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 agentmods add skills/nvidia/nemo-relay/test-ffi-surfacenpx skills add NVIDIA/NeMo-Relay --skill test-ffi-surfacegit 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/test-ffi-surface)<a href="https://agentmods.dev/skills/nvidia/nemo-relay/test-ffi-surface"><img src="https://agentmods.dev/badge/skills/nvidia/nemo-relay/test-ffi-surface.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 | $0.00032 | $0.00440 |
| Opus 5 | $0.00016 | $0.00220 |
| Sonnet 5 | $0.00006 | $0.00088 |
| Haiku 4.5 | $0.00003 | $0.00044 |
Grade A, and why
test-ffi-surface 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 4d 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
Build And Test FFI Surface
Companion Guidance
Use karpathy-guidelines alongside this skill for implementation or review
work. Keep changes scoped, surface assumptions, and define focused validation
before editing.
Use this skill when the change is primarily in crates/ffi, the generated
header, or ABI-facing behavior consumed by Go or external native callers.
Default Path
- Rebuild the FFI crate in release mode so the shared library and header stay in sync.
- Run
cargo fmt --allbecause FFI work is Rust work. - Run
just test-rust. - Run
cargo clippy --workspace --all-targets -- -D warnings. - Check the generated header diff when any exported symbol or type changed.
- If downstream consumers changed too, run their binding-specific skills next.
Common Commands
# Rebuild the shared library with the repo wrapper used by FFI consumers
just build-go
# Required Rust validation
cargo fmt --all
just test-rust
cargo test -p nemo-relay-ffi
cargo clippy --workspace --all-targets -- -D warnings
# Review header drift if the FFI surface changed
git diff -- crates/ffi/nemo_relay.h
When To Escalate
- If Go behavior changed, also use
test-go-binding. - If the FFI change reflects shared runtime semantics rather than a pure bridge
change, also use
validate-change.
References
crates/ffi/Cargo.tomlcrates/ffi/build.rscrates/ffi/cbindgen.tomlcrates/ffi/nemo_relay.hjust build-go.pre-commit-config.yamlREADME.mdvalidate-change
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.
- 4d ago First seen · 62 lines · 32 tokens per session scan A 15266adb0042
test-ffi-surface is a skill published in the GitHub repository NVIDIA/NeMo-Relay (132 stars, last pushed 4d ago), licensed Apache-2.0. It adds 32 tokens to every session and 440 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
rust-development
Idiomatisk Rust-utvikling med cargo, clippy, error handling, async/tokio, unsafe og testing.
rust-async-patterns
Master Rust async programming with Tokio, async traits, error handling, and concurrent patterns. Use when the task involves async Rust, Tokio patterns, Rust concurrent programming, async traits, or Rust futures and streams.
rust-patterns
Idiomatic Rust patterns, ownership, error handling, traits, concurrency, and best practices for building safe, performant applications.
tauri2-react-rust
Guides development of cross-platform desktop apps with Tauri 2, TypeScript, React, and Rust. Use when building Tauri apps, implementing IPC, designing Rust backend or TypeScript/React frontend, when researching or cloning a website (open site, snapshot elements), when verifying local dev or built frontend in browser…
vigilante-issue-implementation-on-rust
Implement a GitHub issue end-to-end when Vigilante dispatches work for a Rust repository with Cargo, Clippy, fmt, and security guidance.
aomi-build
Scaffold new Aomi apps and plugins from API docs, OpenAPI/Swagger specs, or SDK references. aomi-build generates production-ready Rust SDK crates (lib.rs, client.rs, tool.rs) with tool schemas, preambles, host-interop flows, and validation — turning a vendor's API surface into AI-agent-callable tools. It covers the…