrate is a command published in the GitHub repository ruvnet/rvcsi (23 stars, last pushed 16d ago), licensed Apache-2.0. It adds 20 tokens to every session and 318 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 2026-08-30.
Other commands, from other repositories
ruview-advanced
Use advanced RuView capabilities — multistatic sensing, cross-viewpoint fusion, RF tomography, persistent field model, intention signals, adversarial detection, mesh security.
ruview-app
Run a RuView sensing application — presence, vitals, pose, sleep, environment mapping, MAT, point cloud, or a novel RF app.
ruview-flash
Build and flash RuView ESP32 firmware (8MB or 4MB), then confirm the CSI stream.
ruview-start
Get started with RuView — pick the fastest path (Docker demo, repo build, or live ESP32) and walk through it.
stream
Get the Zenoh topic and connection params for a node's data stream.
node-new
Scaffold a new bubbaloop node via the bubbaloop-node-author subagent — guided through manifest, command queryable, validation, and registration.