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-reward-profiling/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-reward-profiling)<a href="https://agentmods.dev/skills/nvidia-nemo/gym/nemo-gym-reward-profiling"><img src="https://agentmods.dev/badge/skills/nvidia-nemo/gym/nemo-gym-reward-profiling/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-reward-profiling"><img src="https://agentmods.dev/badge/skills/nvidia-nemo/gym/nemo-gym-reward-profiling.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 | $0.00078 | $0.00631 |
| Opus 5 | $0.00039 | $0.00316 |
| Sonnet 5 | $0.00016 | $0.00126 |
| Haiku 4.5 | $0.00008 | $0.00063 |
Grade A, and why
nemo-gym-reward-profiling 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 13d 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 — 54 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Nemo Gym Reward Profiling
Invocation Check
Use this skill when the user wants to run, understand, or lightly modify Nemo Gym reward profiling. Keep the answer oriented around the normal workflow:
gym env start starts model/resources servers, gym eval run --no-serve writes rollout artifacts, and gym eval profile generates profiling output from those artifacts.
If the user is primarily debugging a failed job or stack trace, use the nemo-gym-debugging skill first.
Basic Workflow
- Identify the environment config paths and input JSONL.
- Start Gym servers with
gym env start. - Collect rollouts with
gym eval run --no-serve; this writesrollouts.jsonland*_materialized_inputs.jsonl. - Run
gym eval profileon the materialized inputs and rollout JSONL to generate*_reward_profiling.jsonl. - Inspect line counts and profile rows.
Repeated rollouts are the main profiling lever. num_repeats=1 is valid, but per-task averages and variance are only meaningful with multiple rollouts per task.
Core Concepts
*_materialized_inputs.jsonl: expanded collection inputs after repeat expansion, agent defaults, and task/rollout id assignment.rollouts.jsonl: one completed rollout/result per materialized input row.*_reward_profiling.jsonl: one summarized profile row per original task with at least one completed rollout._ng_task_index: original task/sample id._ng_rollout_index: repeated rollout id for that task.rollout_infos: compact per-rollout info inside each task profile row, including reward, token usage, and numeric rollout metrics when available.
Keep reward-to-length or reward-to-token analysis keyed by both _ng_task_index and _ng_rollout_index.
Reference Loading
Load references only when the user needs that detail:
- Read
references/quick-start.mdfor a generic command template and the minimal run sequence. - Read
references/output-format.mdto explain materialized inputs, rollout JSONL, reward profile rows,rollout_infos, and partial profiling.
What ships with it
3 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.
- 13d ago First seen · 54 lines · 78 tokens per session scan A 8adfbde623c2
nemo-gym-reward-profiling is a skill published in the GitHub repository NVIDIA-NeMo/Gym (1,183 stars, last pushed today), licensed Apache-2.0. It adds 78 tokens to every session and 631 once invoked, about $0.0004 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
model_finetuning
Fine-tune LLMs using reinforcement learning with TRL - SFT for instruction tuning, DPO for preference alignment, PPO/GRPO for reward optimization, and reward model training. Use when need RLHF, align model with preferences, or train from human feedback. Works with HuggingFace Transformers.
model_finetuning
Fine-tune LLMs using reinforcement learning with TRL - SFT for instruction tuning, DPO for preference alignment, PPO/GRPO for reward optimization, and reward model training. Use when need RLHF, align model with preferences, or train from human feedback. Works with HuggingFace Transformers.
hugging-face-model-trainer
This skill should be used when users want to train or fine-tune language models using TRL (Transformer Reinforcement Learning) on Hugging Face Jobs infrastructure. Covers SFT, DPO, GRPO and reward modeling training methods, plus GGUF conversion for local deployment. Includes guidance on the TRL Jobs package, UV…
hugging-face-datasets
Create and manage datasets on Hugging Face Hub. Supports initializing repos, defining configs/system prompts, streaming row updates, and SQL-based dataset querying/transformation. Designed to work alongside HF MCP server for comprehensive dataset workflows.
thinking-out-loud
A contract for what the agent does when a long, messy, stream-of-consciousness ramble arrives (usually voice dictation): act on nothing until the echo brief is approved. The echo audits the entire transfer, mission, locked decisions and constraints, open questions, flips and parked tangents, with the model's…
torchforge-rl-training
Provides guidance for PyTorch-native agentic RL using torchforge, Meta's library separating infra from algorithms. Use when you want clean RL abstractions, easy algorithm experimentation, or scalable training with Monarch and TorchTitan.