Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/NVIDIA-NeMo/Megatron-Bridgenpx agentmods add skills/nvidia-nemo/megatron-bridge/nemo-rl-e2e-testingWrote 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/skills/nvidia-nemo/megatron-bridge/nemo-rl-e2e-testing)<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/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.
<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="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Agent Snooping · line 468 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
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 | $0.00154 | $0.07141 |
| Opus 5.5 | $0.00062 | $0.02856 |
| Sonnet 5.5 | $0.00031 | $0.01428 |
| Haiku 4.5 | $0.00015 | $0.00714 |
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 1mo 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.
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 |
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.
- 1mo ago First seen · 557 lines · 154 tokens per session scan A d11394529d73
nemo-rl-e2e-testing is a skill published in the GitHub repository NVIDIA-NeMo/Megatron-Bridge (970 stars, last pushed today), licensed Apache-2.0. It adds 154 tokens to every session and 7,141 once invoked, about $0.0006 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 2026-08-30.
Other skills, from other repositories
eval-dataset-design
A guide to creating reliable test sets for AI agents. Each evaluation task includes the request, the simulated user's behaviour, a reset starting state, and a success check that can be independently verified.
verify-omnigent
Drive Omnigent the way a user does and prove a behavior with recorded evidence, using an isolated server, runner, and mock model plus a feature map of every user entry point. Load before reproducing a user-facing bug, before claiming a fix works, or when reviewing whether a change covered every surface (session vs.…
test-master
Generates test files, creates mocking strategies, analyzes code coverage, designs test architectures, and produces test plans and defect reports across functional, performance, and security testing disciplines. Use when writing unit tests, integration tests, or E2E tests; creating test strategies or automation…
dogfood
Systematically explore and test a mobile app on iOS/Android with agent-device to find bugs, UX issues, and other problems. Use when asked to dogfood, QA, exploratory test, find issues, bug hunt, or test this app on mobile.
cua-driver
Use Cua Driver for desktop or browser tasks that are awkward or unavailable through Bash/APIs, or when the user explicitly wants GUI interaction: app testing, visual bug reproduction, form filling, calendar entry, screenshots, and demo recording. Also covers Cua setup; not OpenAI Codex Computer Use or web research.
critique
Adversarial design critique of the current work. Render it, look at it, and argue for rejection. Run after the gates are green, never instead of them.