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-community-gardening/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-community-gardening)<a href="https://agentmods.dev/skills/nvidia-nemo/switchyard/switchyard-community-gardening"><img src="https://agentmods.dev/badge/skills/nvidia-nemo/switchyard/switchyard-community-gardening/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-community-gardening"><img src="https://agentmods.dev/badge/skills/nvidia-nemo/switchyard/switchyard-community-gardening.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00057 | $0.01363 |
| Opus 5.5 | $0.00023 | $0.00545 |
| Sonnet 5.5 | $0.00011 | $0.00273 |
| Haiku 4.5 | $0.00006 | $0.00136 |
Grade A, and why
switchyard-community-gardening 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 — 122 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Switchyard Community Gardening
Use live GitHub state to move community contributions forward. Do not store mutable PR lists, contributor identities, or rotation dates in the skill.
Establish The Evidence
- Record the repository, authenticated GitHub user, subject gardener, time window, and current UTC time. Default the subject to the authenticated user unless the request names someone.
- Read
scripts/community_gardener/READMEfor the human-maintained role notes. Do not edit it unless the user explicitly requests a human-authored update. - Load policy only as needed:
CONTRIBUTING.mdfor contributor guidance,SECURITY.mdfor sensitive reports,.github/CODEOWNERSfor ownership, and applicable workflows for CI or merge decisions. - Treat live GitHub as the source of truth. Refresh mutable state before delivery, and report collection failures or blind spots instead of turning a partial response into “no activity.”
- Work read-only unless the user explicitly asks to post, review, approve, close, label, assign, merge, push, or modify a contributor's branch.
Pick Up Daily Work
Use a supplied checkpoint; otherwise inspect the last 24 hours and state that limitation. Start with:
gh auth status
gh api user --jq .login
gh repo view --json nameWithOwner,defaultBranchRef
./scripts/community_gardener/github_last_night.sh 24
The helper includes only currently open, non-draft items. Supplement it with:
- New issues and PRs, including drafts.
- New human comments, inline comments, and submitted reviews.
- New commits and changes to readiness, conflicts, workflow approval, reviews, or CI.
- Work the gardener previously touched or promised to revisit, including items merged or closed.
Without a checkpoint, some historical status changes cannot be reconstructed. Report their current
state instead of guessing. Exclude bots from human responses but retain their checks as evidence.
Check linked work for stacks, replacements, and duplicates. Reconcile synced SYGH issues when
Linear is available; otherwise name that blind spot.
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 · 122 lines · 57 tokens per session scan A 101eaabf5299
switchyard-community-gardening is a skill published in the GitHub repository NVIDIA-NeMo/Switchyard (3,458 stars, last pushed today), licensed Apache-2.0. It adds 57 tokens to every session and 1,363 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 2026-09-12.
Other skills, from other repositories
antfu-issue-triage
Triage open issues and PRs of the current GitHub repo - find already-fixed, duplicate, and spam items, suggest labels, gauge demand from reactions and comments, then present a table of proposed actions and comments for confirmation before touching anything. Use when asked to triage, organize, clean up, or groom issues…
mcore-split-pr
Split a PR into multiple PRs to reduce the number of required CODEOWNERS reviewer groups.
engineer-bot-ops
A workflow for carrying an engineering task from scope through implementation and reviewable delivery. It works with a repository's branch, existing changes, rules, checks, and permissions while separating completed, unverified, and next-step work.
shiplog
Recap of everything shipped since the last run - cross-repo PRs, security fixes, star deltas, and X traction, synthesized into a digest article and a ready-to-post shiplog in your voice.
connect
Choose which wiki this session uses, the team project's pages on the Nimbalyst server or the project's local wiki of files, and connect a repository to its team project. Use at the start of a task before any wiki tool, when a wiki tool returns reponotbound, ambiguousproject, pinmismatch, projectnotaccessible…
llxprt-issue-workflow
Use this skill when asked to address, fix, or work on a GitHub issue in the llxprt-code repository. Covers the complete issue lifecycle - branch setup, gh CLI usage, test-first planning, subagent delegation and review loops, the full verification cycle (including the zai-glm-flash smoke test), open code review (ocr)…