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/publish-python-release/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/publish-python-release)<a href="https://agentmods.dev/skills/nvidia-nemo/switchyard/publish-python-release"><img src="https://agentmods.dev/badge/skills/nvidia-nemo/switchyard/publish-python-release/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/publish-python-release"><img src="https://agentmods.dev/badge/skills/nvidia-nemo/switchyard/publish-python-release.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 | $0.00055 | $0.00560 |
| Opus 5.5 | $0.00022 | $0.00224 |
| Sonnet 5.5 | $0.00011 | $0.00112 |
| Haiku 4.5 | $0.00006 | $0.00056 |
Grade A, and why
publish-python-release 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 — 57 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Publish The Python Package
Use .github/workflows/publish.yml as the source of truth. The supporting runbook is
docs/internal/release_workflow.md.
Release Paths
| Intent | Trigger | Result |
|---|---|---|
| One temporary wheel | Manual dispatch with build_dev_artifact=true |
Linux x86_64 GitHub artifact, retained for one day |
| Full matrix test | Manual dispatch with build_dev_matrix=true |
sdist and wheel artifacts; no publish |
| Official release | Push vMAJOR.MINOR.PATCH matching pyproject.toml |
Full matrix, PyPI publish, GitHub Release |
Manual builds are artifact-only. Official releases use PyPI Trusted Publishing through the
GitHub environment named pypi; do not add a long-lived PyPI token.
Workflow
- Read the current workflow and
pyproject.toml; do not rely on remembered inputs or versions. - Confirm the requested version and whether the user explicitly authorized creating a tag.
- For workflow changes, run the focused release-helper tests and inspect the workflow diff.
- Dispatch a development build or push the authorized release tag.
- Monitor every matrix job and verify the resulting package from a clean temporary environment.
Example development dispatch:
gh workflow run publish.yml \
-f build_dev_artifact=true \
-f build_dev_matrix=false \
-f dev_version=0.0.1.dev0
Guardrails
- Never create or push a tag unless the user explicitly requested it.
- Never publish a manual development build to PyPI.
- Never reuse a deleted PyPI filename or version; PyPI permanently reserves filenames.
- Keep release versions consistent across the tag,
pyproject.toml, and package metadata. - Verify installation outside the checkout so local imports cannot mask packaging defects.
- Cargo crate publishing is a separate manual workflow. Inspect each crate's
Cargo.toml, dependency publication order, and crates.io ownership before runningcargo publish.
Release-Infrastructure Validation
uv run ruff check scripts/release/set_dev_wheel_version.py tests/test_dev_wheel_versioning.py
uv run pytest tests/test_dev_wheel_versioning.py -v
python scripts/release/set_dev_wheel_version.py 0.0.1.dev0 --print-version
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 · 57 lines · 55 tokens per session scan A 935ac24fe09f
publish-python-release is a skill published in the GitHub repository NVIDIA-NeMo/Switchyard (3,458 stars, last pushed today), licensed Apache-2.0. It adds 55 tokens to every session and 560 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
pypi-release
This skill should be used when releasing tunacode-cli to PyPI. It keeps the existing local release checks, then hands the actual PyPI upload to a GitHub Actions workflow that uses the repository's PYPIAPITOKEN secret.
python-packaging
Create distributable Python packages with proper project structure, setup.py/pyproject.toml, and publishing to PyPI. Use when packaging Python libraries, creating CLI tools, or distributing Python code.
python-format
Formats Python files with ruff format and reports which files changed.
versioning-releases
This skill should be used when the user is choosing a versioning scheme, writing a changelog, preparing a release, configuring Towncrier or python-semantic-release, planning deprecations, managing major version migrations, or setting up version single-source-of-truth. Covers SemVer, CalVer, PEP 440, Keep a Changelog…
plainx-release
Releases plainx packages with version suggestions, changelog generation, and git tagging. Use when releasing a package to PyPI.
python-release
Release engineering for Python projects on uv — static versioning in pyproject.toml exposed via importlib.metadata, building the sdist and wheel with uv build, publishing to PyPI with uv publish via Trusted Publishing (OIDC, no token), tag-triggered GitHub Actions releases, CI running ruff/ty (or pyright)/pytest with…