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 isaac-labgit 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/isaac-lab)<a href="https://agentmods.dev/skills/nebius/nebius-physical-ai/isaac-lab"><img src="https://agentmods.dev/badge/skills/nebius/nebius-physical-ai/isaac-lab/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/isaac-lab"><img src="https://agentmods.dev/badge/skills/nebius/nebius-physical-ai/isaac-lab.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00027 | $0.02684 |
| Opus 5 | $0.00014 | $0.01342 |
| Sonnet 5 | $0.00005 | $0.00537 |
| Haiku 4.5 | $0.00003 | $0.00268 |
Grade A, and why
isaac-lab 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 2d 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.
How it starts
The opening of the file, as written. The whole thing — 215 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Isaac Lab
Isaac Lab is the RL simulation framework. The canonical workbench pins the
latest published 3.Y beta point, v3.0.0-beta2.patch1 / wheel
3.0.0b2.post1, with Isaac Sim 6.0.1.0. Upstream has not labeled this a GA
release; keep the beta limitation explicit. Use L40S or RTX Pro 6000 for the
validated graphics/PhysX path. Rendering, camera-bearing tasks, and deployed
workbenches require RT cores and cannot target B200, H100, or H200.
The standalone training routing guard allows state-based, camera-free tasks to select datacenter GPUs. This is routing eligibility, not proof that the selected Isaac image, PhysX runtime, and driver work there. Require real training and a checkpoint from that exact runtime before claiming support; historical Isaac Lab 2.x results do not validate the generation 3 beta image.
Generation 3 training must invoke --visualizer none. A compatibility path
that can also receive a generation 2 image must select --headless only when
the image's ISAAC_LAB_VERSION starts with 2..
Before provisioning, building, downloading, or submitting an Isaac workload,
load skills/atomic/third-party-eula-preflight/SKILL.md. NPA defaults the
run-scoped ACCEPT_EULA=Y value for non-interactive use and preserves a
recognized negative value or --no-accept-eula opt-out. Legacy affirmative
spellings normalize case-insensitively; unrecognized values are errors.
Runtime Isaac bootstrap (the container ships no Isaac Sim)
The npa-isaac-lab image contains no NVIDIA Isaac Sim, Isaac Lab, Omniverse
Client, or other proprietary NVIDIA runtime code. It used to bake Omniverse
Kit, which made it non-redistributable; the exact runtime wheel set is now
downloaded on first use of /isaac-sim/python.sh from
https://pypi.nvidia.com, hash-verified, and installed into a cache volume
under the operator's own EULA acceptance. Full rationale:
docs/workbench/container-packaging.md and skills/atomic/solution-licensing/SKILL.md.
What this changes in practice:
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.
- 2d ago Changed · +7 lines 67d1f733cf9b
- 10d ago First seen · 208 lines · 27 tokens per session scan A c8d37c1cddbe
isaac-lab is a skill published in the GitHub repository nebius/nebius-physical-ai (27 stars, last pushed today), licensed Apache-2.0. It adds 27 tokens to every session and 2,684 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 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…
matlab
Build, review, migrate, and safely plan MATLAB or GNU Octave numerical workflows, including arrays, tabular/time data, tests, projects, graphics, MAT files, and explicit Python interoperability.
exploratory-data-analysis
Perform bounded, local exploratory analysis of explicitly supported scientific files. Use for 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…
phylogenetics
Build and analyze phylogenetic trees using MAFFT (multiple alignment), IQ-TREE 2 (maximum likelihood), and FastTree (fast NJ/ML). Visualize with ETE3 or FigTree. For evolutionary analysis, microbial genomics, viral phylodynamics, protein family analysis, and molecular clock studies.
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.
mapping-to-snomed
Maps clinical concept spans extracted by OpenMed to SNOMED CT concepts through a USER-SUPPLIED terminology server (the user's own Ontoserver, Snowstorm, or UMLS/UTS), never a bundled vocabulary. Use when the user wants to code findings, disorders, procedures, body structures, or substances to SNOMED CT, run an ECL…