NVIDIA/NeMo-Relay is a runtime and library that gives coding agents and applications shared control over agent execution scopes, policies, plugins, lifecycle events, and observability data. It is for developers who need to inspect or instrument runs from agents such as Codex or Claude Code, or integrate frameworks and export traces and trajectories. The catalogue entries provide Relay plugins, hooks, instructions, skills, and an MCP server for those workflows.
Borrowing it
Nothing to install: this file belongs to NVIDIA/NeMo-Relay. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/NVIDIA/NeMo-Relay/main/.agents/skills/prepare-pr/SKILL.mdgit clone --depth 1 https://github.com/NVIDIA/NeMo-RelayWrote 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-relay/prepare-pr)<a href="https://agentmods.dev/skills/nvidia/nemo-relay/prepare-pr"><img src="https://agentmods.dev/badge/skills/nvidia/nemo-relay/prepare-pr/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-relay/prepare-pr"><img src="https://agentmods.dev/badge/skills/nvidia/nemo-relay/prepare-pr.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00040 | $0.00765 |
| Opus 5.5 | $0.00016 | $0.00306 |
| Sonnet 5.5 | $0.00008 | $0.00153 |
| Haiku 4.5 | $0.00004 | $0.00076 |
Grade A, and why
prepare-pr 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 — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Prepare A PR For NeMo Relay
Use this skill at the end of a contributor or maintainer change before opening a pull request. Also use it whenever a user asks to create, open, publish, update, or edit a NeMo Relay pull request, pull request description, or PR body.
If this repo-local guidance conflicts with generic GitHub publishing, connector, or plugin guidance, this skill wins for PR body format, validation language, and review handoff details.
Checklist
- Branch scope is coherent and reviewable
- Validation results accurately report checks already run and relevant omissions without widening validation solely for PR preparation
- Pull request title follows Conventional Commit style and uses the correct type
- Pull request body follows
.github/pull_request_template.md - Breaking changes or renamed surfaces are called out explicitly
Pull Request Title
Use Conventional Commit style for PR titles:
<type>: <concise imperative summary>
Choose the type from the actual change surface, not from the impact of the
review comment or CI outcome. Use fix only for an actual user-facing or
runtime/product code bug fix. Never use fix for changes that are not related
to product code behavior, including chores, CI configuration, docs, tests,
packaging metadata, generated-output handling, or agent/skill guidance.
Common examples:
ci: update codecov coverage reportingdocs: clarify release workflowenhancement: improve scope configurationchore: refresh generated attribution dataskills: add a plugin-authoring guidetest: add Python scope regression coveragefix: preserve scope-local middleware cleanup
Opening A Pull Request
Always use .github/pull_request_template.md as the source of truth for the PR
body. Before opening a PR, read the current template and preserve its headings,
checkboxes, comments' intent, and related-issue guidance.
This applies both when creating a new PR and when editing an existing PR
description. Do not use a generic Summary / Why / Validation body unless the
current repository template uses those headings.
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 Changed · -18 lines · +1 tokens per session d42d5f751483
- 1mo ago First seen · 111 lines · 39 tokens per session scan A 7f9ecc33b03a
prepare-pr is a skill published in the GitHub repository NVIDIA/NeMo-Relay (212 stars, last pushed today), licensed Apache-2.0. It adds 40 tokens to every session and 765 once invoked, about $0.0002 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
adk-git
Writes commit messages and pull request descriptions for the adk-python repository: Conventional Commits types and scopes, subject lines that say why a change was made, and the linked-issue and testing-plan sections the PR template requires. Use when writing or rewording a commit message, squashing commits before a…
commit-context
Trace a file, function, or line back to the agent session that produced its current commit. Use when the user asks "why is this code here", "what was the agent doing when this changed", "who wrote this", or wants context on a specific location in the codebase.
commit-history
List recent git commits linked to agent sessions, optionally filtered by branch or repo. Use when the user asks "show agent commits", "what has the agent shipped", "list linked commits", or wants commits with their session context.
resolve-publish
Commit the validated fix and follow local-only, workflow-owned, or direct PR publication.
commit-messages
Write git commit messages and pull request titles in the WARP format used by the swarms repo.
feature-publish
Commit the feature, write the PR body, publish in the selected mode, and drive the PR.