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 skills add nebius/nebius-physical-ai --skill physical-prompt-comparisongit clone --depth 1 https://github.com/nebius/nebius-physical-aiWrote 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/skills/nebius/nebius-physical-ai/physical-prompt-comparison)<a href="https://agentmods.dev/skills/nebius/nebius-physical-ai/physical-prompt-comparison"><img src="https://agentmods.dev/badge/skills/nebius/nebius-physical-ai/physical-prompt-comparison/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/skills/nebius/nebius-physical-ai/physical-prompt-comparison"><img src="https://agentmods.dev/badge/skills/nebius/nebius-physical-ai/physical-prompt-comparison.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 | $0.00035 | $0.00345 |
| Opus 5.5 | $0.00014 | $0.00138 |
| Sonnet 5.5 | $0.00007 | $0.00069 |
| Haiku 4.5 | $0.00003 | $0.00034 |
Grade A, and why
physical-prompt-comparison 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 11d 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
Physical prompt comparison
Use the guide and
physical-prompt-comparison.yaml for this
inference experiment. It compares baseline prompts, physical descriptions, and
negative guidance at matched seeds. Treat its sampled-frame scores as exploratory
measurements, not a physics benchmark, training method, or robot-policy result.
Run through npa workbench workflow submit on the supported Linux isolated
SkyPilot path. Select the operator's project/context and storage explicitly.
Follow health-preflight and submit-workflow; verify the exact pinned Wan
weight payload and hosted text/vision model access before GPU execution.
Keep the six scenarios, sealed assertions, paired seeds, and three conditioning arms intact for the shipped comparison. Full generation means 81 frames, 1280×720, 50 steps, and the pinned native Wan 2.1 14B model. Reduced settings would be a different experiment and cannot qualify this workflow. Generation uses one resident model per GPU shard, with original media and native receipts.
Inspect the final report and complete videos. Require exact paired coverage, verified storage readback, and model request/response identity. A valid video is not proof of correct physics. Unknown sampled-frame assertions do not pass; retain negative results and distinguish VLM judgments from human assessment. Preserve failed-stage evidence and standard durable run state when debugging.
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.
- 11d ago First seen · 30 lines · 35 tokens per session scan A e3bcc2acd03c
physical-prompt-comparison is a skill published in the GitHub repository nebius/nebius-physical-ai (50 stars, last pushed today), licensed Apache-2.0. It adds 35 tokens to every session and 345 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-10-11.
Other skills, from other repositories
instrument-data-to-allotrope
Convert laboratory instrument output files (PDF, CSV, Excel, TXT) to Allotrope Simple Model (ASM) JSON format or flattened 2D CSV. Use this skill when scientists need to standardize instrument data for LIMS systems, data lakes, or downstream analysis. Supports auto-detection of instrument types. Outputs include full…
exploratory-data-analysis
Performs bounded, local exploratory analysis of explicitly supported scientific files. Supports redacted CSV/TSV/JSON profiles; optional NumPy, HDF5, FASTA/FASTQ, and basic image metadata inspection; missingness/leakage audits; outlier and transformation sensitivity; and rigorous EDA report scaffolds. Other domain…
matlab
Builds, reviews, migrates, and plans MATLAB or GNU Octave numerical workflows. Use for arrays, tabular/time data, tests, projects, graphics, MAT files, and explicit Python interoperability.
phylogenetics
Builds and analyzes phylogenetic trees using MAFFT multiple sequence alignment, IQ-TREE maximum likelihood with ModelFinder and branch support, and FastTree approximate inference. Uses ETE3 for tree summaries and visualization. Applies to homologous nucleotide or protein sequences, microbial gene trees, protein…
research-engineer
An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal implementation across any required technology.
presenting-conference-talks
Generates conference presentation slides (Beamer LaTeX PDF and editable PPTX) from a compiled paper with speaker notes and talk script. Use when preparing oral talks, spotlight presentations, or invited talks for ML and systems conferences.