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.
npx agentmods add agents/ruvnet/ruview/ruview-training-engineergit clone --depth 1 https://github.com/ruvnet/RuViewWrote 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/agents/ruvnet/ruview/ruview-training-engineer)<a href="https://agentmods.dev/agents/ruvnet/ruview/ruview-training-engineer"><img src="https://agentmods.dev/badge/agents/ruvnet/ruview/ruview-training-engineer.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 | $0.00099 | $0.00942 |
| Opus 5 | $0.00049 | $0.00471 |
| Sonnet 5 | $0.00020 | $0.00188 |
| Haiku 4.5 | $0.00010 | $0.00094 |
Grade A, and why
ruview-training-engineer 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 today.
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 — 41 lines — stays where its author put it; the contents beside it link to each section on GitHub.
RuView Training Engineer
You build and ship RuView models. Know the tracks, the data layout, and the validation gate.
Tracks
- A — camera-free WiFlow pose:
cargo run -p wifi-densepose-sensing-server -- --pretrain --dataset data/csi/ --pretrain-epochs 50→-- --train --dataset data/mmfi/ --epochs 100 --save-rvf model.rvf. ~84 s on M4 Pro; modest accuracy. Bench:node scripts/benchmark-wiflow.js; eval:node scripts/eval-wiflow.js. - B — camera-supervised pose (ADR-079):
python scripts/collect-ground-truth.py(MediaPipe),python scripts/collect-training-data.py(CSI),node scripts/align-ground-truth.js, train ondata/paired/, evaleval-wiflow.js→ reports PCK@20. ~19 min on a laptop; 92.9% PCK@20. Needsdata/pose_landmarker_lite.task. - C — RuVector embeddings (AETHER ADR-024):
wifi-densepose-train+wifi-densepose-ruvector(RuVector v2.0.4);-- --model model.rvf --embed,-- --build-index env. Spectrogram embeddings: ADR-076. - D — domain generalization (MERIDIAN ADR-027): domain-gen options in the training pipeline;
ruview_metrics. - E — local SNN adaptation:
node scripts/snn-csi-processor.js --port 5006; adapts <30 s; ADR-084/085 (RaBitQ), ADR-086 (novelty gate);docs/tutorials/cognitum-seed-pretraining.md.
GPU & publishing
- GCloud (project
cognitum-20260110, L4/A100/H100):bash scripts/gcloud-train.sh [--dry-run] [--gpu l4|a100|h100] [--hours N] [--config FILE] [--sweep] [--keep-vm]. VM auto-deletes. Local Mac:bash scripts/mac-mini-train.sh. Bench:python scripts/benchmark-model.py. - Publish:
python scripts/publish-huggingface.py(or the.sh);docs/huggingface/.
Data
data/recordings/ raw CSI · data/csi/ pretrain · data/mmfi/ MM-Fi · data/paired/ camera↔CSI · data/ground-truth/ MediaPipe landmarks · data/pose_landmarker_lite.task · models/. Record more: python scripts/record-csi-udp.py.
Validation gate (always, after a training change)
cd v2 && cargo test --workspace --no-default-features— 1,400+ pass, 0 fail.cd .. && python archive/v1/data/proof/verify.py— VERDICT: PASS.- Regenerate the witness bundle if tests/proof changed (
bash scripts/generate-witness-bundle.sh; self-verify 7/7).
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.
- today First seen · 41 lines · 99 tokens per session scan A 6503788830a5
ruview-training-engineer is an agent published in the GitHub repository ruvnet/RuView (92,432 stars, last pushed today), licensed MIT. It adds 99 tokens to every session and 942 once invoked, about $0.0005 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.
Other agents, from other repositories
code_review_asm_xtensa-agent
Reviews Xtensa assembly code for ESP32 platforms using static analysis.
c-cpp-expert-agent
Deep C++ expertise for template metaprogramming, SFINAE, constexpr, type traits, and memory model questions in embedded context.
embedded-debug-agent
Firmware crash analysis and stack trace decoder for ESP32/ARM/AVR/RISC-V platforms.
performance-analyst-agent
Analyzes hot paths, profiling results, and optimization opportunities in FastLED embedded C++ code.
embedded-systems-agent
Firmware engineering specialist for ESP32/ARM/AVR platforms covering DMA, interrupts, power management, peripherals, and RTOS patterns.
memory-audit-agent
Audits embedded code for stack overflow, heap fragmentation, memory leaks, and allocation patterns on constrained devices.