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/review-doc-style/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/review-doc-style)<a href="https://agentmods.dev/skills/nvidia/nemo-relay/review-doc-style"><img src="https://agentmods.dev/badge/skills/nvidia/nemo-relay/review-doc-style.svg" alt="Measured on agentmods" 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 | $0.00024 | $0.01229 |
| Opus 5 | $0.00012 | $0.00615 |
| Sonnet 5 | $0.00005 | $0.00246 |
| Haiku 4.5 | $0.00002 | $0.00123 |
Grade A, and why
review-doc-style 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 8d 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 — 119 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Review Documentation Style
Companion Guidance
Use karpathy-guidelines alongside this skill for implementation or review
work. Keep changes scoped, surface assumptions, and define focused validation
before editing.
Use this skill when reviewing docs-only changes, example-heavy changes, or any public-facing text update that should be checked against NVIDIA style guidance and NeMo Relay repo conventions.
Review Priorities
- Prioritize factual accuracy over copy polish
- Flag stale commands, package names, APIs, bindings, repo paths, or support claims before stylistic issues
- Keep docs aligned with current NeMo Relay behavior, repo layout, and entry points
- Apply NVIDIA technical-writing guidance where it improves clarity and consistency without watering down technical precision
Review Flow
- Identify the changed docs, examples, or public-facing strings.
- Confirm the described behavior is still true in the current repo.
- Check whether entry-point docs also need updates:
README.mddocs/index.md- Package or crate READMEs
- Binding-level source READMEs such as
python/nemo_relay/README.mdorcrates/core/README.md
- Start with
assets/nvidia-style-guide.md, then open only the focused support document needed for the issue under review. - Scan for high-signal style issues in headings, links, code formatting, terminology, procedures, and plain-English readability.
- Report findings in severity order with file references and concrete rewrites.
Must-Fix Findings
Treat these as blocking issues:
- Commands, package names, file paths, or APIs are incorrect or stale
- Public behavior changed but the corresponding entry-point docs were not updated
- A doc claims support for a binding, feature, or workflow that the repo no longer provides
- Examples or procedures are likely to fail as written
- User-facing naming is inconsistent with current repo terminology
- MDX top-of-file SPDX comments use HTML comment delimiters instead of
{/* ... */} - NVIDIA is not capitalized correctly
- Code, commands, paths, or filenames are not formatted as inline code where needed
What ships with it
4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 8d ago First seen · 119 lines · 24 tokens per session scan A 64eb4446c6e3
review-doc-style is a skill published in the GitHub repository NVIDIA/NeMo-Relay (165 stars, last pushed yesterday), licensed Apache-2.0. It adds 24 tokens to every session and 1,229 once invoked, about $0.0001 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.
Other skills, from other repositories
migration-review
Review database migration files when a change adds or modifies paths under migrations/. Use it before merge to collect forward, rollback, locking, and data-safety evidence.
learn-from-sage
Detection-gap (miss) analysis for Code Review Sage. Learn from shipped fixes, acted-on human comments, and design outcomes to close reviewer blind spots. Inline during review stages a candidate; a human triggers a one-shot AI consolidation into the live ruleset.
github-review-pr
Review GitHub pull requests with detailed, multi-perspective code analysis using parallel subagents. Use this skill whenever the user wants to review a PR, asks for code review on a pull request, mentions "review PR", "check this PR", "look at pull request", or references a PR number or GitHub PR URL. Do NOT use for…
review-export
Export CocoReview reports as markdown, html, or pdf-ready status artifacts. Usage: $review export markdown|html|pdf [report-path].
no-mistakes
Validate committed feature-branch changes through the no-mistakes pipeline: intent, rebase, review, test, docs, lint, push, PR, and CI. Use when the user asks to run no-mistakes, ship safely, validate before pushing, or gate a change before it reaches upstream.
fkteams
A command-line tool and web interface for asking AI models questions, reviewing code, and running multi-agent discussions. A command-line tool is software controlled by typing commands in a terminal.