What is Gym AGENTS.md?

Shared instructions for AI coding assistants working on NVIDIA NeMo Gym, including its quality standards, architecture, and environment setup.

Use them when changing environments or agents, reviewing generated code, running tests and pre-commit checks, or preparing a signed contribution.

They keep changes focused and require real agent rollouts and local checks, helping reveal problems that ordinary unit tests may miss.

Gym AGENTS.md — Instructions file by NVIDIA-NeMo

Install

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.

agentmods

npx agentmods add instructions/nvidia-nemo/gym/agents-md

Clone the repo

git clone --depth 1 https://github.com/NVIDIA-NeMo/Gym

Made for: Codex, OpenCode.

Per session 2,289 This file is loaded in full into every session.

When invoked 2,289 The same file — it is already loaded in full.

Security scan A 0 findings. Scan, not verified.

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.

Model	Per session	Once invoked
Fable 5	$0.02289	$0.02289
Opus 5	$0.01144	$0.01144
Sonnet 5	$0.00458	$0.00458
Haiku 4.5	$0.00229	$0.00229

Measured 3d ago against content hash 5556d6287ced, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

Gym AGENTS.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 3d 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.md · 165 lines

How it starts

The opening of the file, as written. The whole thing — 165 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

Unified root instructions for AI coding assistants (Cursor, Claude, Codex, OpenCode, Copilot, and similar).

CLAUDE.md is a symlink to this file so Claude Code and other tools share one source of truth.

Humans: see Development Setup → Use of AI and LLM Tools (maintainer response policy) and Agent Skills.

Quality bar

Prefer focused changes. Do not make unrelated "drive-by" edits. If a drive-by fix is worth keeping, open a separate issue or PR.
Intentional synthetic scaling of environments is fine when scoped via an issue or focused PR; do not dump unreviewed bulk diffs.
You (the human author) own every line submitted. Treat model output as untrusted until reviewed.
For environment or agent changes: run real rollouts with a model and inspect agent and verifier behavior. Green unit tests alone are not enough.
Before opening a PR, run the local checks that mirror CI: tests (skip or N/A for docs-only), pre-commit run --all-files, and DCO sign-off (git commit -s). Cryptographic -S signing is optional and not required.
AI-generated tests must assert real behavior; avoid vacuous pass-through tests.
Prefer the vetted skills under .agents/skills/ (see Agent Skills).
Docs live under fern/versions/latest/pages/. Bleeding-edge nav is fern/versions/main.yml. See fern/README.md and the nemo-gym-docs skill.
Do not introduce licenses incompatible with Apache-2.0. New source files need the standard NVIDIA SPDX header.

What This Is

NeMo Gym is a library for evaluating and improving models and agents using environments. It provides infrastructure to develop environments, scalably run evaluation and training, and a collection of popular benchmarks and training environments. All components are composable and modular — bring your own agent, model, or environment and integrate with Gym where you need it.

Read the full file on GitHub · 165 lines

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.

3d ago First seen · 165 lines · 2,289 tokens per session scan A 5556d6287ced

Subscribe to this mod's changes

Gym AGENTS.md is an instructions file published in the GitHub repository NVIDIA-NeMo/Gym (1,148 stars, last pushed 3d ago), licensed Apache-2.0. It adds 2,289 tokens to every session, about $0.0114 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.

agents gym reinforcement-learning reinforcement-learning-environments rl-environment rl-training

Gym AGENTS.md

Getting it into your agent

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

AGENTS.md

Quality bar

What This Is

What this file has done since we first saw it

Other instructions, from other repositories

mobilegym AGENTS.md

mobilegym CLAUDE.md

baba-is-auto AGENTS.md

RosettaStone AGENTS.md

omnigent copilot-instructions.md

AutoAgents AGENTS.md