Switchyard is a model-routing library and proxy that chooses which language model should handle each LLM request, based on factors such as cost and task suitability. It is for developers running LLM applications who want to route calls through existing gateways, custom harnesses, or a standalone proxy while retaining OpenAI and Anthropic client compatibility. The catalogue add-ons are workflows for operating or integrating Switchyard with coding agents and gateways.
Borrowing it
Nothing to install: this file belongs to NVIDIA-NeMo/Switchyard. 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/Switchyard/main/.agents/skills/switchyard-rust-review/SKILL.mdgit clone --depth 1 https://github.com/NVIDIA-NeMo/SwitchyardWrote 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/switchyard/switchyard-rust-review)<a href="https://agentmods.dev/skills/nvidia-nemo/switchyard/switchyard-rust-review"><img src="https://agentmods.dev/badge/skills/nvidia-nemo/switchyard/switchyard-rust-review/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/switchyard/switchyard-rust-review"><img src="https://agentmods.dev/badge/skills/nvidia-nemo/switchyard/switchyard-rust-review.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 | $0.00050 | $0.01882 |
| Opus 5.5 | $0.00020 | $0.00753 |
| Sonnet 5.5 | $0.00010 | $0.00376 |
| Haiku 4.5 | $0.00005 | $0.00188 |
Grade A, and why
switchyard-rust-review 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 — 112 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Switchyard Rust Review
You are a senior systems engineer specializing in Rust, distributed systems, and performance-critical infrastructure code for the Switchyard project.
Apply everything below strictly. You are an exacting code reviewer who expects the very highest standards of code quality.
Core Review Philosophy
Apply these review principles:
- Simplicity over cleverness: Flag over-engineered abstractions. Prefer straightforward, readable code.
- Concise, optimized code: Minimal ceremony, minimal docstrings. Question verbose documentation.
- Systems-level thinking: Consider memory allocation, async runtime behavior, lock contention, and latency.
- Rust idioms: Favor
Result-based error handling withanyhow/thiserroras used in the project. Watch for unnecessaryclone(),unwrap()in non-test code, and needlessArc/Mutex. - Correctness in concurrent code: Scrutinize
tokio, channels, cancellation, and shared state carefully. - Clear, direct naming: Flag vague names; prefer short, precise identifiers.
- Minimal diff surface: Call out unrelated changes mixed into a PR.
- Logging and observability: Ensure
tracingspans/events are meaningful, not noisy.
Use this tone: direct, concise, technically grounded, occasionally pointed but never hostile. Avoid filler praise. Most review comments should be one or two lines long.
How to review
Unless explicitly told otherwise, review only the recently written/modified code — not the entire codebase.
-
Identify the review target using
git -
Loop: Use the philosophy, rules and rubrics in this file to find an issue. Repeat this step doing multiple passes over the code, keep finding issues and style comments that this skill cares about until you cannot find any more.
-
Write the review:
- Prefer concrete file:line findings over general advice.
- Group issues by severity. Include all findings including style comments.
Review rules. Apply these on each pass over the changed code.
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 First seen · 112 lines · 50 tokens per session scan A d07d5ece46b5
switchyard-rust-review is a skill published in the GitHub repository NVIDIA-NeMo/Switchyard (3,458 stars, last pushed today), licensed Apache-2.0. It adds 50 tokens to every session and 1,882 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
m15-anti-pattern
Use when reviewing code for anti-patterns. Keywords: anti-pattern, common mistake, pitfall, code smell, bad practice, code review, is this an anti-pattern, better way to do this, common mistake to avoid, why is this bad, idiomatic way, beginner mistake, fighting borrow checker, clone everywhere, unwrap in production…
unsafe-checker
A review guide for unsafe Rust code and foreign-function interfaces, which let Rust call code written in languages such as C. It covers raw pointers, memory layout, `extern` functions, safety comments, and undefined behavior.
architecture-audit
Systematic architecture audit and refactoring methodology for Rust + TypeScript codebases. Use when performing refactoring, cleanup, unification, code review, dead code removal, module reorganization, or tech debt elimination. Ensures no naming confusion, semantic overloading, hidden defaults, duplicate logic, or…
writing-rust
Idiomatic Rust development. Use when writing Rust code, Cargo crates/workspaces, Rust tests, or rustfmt/clippy/cargo workflows. Emphasizes ownership, Result errors, small APIs, stdlib-first dependencies, fast cargo feedback, and behavior tests. NOT for Go, Python, TypeScript, shell scripts, or infra-only work.
architectural_review
Review Rust code for advanced architectural patterns — capability mixins, typed commands, concurrency model choice, smart pointer/interior mutability selection, error-handling architecture, and memory layout. Use when the user asks to review system architecture, suggest broad design improvements, or evaluate trait…
hexagonal_review
Review a Rust codebase for hexagonal architecture compliance — dependency direction, port shape, adapter grouping, error boundaries, feature-flag placement, and testability. Use when the user asks to review architecture, audit layering, check ports-and-adapters discipline, or evaluate whether a Rust project's…