nemo-rl-e2e-testing

nemo-rl-e2e-testing is a skill for Claude Code, Codex from NVIDIA-NeMo/Megatron-Bridge. It costs 154 tokens per session (7,141 once invoked), scanned A, original, Apache-2.0.

An end-to-end test workflow for checking Megatron-Bridge model or training changes inside NeMo-RL, a reinforcement-learning training system for language models. It checks whether the change works across the external training process, not only in focused Bridge tests.

In plain words
What is it for?
Use it after focused Bridge tests when changing a model provider or configuration, starting with a short Megatron policy GRPO test and adding checks for LoRA, importing or exporting models, resuming checkpoints, or vLLM when relevant.
Why use it?
It catches integration problems that isolated model tests may miss, such as checkpoint handling, reward and rollout wiring, or transferring model weights between training and text generation.

Skill for Claude CodeCodex

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 skills/nvidia-nemo/megatron-bridge/nemo-rl-e2e-testing
Any agent
npx skills add NVIDIA-NeMo/Megatron-Bridge --skill nemo-rl-e2e-testing
Clone the repo
git clone --depth 1 https://github.com/NVIDIA-NeMo/Megatron-Bridge

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.

agentmods badge for nemo-rl-e2e-testing

README.md
[![agentmods](https://agentmods.dev/badge/skills/nvidia-nemo/megatron-bridge/nemo-rl-e2e-testing.svg)](https://agentmods.dev/skills/nvidia-nemo/megatron-bridge/nemo-rl-e2e-testing)
Your own site
<a href="https://agentmods.dev/skills/nvidia-nemo/megatron-bridge/nemo-rl-e2e-testing"><img src="https://agentmods.dev/badge/skills/nvidia-nemo/megatron-bridge/nemo-rl-e2e-testing.svg" alt="Measured on agentmods" height="20"></a>
Per session 154 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 7,141 The whole file, excluding the scripts and references it only reads on demand.
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.

ModelPer sessionOnce invoked
Fable 5 $0.00154 $0.07141
Opus 5 $0.00077 $0.03571
Sonnet 5 $0.00031 $0.01428
Haiku 4.5 $0.00015 $0.00714

Measured 5d ago against content hash d11394529d73, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

nemo-rl-e2e-testing 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.

skills/nemo-rl-e2e-testing/SKILL.md · 557 lines

How it starts

The opening of the file, as written. The whole thing — 557 lines — stays where its author put it; the contents beside it link to each section on GitHub.

NeMo-RL E2E Testing

Validate a Megatron-Bridge model or training API change through NeMo-RL's Megatron backend. This catches integration issues that Bridge-only tests miss: NeMo-RL-owned rollout scheduling, reward handling, policy/reference setup, HF import/export through Bridge, optimizer setup, checkpoint ownership, and policy-to-generation weight transfer.

Use this as an external compatibility smoke test after the focused Bridge tests for the model/provider change pass.

This is not a replacement for Bridge model parity tests. A NeMo-RL GRPO or SFT run proves that Bridge can survive an external RL training loop; architecture correctness still comes from Bridge import/export, logits, roundtrip, and model-specific inference tests.

Scope

Think in coverage levels. Start with Level 0 and add only the levels justified by the change.

Level Required when What it proves
0: Megatron policy GRPO smoke Any new provider or provider config change that claims NeMo-RL compatibility NeMo-RL can import the local Bridge provider, build a Megatron policy, initialize optimizer/scheduler state, run rollout/ref/logprob wiring, and finish a short GRPO job
1: LoRA/checkpoint variant Checkpointing, HF export, optimizer state, resume behavior, or a NeMo-RL-supported PEFT path changed NeMo-RL can save through its checkpoint schedule, resume without losing training state, and, when PEFT is enabled in that NeMo-RL checkout, apply Bridge LoRA hooks
2: Non-colocated vLLM refit HF export, weight mapping, policy-to-generation refit, delta compression, packed transfer, or vLLM update behavior changed Bridge-exported weights can be transferred from the Megatron policy worker into separate vLLM generation workers
3: Optional Megatron generation backend Only when the NeMo-RL checkout still supports policy.generation.backend=megatron and the change explicitly targets that path NeMo-RL can use Megatron for both policy and generation rather than only vLLM generation
4: Parallelism stress TP/PP/CP/EP, sequence parallel, MoE dispatch, pipeline stage layout, or distributed optimizer behavior changed Provider settings remain correct under non-trivial Megatron parallel state
5: Architecture-specific e2e VLM, audio, MoE, MTP/draft models, FP8/QAT/ModelOpt, quantized weights, or custom layers are involved The architecture-specific runtime path is exercised, not just a text-only dense GRPO smoke
6: Learning signal Optimizer, scheduler, loss, reward, PEFT trainability, gradient flow, or training stability changed Metrics move in the expected direction over a short run and do not silently produce zero/NaN/unstable updates

Read the full file on GitHub · 557 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. 5d ago First seen · 557 lines · 154 tokens per session scan A d11394529d73

Subscribe to this mod's changes

nemo-rl-e2e-testing is a skill published in the GitHub repository NVIDIA-NeMo/Megatron-Bridge (900 stars, last pushed yesterday), licensed Apache-2.0. It adds 154 tokens to every session and 7,141 once invoked, about $0.0008 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

use-agent-browser-for-airi

Test AIRI display-model imports with agent-browser across stage-tamagotchi Electron, stage-web, and stage-pocket mobile web layouts. Use when uploading and verifying contributor-supplied Live2D ZIP, VRM, or MMD ZIP/PMX/PMD files through AIRI's model selector, including onboarding bypass, format-specific import…

moeru-ai/airi · 87 tokens

run-integration-tests

Build, pack, and run .NET MAUI integration tests locally. Validates templates, samples, and end-to-end scenarios using the local workload.

dotnet/maui · 35 tokens

cli-e2e-testcase-writer

Use when adding or updating Go CLI E2E coverage for one tests/clie2e/{domain} domain of the compiled lark-cli, especially when the work requires live --help or schema exploration, scenario-based clie2e.RunCmd workflows, and per-domain coverage.md maintenance.

larksuite/cli · 78 tokens

webapp-testing

Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.

every-app/open-seo · 35 tokens

harness-test-writer

Add regression test cases to the Bifrost provider harness (the Postman collection run via make run-provider-harness-test) based on a merged PR or a GitHub issue. Fetches the PR/issue, traces the affected wire path in the codebase, checks existing harness coverage, designs cases following harness conventions, inserts…

maximhq/bifrost · 133 tokens

agent-device-evidence

Records iOS/Android native MP4 evidence for test/repro flows extracted from an Expensify GitHub PR or issue. Use when the user asks to "record the flow for PR.

Expensify/App · 43 tokens