nemo-gym-recipe-integration

nemo-gym-recipe-integration is a skill for Claude Code from redai-infra/Relax. It costs 73 tokens per session (2,877 once invoked), scanned A, original, Apache-2.0.

A three-step recipe for adding an NVIDIA NeMo Gym environment to Relax. NeMo Gym provides interactive environments for training AI agents, while Relax runs the training process.

In plain words
What is it for?
Use it to prepare recipe data, start a private local Gym service, launch remote Ray training, validate the verifier, connect callbacks, and investigate failed runs.
Why use it?
It lays out the required data, local service, training, verification, networking, and cleanup steps in one workflow. This helps avoid incomplete recipes and common connection or startup failures.

Skill for Claude Code

Written for Claude Code: argument-hint in frontmatter.

Good fit Use it to prepare recipe data, start a private local Gym service, launch remote Ray training, validate the verifier, connect callbacks, and investigate failed runs.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/redai-infra/relax/nemo-gym-recipe-integration
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.

Any agent
npx skills add redai-infra/Relax --skill nemo-gym-recipe-integration
Clone the repo
git clone --depth 1 https://github.com/redai-infra/Relax

Made for: Claude Code.

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-recipe-integration

README.md
[![agentmods](https://agentmods.dev/badge/skills/redai-infra/relax/nemo-gym-recipe-integration/github.svg)](https://agentmods.dev/skills/redai-infra/relax/nemo-gym-recipe-integration)
Your own site
<a href="https://agentmods.dev/skills/redai-infra/relax/nemo-gym-recipe-integration"><img src="https://agentmods.dev/badge/skills/redai-infra/relax/nemo-gym-recipe-integration/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-recipe-integration

Your own site · 80×15
<a href="https://agentmods.dev/skills/redai-infra/relax/nemo-gym-recipe-integration"><img src="https://agentmods.dev/badge/skills/redai-infra/relax/nemo-gym-recipe-integration.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 73 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,877 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 $0.00073 $0.02877
Opus 5 $0.00036 $0.01438
Sonnet 5 $0.00015 $0.00575
Haiku 4.5 $0.00007 $0.00288

Measured 12d ago against content hash 6164f735da29, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

nemo-gym-recipe-integration 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 12d 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.

skills/nemo-gym-recipe-integration/SKILL.md · 241 lines

How it starts

The opening of the file, as written. The whole thing — 241 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Integrating a NeMo Gym recipe

Build a new recipe by following the proven Calendar flow and the accumulated PITFAIL records. Keep the user-facing workflow to exactly three steps:

  1. prepare data;
  2. start the local NeMo Gym service;
  3. start remote Relax training.

Non-negotiable rules

  • Deliver executable scripts, not a prose-only procedure.
  • Run steps 1 and 2 locally. Fix and retry until data, readiness, and the verifier all pass.
  • Put only deployment-specific values in env.sh: image, model path, Gym host/port, shared data path, and optionally remote Ray address.
  • Write training hyperparameters directly in the training script. Do not create NEMO_GYM_NUM_ROLLOUT, NEMO_GYM_N_SAMPLES_PER_PROMPT, context-length, batch-size, or parser environment variables.
  • The training script must contain the complete parameter arrays and final ray job submit. It may use scripts/run_training.sh as the remote job entry and scripts/run_agent_app.sh as the thin agent client, but must not delegate to another model training recipe.
  • Never enable --no-wait by default. Add it only when the caller explicitly sets RAY_NO_WAIT=1.
  • Data preparation must create the exact shared file checked by training. A file left only in a Docker volume is not prepared data.
  • Training consumes the raw NeMo Gym JSONL. Do not pass an already converted *_relax.jsonl back through convert_dataset.py.
  • Do not claim success from /readyz, a Ray Job SUCCEEDED state, or a one-sample rollout alone.
  • A NeMo HTTP 500 must leave a traceback in docker logs; do not accept access-log-only failures.
  • Preserve user changes and replace only the named recipe container after verifying its ownership label.
  • Never run broad ray stop, pkill, Docker prune, or sandbox cleanup on a shared system.

Read before editing

Read these files completely because they evolve with real failures:

rg --files examples/nemo_gym_agentic/recipes | rg '/PITFAIL\.md$' | sort

Then read:

  • every returned PITFAIL.md;
  • the target environment config in the pinned NeMo Gym checkout;
  • the target agent, resource server, dataset declaration, verifier, and cleanup behavior;
  • examples/nemo_gym_agentic/service/Dockerfile;
  • examples/nemo_gym_agentic/scripts/convert_dataset.py;
  • examples/nemo_gym_agentic/scripts/run_training.sh;
  • examples/nemo_gym_agentic/scripts/run_agent_app.sh;
  • the Calendar recipe as the simple-agent reference;
  • Workplace Assistant for stateful tool/resource cleanup;
  • R2E-Gym for sandbox, artifact, and multi-process callback propagation.

Read the full file on GitHub · 241 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.

  1. 12d ago First seen · 241 lines · 73 tokens per session scan A 6164f735da29

Subscribe to this mod's changes

nemo-gym-recipe-integration is a skill published in the GitHub repository redai-infra/Relax (580 stars, last pushed 14d ago), licensed Apache-2.0. It adds 73 tokens to every session and 2,877 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

verl-rl-training

Provides guidance for training LLMs with reinforcement learning using verl (Volcano Engine RL). Use when implementing RLHF, GRPO, PPO, or other RL algorithms for LLM post-training at scale with flexible infrastructure backends.

davila7/claude-code-templates · 51 tokens

openrlhf-training

High-performance RLHF framework with Ray+vLLM acceleration. Use for PPO, GRPO, RLOO, DPO training of large models (7B-70B+). Built on Ray, vLLM, ZeRO-3. 2× faster than DeepSpeedChat with distributed architecture and GPU resource sharing.

davila7/claude-code-templates · 72 tokens

verl-rl-training

Provides guidance for training LLMs with reinforcement learning using verl (Volcano Engine RL). Use when implementing RLHF, GRPO, PPO, or other RL algorithms for LLM post-training at scale with flexible infrastructure backends.

OpenLAIR/dr-claw · 51 tokens

openrlhf-training

High-performance RLHF framework with Ray+vLLM acceleration. Use for PPO, GRPO, RLOO, DPO training of large models (7B-70B+). Built on Ray, vLLM, ZeRO-3. 2× faster than DeepSpeedChat with distributed architecture and GPU resource sharing.

OpenLAIR/dr-claw · 72 tokens

verl-rl-training

Provides guidance for training LLMs with reinforcement learning using verl (Volcano Engine RL). Use when implementing RLHF, GRPO, PPO, or other RL algorithms for LLM post-training at scale with flexible infrastructure backends.

Orchestra-Research/AI-Research-SKILLs · 51 tokens

openrlhf-training

High-performance RLHF framework with Ray+vLLM acceleration. Use for PPO, GRPO, RLOO, DPO training of large models (7B-70B+). Built on Ray, vLLM, ZeRO-3. 2× faster than DeepSpeedChat with distributed architecture and GPU resource sharing.

Orchestra-Research/AI-Research-SKILLs · 72 tokens