NVIDIA-NeMo/Gym is a library and infrastructure for evaluating and improving models and agents inside environments, where each environment defines tasks, agent interaction, verification, and execution state. It is for teams running reproducible evaluations or training at scale across settings such as code execution, tool calling, and sandboxes, and the catalogue entries provide skills and instructions for working with it.
Borrowing it
Nothing to install: this file belongs to NVIDIA-NeMo/Gym. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/NVIDIA-NeMo/Gym/main/.agents/skills/nemo-gym-docs/SKILL.mdgit clone --depth 1 https://github.com/NVIDIA-NeMo/GymWrote 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/nvidia-nemo/gym/nemo-gym-docs)<a href="https://agentmods.dev/skills/nvidia-nemo/gym/nemo-gym-docs"><img src="https://agentmods.dev/badge/skills/nvidia-nemo/gym/nemo-gym-docs/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/nvidia-nemo/gym/nemo-gym-docs"><img src="https://agentmods.dev/badge/skills/nvidia-nemo/gym/nemo-gym-docs.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 4 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium MCP Rug Pull · line 25 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
- medium MCP Rug Pull · line 178 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
- medium MCP Rug Pull · line 181 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
- medium MCP Rug Pull · line 277 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
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 | $0.00080 | $0.03536 |
| Opus 5.5 | $0.00032 | $0.01414 |
| Sonnet 5.5 | $0.00016 | $0.00707 |
| Haiku 4.5 | $0.00008 | $0.00354 |
Grade A, and why
nemo-gym-docs 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 — 285 lines — stays where its author put it; the contents beside it link to each section on GitHub.
NeMo Gym Docs Maintenance
Unified skill for adding, updating, moving, and removing pages on the NeMo Gym Fern documentation site.
Scope Rule
ALL docs edits happen under fern/. All new pages — including release notes and migration guides — belong under fern/.
Bleeding-edge tree + GA snapshots. Gym keeps one bleeding-edge content tree at fern/versions/latest/ (the folder name is historical — it's mounted under the main slug via main.yml) and one frozen GA snapshot per shipped release (currently fern/versions/v0.2.1/). All new edits land in fern/versions/latest/. The latest.yml file is a GA alias — a symlink to the current GA's yml — so /latest/... and /<current-ga>/... serve the same pages. Back-ports into a frozen GA snapshot are deliberate and rare; default to editing fern/versions/latest/ only.
Layout at a Glance
fern/
├── fern.config.json # Org + Fern CLI version (currently 4.80.3)
├── package.json # `npm run dev|check|generate` — wraps `npx -y fern-api@latest`
├── docs.yml # Site config: instances, versions, tabs, redirects, libraries
├── versions/
│ ├── latest.yml # GA alias — symlink to the current GA's yml (currently v0.2.1.yml)
│ ├── main.yml # Nav tree for the bleeding-edge train (mounts ./latest/pages)
│ ├── latest/pages/ # MDX content for the bleeding-edge train (slug: main)
│ ├── v0.2.1.yml # Nav tree for the 0.2.1 GA snapshot
│ └── v0.2.1/pages/ # MDX content for the 0.2.1 GA snapshot
├── components/ # Custom TSX (CTAButtons, NavButton, CustomFooter)
├── assets/ # Images, SVGs, favicon
├── main.css # Global theme overrides (NVIDIA green, badge spacing, etc.)
└── product-docs/ # GENERATED library reference (gitignored)
File system Published URL
───────────────────────────────────────────────────── ──────────────────────────────────
fern/versions/latest/pages/get-started/quickstart.mdx docs.nvidia.com/nemo/gym/main/get-started/quickstart
fern/versions/v0.2.1/pages/get-started/quickstart.mdx docs.nvidia.com/nemo/gym/v0.2.1/get-started/quickstart
docs.nvidia.com/nemo/gym/latest/get-started/quickstart (GA alias)
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 Changed · +4 lines 68ea79e089e6
- 1mo ago Changed · -1 lines 67a647134ce8
- 2mo ago First seen · 282 lines · 80 tokens per session scan A 0d60075c316f
nemo-gym-docs is a skill published in the GitHub repository NVIDIA-NeMo/Gym (1,320 stars, last pushed today), licensed Apache-2.0. It adds 80 tokens to every session and 3,536 once invoked, about $0.0003 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 2026-08-30.
nemo-gym-docs compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| nemo-gym-docsNVIDIA-NeMo/Gym | Skill | 1.3k | today | Apache-2.0 | A | 80 | Claude Code, Codex |
| model_finetuningvuralserhat86/antigravity-agentic-skills | Skill | 43 | 10mo ago | none | A | 67 | Claude Code, Codex |
| model_finetuningDonggangChen/antigravity-agentic-skills | Skill | 2 | 10mo ago | none | A | 67 | Claude Code, Codex |
| foundry-config-setupmicrosoft/agent-framework | Skill | 15k | yesterday | MIT | A | 65 | Claude Code, Codex |
| rowboat-spacesrowboatlabs/rowboat | Skill | 18k | yesterday | Apache-2.0 | A | 60 | Claude Code, Codex |
| create-tech-designhumanlayer/humanlayer | Skill | 13k | yesterday | Apache-2.0 | A | 16 | Claude Code, Codex |
| deploy-docker-composeomnigent-ai/omnigent | Skill | 11k | today | Apache-2.0 | A | 84 | Claude Code, Codex |