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-get-startedgit 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-get-started)<a href="https://agentmods.dev/skills/nvidia/nemo-relay/nemo-relay-get-started"><img src="https://agentmods.dev/badge/skills/nvidia/nemo-relay/nemo-relay-get-started/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/nemo-relay-get-started"><img src="https://agentmods.dev/badge/skills/nvidia/nemo-relay/nemo-relay-get-started.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 Excessive Agency · line 40 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00047 | $0.01041 |
| Opus 5.5 | $0.00019 | $0.00416 |
| Sonnet 5.5 | $0.00009 | $0.00208 |
| Haiku 4.5 | $0.00005 | $0.00104 |
Grade A, and why
nemo-relay-get-started 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 15d 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 — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Get Started With NeMo Relay
Help the user choose and follow the maintained quick-start guide that fits their existing runtime, framework, plugin, or application. The guide owns the implementation; this skill owns selection, continuity, and evidence.
Select The Guide
Read the current quick-start index. Use the user's stated goal and existing environment to find the smallest applicable path. Preserve a target established in conversation or installation.
When the boundary is unclear, ask one concise question before choosing. Do not infer that every generic "try Relay" request means a coding-agent demo, or introduce a framework just to demonstrate Relay.
Use these references only for target-specific routing and cautions:
| Established boundary | Reference |
|---|---|
| Local coding agent or CLI | CLI Trial |
| Native agent runtime or managed plugin | Agent Runtime Trial |
| Maintained framework integration | Framework Trial |
| Switchyard routing | Switchyard Trial |
| Application-owned language calls | Language Trial |
Follow The Current Guide
Read the selected guide before proposing commands or configuration, including its prerequisites, sample files, run instructions, verification, and limitations. Use documentation compatible with the installed stable release. The current published guide is the normal source; use an explicitly requested pending PR or other supplied revision as such, without treating it as published support. Resolve the documentation version instead of assuming an unversioned URL is current. When rendered documentation is inaccessible or omits the selected path, use the official source at the matching release tag, or the development checkout for an explicitly requested development preview. A failed HTTP request alone does not prove that a guide was removed; check its index and source.
What ships with it
10 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.
- BENCHMARK.md 11 KB
- evals/evals.json 19 KB
- references/agent-runtimes-try-now.md 1.8 KB
- references/built-in-integrations-try-now.md 1.4 KB
- references/cli-try-now.md 1.8 KB
- references/first-value.md 2.6 KB
- references/manual-language-try-now.md 1.5 KB
- references/switchyard-try-now.md 1.7 KB
- skill-card.md 4.8 KB
- skill.oms.sig 5.9 KB
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.
- 15d ago Changed · -40 lines · -11 tokens per session 7a633bdd0bf9
- 2mo ago First seen · 140 lines · 58 tokens per session scan A 9634fc9783e0
nemo-relay-get-started is a skill published in the GitHub repository NVIDIA/NeMo-Relay (234 stars, last pushed yesterday), licensed Apache-2.0. It adds 47 tokens to every session and 1,041 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.
nemo-relay-get-started compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| nemo-relay-get-startedNVIDIA/NeMo-Relay | Skill | 234 | yesterday | Apache-2.0 | A | 47 | Claude Code, Codex |
| foundry-config-setupmicrosoft/agent-framework | Skill | 15k | yesterday | MIT | A | 65 | Claude Code, Codex |
| rowboat-spacesrowboatlabs/rowboat | Skill | 18k | yesterday | Apache-2.0 | A | 60 | Claude Code, Codex |
| create-tech-designhumanlayer/humanlayer | Skill | 13k | yesterday | Apache-2.0 | A | 16 | Claude Code, Codex |
| deploy-docker-composeomnigent-ai/omnigent | Skill | 11k | yesterday | Apache-2.0 | A | 84 | Claude Code, Codex |
| haikuagno-agi/agno | Skill | 43k | yesterday | Apache-2.0 | A | 0 | Claude Code, Codex |
| fastapi-router-pymicrosoft/skills | Skill | 3.2k | yesterday | MIT | A | 46 | Claude Code |