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-rust-corenpx skills add NVIDIA/NeMo-Relay --skill test-rust-coregit clone --depth 1 https://github.com/NVIDIA/NeMo-RelayWhat 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 | $0.00050 | $0.00634 |
| Opus 5 | $0.00025 | $0.00317 |
| Sonnet 5 | $0.00010 | $0.00127 |
| Haiku 4.5 | $0.00005 | $0.00063 |
Grade A, and why
test-rust-core 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 2d 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 — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Build And Test Rust Core
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 a change is primarily in crates/core, crates/adaptive,
dynamic plugin Rust crates, or shared Rust runtime semantics.
Default Path
- Run
cargo fmt --all. - Run
just test-rust. - Run
cargo clippy --workspace --all-targets -- -D warnings. - Because this skill covers
crates/core,crates/adaptive, or shared runtime semantics, expand to the full binding matrix withvalidate-change.
Use narrower crate tests as a local debug loop, not as the final validation story for a Rust change.
Common Commands
# Shared-runtime build/test wrapper
just test-rust
# Required Rust format pass
cargo fmt --all
# Required Rust lint pass
cargo clippy --workspace --all-targets -- -D warnings
# Core runtime only
cargo test -p nemo-relay
# Adaptive crate when touched
cargo test -p nemo-relay-adaptive
# Dynamic plugin crates when touched
just build-test-plugin-fixtures
cargo test -p nemo-relay-types
cargo test -p nemo-relay-plugin
cargo test -p nemo-relay-worker-proto
cargo test -p nemo-relay-worker
cargo test -p nemo-relay --features worker-grpc --test native_plugin_integration --test worker_plugin_integration
# Compile sweep
just build-rust
# Shared-semantics or broad runtime changes
just ci=true test-rust
When To Escalate
- If a public API, event shape, middleware behavior, plugin semantics, or any
crates/core/crates/adaptivebehavior changed, also usevalidate-change. - If native dynamic plugins, gRPC workers,
nemo-relay-plugin,nemo-relay-worker,nemo-relay-worker-proto, ornemo-relay-typeschanged, also usemaintain-dynamic-plugins. - If the change is isolated to one binding wrapper on top of unchanged Rust semantics, prefer that binding's build/test skill instead.
References
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.
- 2d ago First seen · 84 lines · 50 tokens per session scan A b88629360a5a
test-rust-core is a skill published in the GitHub repository NVIDIA/NeMo-Relay (132 stars, last pushed 3d ago), licensed Apache-2.0. It adds 50 tokens to every session and 634 once invoked, about $0.0003 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
python-testing
Guidelines for writing and running tests in the Agent Framework Python codebase. Use this when creating, modifying, or running tests.
testing-python
Write and evaluate effective Python tests using pytest. Use when writing tests, reviewing test code, debugging test failures, or improving test coverage. Covers test design, fixtures, parameterization, mocking, and async testing.
python-testing
Select and run Python SDK verification with nox, Makefile targets, Ruff, mypy, pytest markers, sanity tests, type inference checks, and build checks. Use when adding Python tests, diagnosing Python CI, or validating Python SDK/provider changes. Do not use for TypeScript-only checks.
writing-tests
How to write a Kiro Crew backend test that has NO side effects and does not flake. Use when adding, editing, reviewing, or debugging a pytest test in the Kiro Crew source repo: which conftest is under your file, what leaks (temp dirs, the real data home, /.kiro, cron, threads, child processes), how to tell which of…
test-writer
How to write pytest tests for modules in this workspace. Load whenever you are about to write or extend tests.
rust-unit-tests
Write, improve, and run Rust unit tests in the warp Rust codebase.