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.
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.
npx skills add NVIDIA/NeMo-Relay --skill nemo-relay-installgit 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/nemo-relay-install)<a href="https://agentmods.dev/skills/nvidia/nemo-relay/nemo-relay-install"><img src="https://agentmods.dev/badge/skills/nvidia/nemo-relay/nemo-relay-install.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00048 | $0.01478 |
| Opus 5 | $0.00024 | $0.00739 |
| Sonnet 5 | $0.00010 | $0.00296 |
| Haiku 4.5 | $0.00005 | $0.00148 |
Grade A, and why
nemo-relay-install 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 7d 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 — 146 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Install NeMo Relay
Choose the package or executable from the user's desired outcome. Stop after
installation and basic availability checks. Do not configure runtime behavior,
write plugins.toml, create scopes, register middleware, or build a first app
example from this skill.
Keep installation separate from first-use instrumentation.
Choose The Install Path
If the user asks to install NeMo Relay but does not identify a target or desired outcome, ask one short clarifying question before giving commands:
Which install path do you want: CLI for coding-agent/local gateway use, language package for a Python/Node.js/Rust app, or framework integration for LangChain, LangGraph, Deep Agents, OpenClaw, or built-in Hermes Agent support?
Do not ask when the user already names a CLI, language, framework, harness,
source checkout, or target project file such as pyproject.toml, package.json,
or Cargo.toml.
Use this order from least to most application-specific:
- CLI for a generic "try Relay" request, a temporary coding-agent run, the local gateway, or explicit persistent host-plugin setup. Read CLI Installation.
- Maintained integration when the user already uses OpenClaw, Hermes, LangChain, LangGraph, or Deep Agents. Read Maintained Integration Installation.
- Language package when a Python, Node.js, or Rust application directly owns its tool or model call sites. Read Language Package Installation.
- Source checkout only for contributors or unpublished changes. Follow the repository development guide instead of published package commands.
For "try Relay" requests, default to the CLI and temporary transparent run. Do not make persistent host-plugin installation the default.
Protect Codex Desktop Continuity
Before persistent Codex installation, determine whether the user is operating
from Codex Desktop. Persistent nemo-relay install codex changes the active
Codex provider and can make the current or older Desktop threads appear missing
after restart because of an upstream provider-filtering bug. The threads are
not deleted.
What ships with it
8 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.
- 7d ago First seen · 146 lines · 48 tokens per session scan A 3b1cc4213434
nemo-relay-install is a skill published in the GitHub repository NVIDIA/NeMo-Relay (164 stars, last pushed yesterday), licensed Apache-2.0. It adds 48 tokens to every session and 1,478 once invoked, about $0.0002 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
foundry-config-setup
Resolve missing setup caused by a hardcoded Foundry project endpoint or model in a sample. Use when a sample fails because it uses a placeholder/hardcoded projectendpoint (for example "https://your-project.services.ai.azure.com") or a hardcoded model instead of reading them from the environment.
deploy-docker-compose
Run the Omnigent server as a Docker compose stack (server + Postgres) on any Docker host — your laptop, a VPS, EC2 by hand, or as the base layer of any container-platform deploy. Invoke when the user wants to build the image, bring up the compose stack, debug the stack on a host they already have, or extend the stack…
haiku
When writing a haiku for this bot, follow these conventions.
fastapi-router-py
Create FastAPI routers with CRUD operations, authentication dependencies, and proper response models. Use when building REST API endpoints, creating new routes, implementing CRUD operations, or adding authenticated endpoints in FastAPI applications.
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.
mochi-remind
Handle due reminders — notify the user with natural language and mark them done.