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-release-notes/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-release-notes)<a href="https://agentmods.dev/skills/nvidia-nemo/gym/nemo-gym-release-notes"><img src="https://agentmods.dev/badge/skills/nvidia-nemo/gym/nemo-gym-release-notes/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-release-notes"><img src="https://agentmods.dev/badge/skills/nvidia-nemo/gym/nemo-gym-release-notes.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 | $0.00050 | $0.01077 |
| Opus 5.5 | $0.00020 | $0.00431 |
| Sonnet 5.5 | $0.00010 | $0.00215 |
| Haiku 4.5 | $0.00005 | $0.00108 |
Grade A, and why
nemo-gym-release-notes 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 1mo 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 — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.
NeMo Gym Release Notes
Write concise release notes that explain what users can now accomplish and why it matters.
Build an evidence base
- Identify the previous release tag and exact release branch or commit.
- Treat that bounded range as authoritative. Exclude changes outside it, regardless of branch.
- Read the preceding release notes for structure, voice, bullet length, punctuation, and emphasis.
- For each candidate, record the supporting commit or PR, user outcome, shipped scope, and intended section.
- Verify contributor counts and first-time status from the same range, excluding bots.
- Check ambiguous claims against the implementing PR, code, tests, and docs.
- Distinguish a PR's motivating use case from the interface contract actually shipped.
Work in dependency order
- Draft all detailed release-note sections.
- Self-review every bullet with the checklist below, then reread the full draft for duplication, inconsistent terminology, misplaced items, weak priority, and contradictions.
- Recheck corrected claims against the evidence base.
- Derive the Release Summary and Highlights from the approved sections.
- Update README news last as a condensed mirror of the approved Highlights.
Write for users
- Lead with the outcome; name the mechanism afterward.
- Replace implementation jargon with the task it enables, or define the term on first use.
- Omit command syntax unless it is essential to the user action; leave procedural details to the documentation.
- Explain unfamiliar environments or integrations instead of listing names alone.
- Give migrations enough context for users to understand what changed, whether they are affected, and what action to take.
- State safety or isolation limits explicitly. For example, host-process execution is not sandbox isolation.
- Describe only shipped support. Distinguish infrastructure for defining a capability from ready-made implementations, and provider-neutral architecture from providers that implement it.
- Keep documentation additions in a documentation section rather than presenting them as product capabilities.
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 1mo ago First seen · 97 lines · 50 tokens per session scan A 519602ea9596
nemo-gym-release-notes is a skill published in the GitHub repository NVIDIA-NeMo/Gym (1,320 stars, last pushed today), licensed Apache-2.0. It adds 50 tokens to every session and 1,077 once invoked, about $0.0002 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 2026-10-08.
nemo-gym-release-notes compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| nemo-gym-release-notesNVIDIA-NeMo/Gym | Skill | 1.3k | today | Apache-2.0 | A | 50 | 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 |