What is nemo-gym-pr-checks-and-labels?

A pull-request review workflow for NVIDIA-NeMo/Gym. A pull request is a proposed code change; this workflow selects relevant checks, investigates failures, and applies the repository's current labels.

Use it to assess pull-request readiness, choose local and CI checks, diagnose missing or failed checks, and label changes by type, area, and state.

It avoids running irrelevant checks or assigning labels based on guesswork. It uses the repository's own rules, change classification, history, and continuous-integration results.

How NVIDIA-NeMo/Gym configures Claude Code and Codex

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 · 1,320 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-pr-checks-and-labels/SKILL.md

Clone the repo

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

Made for: Claude Code, 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/nvidia-nemo/gym/nemo-gym-pr-checks-and-labels/github.svg)](https://agentmods.dev/skills/nvidia-nemo/gym/nemo-gym-pr-checks-and-labels)

Your own site

<a href="https://agentmods.dev/skills/nvidia-nemo/gym/nemo-gym-pr-checks-and-labels"><img src="https://agentmods.dev/badge/skills/nvidia-nemo/gym/nemo-gym-pr-checks-and-labels/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/nvidia-nemo/gym/nemo-gym-pr-checks-and-labels"><img src="https://agentmods.dev/badge/skills/nvidia-nemo/gym/nemo-gym-pr-checks-and-labels.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 123 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 2,882 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.

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 5.1	$0.00123	$0.02882
Opus 5.5	$0.00049	$0.01153
Sonnet 5.5	$0.00025	$0.00576
Haiku 4.5	$0.00012	$0.00288

Measured 16d ago against content hash c7ed51b03238, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

nemo-gym-pr-checks-and-labels 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 16d 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-pr-checks-and-labels/SKILL.md · 247 lines

How it starts

The opening of the file, as written. The whole thing — 247 lines — stays where its author put it; the contents beside it link to each section on GitHub.

NeMo Gym PR Checks and Labels

Use this workflow for a local branch or a GitHub pull request in NVIDIA-NeMo/Gym. Keep generic style rules in AGENTS.md, pyproject.toml, and .pre-commit-config.yaml; this skill covers the decisions that depend on Gym's change classifier, runtime contracts, and live PR taxonomy.

Establish Scope

Read the artifact before choosing checks or labels:

git status --short
git diff --stat <base>...HEAD
git diff --name-only <base>...HEAD

gh pr view <PR> --repo NVIDIA-NeMo/Gym \
  --json number,title,body,isDraft,author,baseRefName,headRefName,headRefOid,labels,reviewDecision,mergeStateStatus
gh api repos/NVIDIA-NeMo/Gym/pulls/<PR> --jq .author_association
gh pr diff <PR> --repo NVIDIA-NeMo/Gym --name-only
gh pr checks <PR> --repo NVIDIA-NeMo/Gym

For local validation and CI routing, treat these repository files as authoritative:

AGENTS.md for the quality bar and required rollout evidence.
CONTRIBUTING.md for contributor and environment requirements.
.pre-commit-config.yaml and pyproject.toml for enforced style.
.github/actions/classify-changes/action.yml for test-scope classification.
.github/workflows/unit-tests.yml and .github/workflows/cicd-main.yml for actual CI behavior.
scripts/ci/cov_fail_under.py for the coverage threshold used by CI.

When those files disagree with this skill, follow the repository files and report the drift.

Review Relevant History

Before implementing or approving a non-trivial change to established behavior, do a bounded history pass over the affected code. Inspect behavior-owning source files even when the diff changes only tests; a new test can accidentally encode behavior that an earlier PR deliberately excluded or kept compatible.

Start with recent commits and narrow blame where the behavior is not obvious:

git log --oneline -n 10 -- <path>
git blame -L <start>,<end> -- <path>

For a relevant commit, follow a PR number in its subject or ask GitHub which PR contained it. Read both the PR-level discussion and inline review threads, because important constraints are often recorded only in review comments:

Read the full file on GitHub · 247 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.

16d ago Changed · +1 lines · +40 tokens per session c7ed51b03238
1mo ago First seen · 246 lines · 83 tokens per session scan A 2aad2b90470a

Subscribe to this mod's changes

nemo-gym-pr-checks-and-labels is a skill published in the GitHub repository NVIDIA-NeMo/Gym (1,320 stars, last pushed today), licensed Apache-2.0. It adds 123 tokens to every session and 2,882 once invoked, about $0.0005 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 2026-09-18.

Code review Git and workflow agents gym reinforcement-learning reinforcement-learning-environments rl-environment rl-training

nemo-gym-pr-checks-and-labels next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
nemo-gym-pr-checks-and-labelsNVIDIA-NeMo/Gym	Skill	1.3k	today	Apache-2.0	A	123	Claude Code, Codex
hunk-launch-videomodem-dev/hunk	Skill	9.8k	yesterday	MIT	A	60	Claude Code, Codex
otto-pr-review-loopomnigent-ai/omnigent	Skill	11k	yesterday	Apache-2.0	A	17	Claude Code, Codex
hunk-releasemodem-dev/hunk	Skill	9.8k	yesterday	MIT	A	38	Claude Code, Codex
resolve-drive-promnigent-ai/omnigent	Skill	11k	yesterday	Apache-2.0	A	21	Claude Code, Codex
describe-prhumanlayer/humanlayer	Skill	13k	yesterday	Apache-2.0	A	15	Claude Code, Codex
feature-publishomnigent-ai/omnigent	Skill	11k	yesterday	Apache-2.0	A	24	Claude Code, Codex

Gym: Skill for Claude Code