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 skills/ruvnet/ruview/train-posenpx skills add ruvnet/RuView --skill train-posegit clone --depth 1 https://github.com/ruvnet/RuViewWhat 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 | $0.00044 | $0.00397 |
| Opus 5 | $0.00022 | $0.00198 |
| Sonnet 5 | $0.00009 | $0.00079 |
| Haiku 4.5 | $0.00004 | $0.00040 |
Grade A, and why
train-pose 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.
What it actually says
train-pose
Build a CSI→pose model without overstating it. The project has a retracted 92.9%/100% history — the discipline below exists so it never recurs.
The non-negotiable: mean-pose baseline first
A pose model that always predicts the dataset's mean pose already scores ~50% PCK. Quote PCK only as a delta over that baseline, on a held-out split with no subject or temporal leakage. Example honest result (ADR-181):
Held-out PCK@20 59.5% vs a 50% mean-pose baseline = +9.4 pp real signal — MEASURED.
Paths
- camera-supervised (ADR-079) — MediaPipe Pose labels the camera frame; paired CSI trains the net. Train/infer in one camera frame so the skeleton aligns.
- camera-free (WiFlow, ADR-152) — no camera at inference; geometry-conditioned.
- in-browser (ADR-181) — WebGPU/WASM trainer; the active backend is shown as a badge (honest about what's executing).
Before you publish a number
- Run the mean-pose baseline on the same split.
- Report
(model − baseline)in pp, with the split definition (chronological / blocked-gap / grouped-bucket; no leakage). ruview_claim_checkthe writeup — it flags any untagged or 100%/perfect claim.- If it's a benchmark vs SOTA, tag MEASURED-EQUIVALENT only with the reproducer.
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 · 34 lines · 44 tokens per session scan A 92aebd442347
train-pose is a skill published in the GitHub repository ruvnet/RuView (92,406 stars, last pushed today), licensed MIT. It adds 44 tokens to every session and 397 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 2026-09-03.
Other skills, from other repositories
alphafold
Validate protein designs using AlphaFold2 structure prediction. Use this skill when: (1) Validating designed sequences fold correctly, (2) Predicting binder-target complex structures, (3) Calculating confidence metrics (pLDDT, pTM, ipTM), (4) Self-consistency validation of designs, (5) Multi-chain complex prediction…
esm
ESM2 protein language model for embeddings and sequence scoring. Use this skill when: (1) Computing pseudo-log-likelihood (PLL) scores, (2) Getting protein embeddings for clustering, (3) Filtering designs by sequence plausibility, (4) Zero-shot variant effect prediction, (5) Analyzing sequence-function relationships.…
model-training
Train machine learning models end-to-end, covering data loading, preprocessing, architecture selection, training loops, validation, and checkpointing.
remote-sensing-data-scientist
Expert-level Remote Sensing Data Scientist specializing in satellite imagery analysis, SAR processing, multispectral classification, change detection, and geospatial deep learning. Use when: working with remote-sensing-data-scientist.
deepspot-m
Generate transcriptome-wide virtual spatial transcriptomics from H&E histology with DeepSpot-M. Use when you need spatial gene expression in log1p-CPM for 224x224 tiles at about 20x, want to query protein-coding genes by symbol instead of a fixed panel, or want to run prediction across a whole slide after tiling with…
digital-health-clinical-asr-finetune
Stage 4 of the Clinical ASR Flywheel. Use when priority KER is above 0.3 to run stock NeMo SFT on Parakeet TDT v2 and offline cycle N+1 re-eval. NOT for generic word boosting (use /finetune-asr).