Gym: Skill for Codex

.agents/skills/nemo-gym-reward-profiling/SKILL.md

nemo-gym-reward-profiling is a skill for Codex from NVIDIA-NeMo/Gym. It costs 78 tokens per session (631 once invoked), scanned A, original, Apache-2.0.

A guide for running NeMo Gym reward profiling, which measures how reward results vary across repeated model attempts. It describes starting environments, collecting rollout JSONL files, and generating profiling output.

In plain words
What is it for?
Use it to start Gym environments, run evaluations, create materialized inputs, generate reward-profiling JSONL files, inspect outputs, and run partial profiling.
Why use it?
It gives you a repeatable workflow for inspecting rewards, task identity, repeated runs, and per-task variation.

Skill for Codex

Written for Codex: agents/openai.yaml present. Also seen: installed under .agents/ (shared by several agents).

This is NVIDIA-NeMo/Gym's own configuration. It tells Codex how to work on Gym itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything Gym configures →

About the project

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.

NVIDIA-NeMo/Gym · 1,183 stars · on GitHub · docs.nvidia.com

Reuse

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.

Copy the file
curl -O https://raw.githubusercontent.com/NVIDIA-NeMo/Gym/main/.agents/skills/nemo-gym-reward-profiling/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/NVIDIA-NeMo/Gym

Made for: Codex.

Wrote 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.

agentmods badge for nemo-gym-reward-profiling

README.md
[![agentmods](https://agentmods.dev/badge/skills/nvidia-nemo/gym/nemo-gym-reward-profiling/github.svg)](https://agentmods.dev/skills/nvidia-nemo/gym/nemo-gym-reward-profiling)
Your own site
<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.

agentmods 80×15 button for nemo-gym-reward-profiling

Your own site · 80×15
<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>
Per session 78 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 631 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce 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

Measured 13d ago against content hash 8adfbde623c2, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

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.

.agents/skills/nemo-gym-reward-profiling/SKILL.md · 54 lines

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

  1. Identify the environment config paths and input JSONL.
  2. Start Gym servers with gym env start.
  3. Collect rollouts with gym eval run --no-serve; this writes rollouts.jsonl and *_materialized_inputs.jsonl.
  4. Run gym eval profile on the materialized inputs and rollout JSONL to generate *_reward_profiling.jsonl.
  5. 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.md for a generic command template and the minimal run sequence.
  • Read references/output-format.md to explain materialized inputs, rollout JSONL, reward profile rows, rollout_infos, and partial profiling.

Read the full file on GitHub · 54 lines

Files

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.

Changes

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.

  1. 13d ago First seen · 54 lines · 78 tokens per session scan A 8adfbde623c2

Subscribe to this mod's changes

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.

Related

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.

vuralserhat86/antigravity-agentic-skills · 67 tokens

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.

DonggangChen/antigravity-agentic-skills · 67 tokens

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…

patchy631/ai-engineering-hub · 131 tokens

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.

patchy631/ai-engineering-hub · 49 tokens

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…

Shubhamsaboo/awesome-llm-apps · 206 tokens

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.

davila7/claude-code-templates · 49 tokens