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-optimizer/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-optimizer)<a href="https://agentmods.dev/skills/nvidia/nemo-relay/maintain-optimizer"><img src="https://agentmods.dev/badge/skills/nvidia/nemo-relay/maintain-optimizer/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-optimizer"><img src="https://agentmods.dev/badge/skills/nvidia/nemo-relay/maintain-optimizer.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 | $0.00464 |
| Opus 5.5 | $0.00016 | $0.00186 |
| Sonnet 5.5 | $0.00008 | $0.00093 |
| Haiku 4.5 | $0.00004 | $0.00046 |
Grade A, and why
maintain-optimizer 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.
What it actually says
Maintain Adaptive Surfaces
Use this skill when changing adaptive config schema, built-in sections, shared plugin lifecycle, plugin registration, or binding-native helper APIs.
Public Boundary
The stable adaptive boundary is the config document plus the shared plugin lifecycle:
- Config types and policies
- Built-in adaptive section helpers
- Plugin registration and composition
- Plugin lifecycle
- Reports and diagnostics
There is no separate public adaptive runtime handle.
See docs/configure-plugins/adaptive/configuration.mdx and
docs/configure-plugins/about.mdx.
Keep In Sync
crates/adaptive- Shared plugin behavior in core and bindings
- Python adaptive/plugin wrappers in
python/nemo_relay/adaptive.pyandpython/nemo_relay/plugin.py - Go adaptive helpers under
go/nemo_relay/adaptiveplus shared plugin helpers ingo/nemo_relay - Node.js adaptive helpers and plugin wrappers
- Docs and examples that show canonical config shapes
Checklist
- Dynamic config shape still matches the documented canonical model
- Typed helper constructors still map cleanly to the same config document
- Plugin lifecycle is consistent across languages
- Plugin context surfaces remain aligned
- Validation/report behavior remains documented and tested
- Any new component kind has docs, examples, and binding coverage
Validation
- Run adaptive-focused Rust tests
- Run binding tests for every changed adaptive or plugin surface
- Update adaptive docs and any examples in the same branch
References
docs/configure-plugins/adaptive/configuration.mdxdocs/configure-plugins/adaptive/about.mdxdocs/configure-plugins/adaptive/acg.mdxdocs/configure-plugins/adaptive/adaptive-hints.mdxdocs/build-plugins/about.mdxdocs/build-plugins/configuration-and-validation.mdx
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 · -9 lines · +10 tokens per session 9eb53849bff6
- 1mo ago First seen · 73 lines · 31 tokens per session scan A 2a8491fa503d
maintain-optimizer is a skill published in the GitHub repository NVIDIA/NeMo-Relay (196 stars, last pushed today), licensed Apache-2.0. It adds 41 tokens to every session and 464 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.
verify-omnigent
Drive Omnigent the way a user does and prove a behavior with recorded evidence, using an isolated server, runner, and mock model plus a feature map of every user entry point. Load before reproducing a user-facing bug, before claiming a fix works, or when reviewing whether a change covered every surface (session vs.…
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.