ruview-verify

ruview-verify is a skill for Claude Code from ruvnet/RuView. It costs 69 tokens per session (1,095 once invoked), scanned A, original, MIT.

A verification workflow for RuView software, firmware, and data-processing changes. It runs tests and creates a witness bundle, which is a package of evidence that others can independently check.

In plain words
What is it for?
Use it to run Rust and Python tests, verify a fixed signal-processing result, check firmware hashes, and produce a self-verifying evidence bundle.
Why use it?
It helps detect accidental changes in processing behaviour and confirm that the project still passes its checks before a merge or handoff.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: mentions CLAUDE.md.

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is python archive/v1/data/proof/verify.py # must print VERDICT: PASS.

Part of the ruview plugin — 10 skills, 7 commands, 3 agents shipped together

Good fit Use it to run Rust and Python tests, verify a fixed signal-processing…

Compare 6 skills from other repositories ↓
About the project

RuView is a WiFi sensing platform that uses disturbances in radio signals, captured by low-cost ESP32 sensors, to detect presence, movement, breathing, and heart rate without cameras or wearables. It is intended for spatial monitoring and smart-home integrations. The catalogue add-ons support workflows for operating and integrating RuView.

ruvnet/RuView · 92,565 stars · on GitHub · cognitum.one

Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/ruvnet/RuView
agentmods
npx agentmods add skills/ruvnet/ruview/ruview-verify

Made for: Claude Code.

Or install ruview, the plugin that ships this one along with the rest of its 10 skills, 7 commands, 3 agents.

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 ruview-verify

README.md
[![agentmods](https://agentmods.dev/badge/skills/ruvnet/ruview/ruview-verify.svg)](https://agentmods.dev/skills/ruvnet/ruview/ruview-verify)
Your own site
<a href="https://agentmods.dev/skills/ruvnet/ruview/ruview-verify"><img src="https://agentmods.dev/badge/skills/ruvnet/ruview/ruview-verify.svg" alt="Measured on agentmods" height="20"></a>
Per session 69 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,095 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 $0.00069 $0.01095
Opus 5 $0.00034 $0.00548
Sonnet 5 $0.00014 $0.00219
Haiku 4.5 $0.00007 $0.00110

Measured 3d ago against content hash 6010d4d337ae, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

ruview-verify 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 3d 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/ruview/skills/ruview-verify/SKILL.md · 98 lines

How it starts

The opening of the file, as written. The whole thing — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.

RuView Verification & Witness Bundle

The trust pipeline for RuView. Run this after meaningful changes and before merging.

1. Rust workspace tests

cd v2
cargo test --workspace --no-default-features        # must be 1,400+ passed, 0 failed (~2 min)

Single-crate checks (no GPU): cargo check -p wifi-densepose-train --no-default-features, cargo test -p wifi-densepose-signal --no-default-features, etc.

2. Deterministic Python proof (Trust Kill Switch)

Feeds a reference CSI signal through the production pipeline and hashes the output. Any behavioural drift changes the hash.

cd ..
python archive/v1/data/proof/verify.py              # must print VERDICT: PASS

If it fails on a hash mismatch after a legitimate numpy/scipy bump:

python archive/v1/data/proof/verify.py --generate-hash
python archive/v1/data/proof/verify.py

Artifacts: archive/v1/data/proof/verify.py, expected_features.sha256, sample_csi_data.json (1,000 synthetic frames, seed=42).

3. Python test suite (v1)

cd archive/v1 && python -m pytest tests/ -x -q

4. Generate the witness bundle (ADR-028)

bash scripts/generate-witness-bundle.sh

Produces dist/witness-bundle-ADR028-<sha>.tar.gz containing:

  • WITNESS-LOG-028.md — 33-row attestation matrix, evidence per capability
  • ADR-028-esp32-capability-audit.md — full audit findings
  • proof/verify.py + expected_features.sha256 — the deterministic proof
  • test-results/rust-workspace-tests.log — full cargo test output
  • firmware-manifest/source-hashes.txt — SHA-256 of all 7 ESP32 firmware files
  • crate-manifest/versions.txt — all 15 crates + versions
  • VERIFY.sh — one-command self-verification for recipients

5. Self-verify the bundle

cd dist/witness-bundle-ADR028-*/
bash VERIFY.sh                                       # must be 7/7 PASS

Pre-merge checklist (from CLAUDE.md)

  1. Rust tests pass (1,400+, 0 fail)
  2. Python proof passes (VERDICT: PASS)
  3. README.md updated if scope changed (platform/crate/hardware tables, feature summaries)
  4. CLAUDE.md updated if scope changed (crate table, ADR list, module tables, version)
  5. CHANGELOG.md — entry under [Unreleased]
  6. docs/user-guide.md updated if new data sources / CLI flags / setup steps
  7. ADR index — bump ADR count in README docs table if a new ADR was added
  8. Witness bundle regenerated if tests or proof hash changed
  9. Docker Hub image rebuilt only if Dockerfile / deps / runtime behaviour changed
  10. Crate publishing only if a published crate's public API changed (publish in dependency order — see CLAUDE.md)
  11. .gitignore updated for new build artifacts/binaries
  12. Security review for new modules touching hardware/network boundaries

Read the full file on GitHub · 98 lines

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. 3d ago First seen · 98 lines · 69 tokens per session scan A 6010d4d337ae

Subscribe to this mod's changes

ruview-verify is a skill published in the GitHub repository ruvnet/RuView (92,565 stars, last pushed yesterday), licensed MIT. It adds 69 tokens to every session and 1,095 once invoked, about $0.0003 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 2026-09-03.

Related

Other skills, from other repositories

langsmith-observability

LLM observability platform for tracing, evaluation, and monitoring. Use when debugging LLM applications, evaluating model outputs against datasets, monitoring production systems, or building systematic testing pipelines for AI applications.

davila7/claude-code-templates · 45 tokens

langsmith-observability

LLM observability platform for tracing, evaluation, and monitoring. Use when debugging LLM applications, evaluating model outputs against datasets, monitoring production systems, or building systematic testing pipelines for AI applications.

synthetic-sciences/openscience · 45 tokens

meraki-wireless-ops

Cisco Meraki wireless (read-only) — SSID configuration, RF profiles, Air Marshal, channel utilization, signal quality, client connectivity events via Cisco's official Meraki MCP. Use when inspecting Meraki SSIDs, auditing RF configuration, or investigating WiFi connectivity.

automateyournetwork/netclaw · 60 tokens

branch_health

Quick health check -- test counts and file stats for AIPass branches.

AIOSAI/AIPass · 17 tokens

monitor-test-run

Watch a running Kobiton test run and narrate it to the user: read the org's live-remediation flag up front, poll the run until every execution is terminal, surface the live-remediation URL the moment an execution is blocked, and give a correct post-mortem so a COMPLETED-with-BLOCKERENCOUNTERED execution is never…

kobiton/automate · 215 tokens

create-test-run

Create a Kobiton test run from a test case or suite, then offer to monitor it. When the user gives only partial details (or just a test case id), fill the rest with sensible defaults that match the createTestRun schema, show a summary of what will run, and ask to proceed or customize before creating. After the run is…

kobiton/automate · 207 tokens