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/maintain-observability/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/maintain-observability)<a href="https://agentmods.dev/skills/nvidia/nemo-relay/maintain-observability"><img src="https://agentmods.dev/badge/skills/nvidia/nemo-relay/maintain-observability/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/maintain-observability"><img src="https://agentmods.dev/badge/skills/nvidia/nemo-relay/maintain-observability.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 | $0.00041 | $0.00764 |
| 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
maintain-observability 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 — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Maintain Observability Surfaces
Use this skill when changing event fields, exporter behavior, subscriber config,
or binding parity for ATIF or the full, gen_ai, and openinference
OpenTelemetry projections.
Surfaces To Keep In Sync
- Core event model and emitted fields
crates/core/src/observability/atif.rscrates/core/src/observability/otel.rscrates/core/src/observability/openinference.rs- FFI and binding-native wrappers where the config or lifecycle is exposed
- Python, Go, and Node.js config objects and subscriber/exporter methods
- Observability config version 3, where one
opentelemetrysection contains typed endpoints and OpenInference has no standalone public surface - Docs under
docs/about-nemo-relay/concepts/subscribers.mdxanddocs/configure-plugins/observability/
Design Checklist
- Is this an event-model change, exporter-config change, or lifecycle change?
- Do all bindings expose the same logical knobs and semantics?
- Does every OpenTelemetry endpoint require a type and nonblank destination?
- Does each endpoint resolve
header_envvalues at activation and reject missing, blank, or duplicate headers? - Do layered ATOF sink, ATIF storage, and OpenTelemetry endpoint lists concatenate with higher-precedence entries first?
- Are OpenTelemetry and OpenInference dependencies unconditional rather than Cargo feature-gated?
- Does
gen_aiavoidnemo_relay.*, project sanitized LLM instructions and messages into the standard content attributes, and emit minimal spans for scopes without GenAI semantics so their parentage is preserved? - Does
enable_full_payloadspreserve complete sanitized LLM request input and annotations while leaving credential removal and sanitizers active? - Does Relay derive compliant trace and span IDs consistently across typed OpenTelemetry endpoints while preserving lifecycle parentage?
- Are mark events, start/end events, and orphan cases still handled correctly?
- Does a sanitized tool result annotation remain opaque under
category_profile.tool_result_annotation, ATIF observation-resultextra.tool_result_annotation, and the singlenemo_relay.tool.result.annotationattribute infullandopeninference, whilegen_aiomits it? - Do examples and docs use each exporter's documented flush/deregister order before shutdown?
- Are span or trajectory fields still derived from the intended event data?
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 · -7 lines · +18 tokens per session a5892945d834
- 1mo ago First seen · 79 lines · 23 tokens per session scan A f9adfb3d613e
maintain-observability is a skill published in the GitHub repository NVIDIA/NeMo-Relay (212 stars, last pushed today), licensed Apache-2.0. It adds 41 tokens to every session and 764 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
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.
rowboat-spaces
How to work as a member of Rowboat Spaces, the team chat where people and agents work together. Load it once per session, before acting on any request that reaches you from Rowboat; it covers your setup, mentions and hand-offs, the tools, and files.
create-tech-design
Only use when the user explicitly invokes this skill by name.
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.