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-testing-ci/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-testing-ci)<a href="https://agentmods.dev/skills/nvidia-nemo/switchyard/switchyard-testing-ci"><img src="https://agentmods.dev/badge/skills/nvidia-nemo/switchyard/switchyard-testing-ci/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-testing-ci"><img src="https://agentmods.dev/badge/skills/nvidia-nemo/switchyard/switchyard-testing-ci.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 79 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00049 | $0.00672 |
| Opus 5.5 | $0.00020 | $0.00269 |
| Sonnet 5.5 | $0.00010 | $0.00134 |
| Haiku 4.5 | $0.00005 | $0.00067 |
Grade A, and why
switchyard-testing-ci 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 — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Switchyard Testing And CI
Read .github/workflows/ci.yml before claiming local CI equivalence. Select tests from the current
diff and symbol references rather than a static subsystem inventory.
Validation Matrix
| Change | Minimum trustworthy validation |
|---|---|
| Markdown or skill Markdown only | Parse skill frontmatter when applicable; git diff --check |
| Python implementation | Focused pytest, uv run ruff check ., uv run mypy switchyard |
| Broad Python or public API | Hermetic full pytest plus lint and mypy |
| One Rust crate | cargo fmt --all --check, workspace clippy, focused crate tests |
| Shared Rust/API/FFI | Rust workspace tests plus affected Python tests |
| Packaging, extras, top-level imports | The slim-install smoke commands from the current CI workflow |
| Live provider behavior | Focused integration test only after explicit authorization |
Standard Gates
Python pre-PR gate:
uv run ruff check .
uv run mypy switchyard
env -u OPENROUTER_API_KEY -u NVIDIA_API_KEY -u OPENAI_API_KEY \
-u ANTHROPIC_API_KEY uv run pytest tests/ -v -m "not integration"
Rust workspace gate:
cargo fmt --all --check
cargo clippy --workspace --all-targets -- -D warnings
cargo test --workspace
Use -o addopts= when the repository's pytest defaults would stop failure collection too early.
Run focused tests first, then broaden only when the changed contract or shared ownership warrants it.
Live Tests
Integration tests can spend money, require credentials, and contact real services. Never run them
as an automatic pre-PR step. Provision NVIDIA_API_KEY through the environment or a secret manager
before running the user-authorized path, and state which provider was called:
uv run pytest tests/e2e/<focused_test>.py \
-v -m integration -o addopts=
Skill Validation
Each retained skill must have YAML frontmatter with name and description:
uv run python - <<'PY'
from pathlib import Path
import yaml
for path in Path(".agents/skills").glob("*/SKILL.md"):
parts = path.read_text().split("---", 2)
data = yaml.safe_load(parts[1]) if len(parts) == 3 else None
if not isinstance(data, dict) or not data.get("name") or not data.get("description"):
raise SystemExit(f"{path}: missing name or description")
print("skill frontmatter is valid")
PY
git diff --check
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 · 81 lines · 49 tokens per session scan A 0f31639b1ec7
switchyard-testing-ci is a skill published in the GitHub repository NVIDIA-NeMo/Switchyard (3,458 stars, last pushed today), licensed Apache-2.0. It adds 49 tokens to every session and 672 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
Verification & Quality Assurance
Comprehensive truth scoring, code quality verification, and automatic rollback system with 0.95 accuracy threshold for ensuring high-quality agent outputs and codebase reliability.
quality-scan
Run a scoped, read-only quality scan and report exact-candidate evidence, failures and frozen debt. Use for an ad-hoc gate sweep or release preparation; a static scan is not full release acceptance.
e2e-testing
Use when reviewing CI coverage, automated checks, or test strategy related to Implement end-to-end testing. Focus on whether the rule is continuously verified, not just documented.
mirrord-prev-env
Help users create and manage mirrord preview environments — running a modified service as an isolated pod in a shared Kubernetes cluster, scoped by an environment key and HTTP/queue traffic filtering, so teams can validate and review changes against real traffic without affecting live services. Use when a developer…
test-setup
Scaffold the test framework and CI — tests/ directory, engine test runner, GitHub Actions workflow. Once, before the first sprint.
ci
Configure Ginkgo for continuous integration — the recommended CLI flag set and the rationale for each flag (-r -p --randomize-all --randomize-suites --fail-on-pending --fail-on-empty --keep-going --cover --race --trace --json-report --timeout --poll-progress-after/-interval), invoking via go run to pin the CLI to…