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.
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 agentmods add instructions/nvidia-nemo/gym/claude-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/instructions/nvidia-nemo/gym/claude-md)<a href="https://agentmods.dev/instructions/nvidia-nemo/gym/claude-md"><img src="https://agentmods.dev/badge/instructions/nvidia-nemo/gym/claude-md.svg" alt="Measured on agentmods" 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 | $0.00003 | $0.00003 |
| Opus 5 | $0.00002 | $0.00002 |
| Sonnet 5 | $0.00001 | $0.00001 |
| Haiku 4.5 | $0.00000 | $0.00000 |
Grade A, and why
Gym CLAUDE.md 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 5d 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.
This is a copy
100% identical to deepseek-harness CLAUDE.md — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
What it actually says
AGENTS.md
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.
- 5d ago First seen · 1 lines · 3 tokens per session scan A a54ff182c7e8
Gym CLAUDE.md is an instructions file published in the GitHub repository NVIDIA-NeMo/Gym (1,159 stars, last pushed yesterday), licensed Apache-2.0. It adds 3 tokens to every session, about $0.0000 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to deepseek-harness CLAUDE.md, differing in 0 lines, and is treated as a copy.
Other instructions, from other repositories
mobilegym AGENTS.md
Instructions for Purewhiter/mobilegym, covering agents.md, project overview, type-checking strategy, eslint and with data graph generation.
baba-is-auto AGENTS.md
AGENTS.md instructions for utilForever/baba-is-auto, covering agents.md, what this repository is, golden rules (read before any change), the most common task: changing simulator behavior and repository map.
RosettaStone AGENTS.md
AGENTS.md instructions for utilForever/RosettaStone, covering agents.md, what this repository is, golden rules (read before any change), common task flow and hearthstone model.
UniRL AGENTS.md
AGENTS.md instructions for Tencent-Hunyuan/UniRL, a project described as: UniRL is a Framework for Unified Multimodal Model Reinforcement Learning.
HumanoidClimb-RL CLAUDE.md
Instructions for s1ddh-rth/HumanoidClimb-RL, covering claude.md, environment setup, common commands, architecture and data flow.
mobilegym CLAUDE.md
Instructions for Purewhiter/mobilegym, a project described as: