Borrowing it
Nothing to install: this file belongs to ayutaz/piper-plus. 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/ayutaz/piper-plus/dev/.claude/skills/check-cross-runtime/SKILL.mdgit clone --depth 1 https://github.com/ayutaz/piper-plusWrote 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/ayutaz/piper-plus/check-cross-runtime)<a href="https://agentmods.dev/skills/ayutaz/piper-plus/check-cross-runtime"><img src="https://agentmods.dev/badge/skills/ayutaz/piper-plus/check-cross-runtime.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 5.1 | $0.00100 | $0.05334 |
| Opus 5 | $0.00050 | $0.02667 |
| Sonnet 5 | $0.00020 | $0.01067 |
| Haiku 4.5 | $0.00010 | $0.00533 |
Grade A, and why
check-cross-runtime 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 7d 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 — 348 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Python 変更 → N ランタイム追随漏れチェック
src/python_run/piper_plus/*.py、 src/python/piper_train/*.py、 または
src/python/g2p/piper_plus_g2p/*.py を変更した PR で、 他 7 ランタイム
(C# / Rust × 2 crate / Go / JS-WASM / C API / iOS SPM / Kotlin-Android /
Swift G2P) + 2 docker image (python-inference / webui) が 同じ振る舞いに
追随しているか を PR 提出前に確認する。
なぜこの skill が必要か (既存 2 skill との関係)
| skill | スコープ | 補完範囲 |
|---|---|---|
/check-runtime-parity |
ONNX グラフ I/O (入出力名・形状・dtype) の変更 | 推論バックエンドだけ |
/check-new-runtime-asset |
新規データファイル (JSON/TOML/TSV) の 7 箇所 metadata 配布 | wheel/sdist 同梱漏れだけ |
/check-cross-runtime (本 skill) |
それ以外の Python 変更 = phonemizer ロジック / config field / CLI flag / data file 形式変更 / API 変更 / docker recipe | 既存 2 skill の網からこぼれる広い領域 |
3 skill を組み合わせると、 Python canonical の変更が 7 ランタイム + 2 docker 全部に伝播しているかを 1 PR ごとにチェックできる。
過去事故サマリ
| PR | Python 修正内容 | 追随漏れ | 検出方法 |
|---|---|---|---|
| #391 | speaker_embedding 形状修正 | 5 ランタイム (Rust / Go / C# / C++ / WASM) が古い形状のまま | PR #443 で偶然発見 (silent regression) |
| #443 | MB-iSTFT speaker_embedding 未対応の修正 | 4 runtime (Rust / Go / C# / WASM) + 2 docker image (python-inference / webui) で同じバグ | 手動レビューでようやく発見 |
| #384 | ZH-EN loanword 辞書 schema 拡張 | Rust / Go / C# / WASM / C++ で旧 schema のままパース失敗 | CI gate を後付けで作成 |
共通パターン:
- Python で 1 関数 / 1 schema を 「サクッと」 修正
- ローカル
pytestは green、 CI も Python 観点だけ通る - レビュアーも Python diff しか見ない
- 別 PR / リリース後ユーザー報告で 「他ランタイム壊れている」 が判明
この skill は PR 提出前 に local で同じ修正が他ランタイムにも入っているか チェックリスト化する。
スコープ判定 (何を見るか)
Canonical Python の 3 source of truth
| カテゴリ | パス | 対応する他ランタイム |
|---|---|---|
| A. ランタイム推論 | src/python_run/piper_plus/*.py (voice.py, http_server.py, text_splitter.py, timing.py, model_manager.py) |
C# / Rust core / Go / WASM / C API / iOS SPM |
| B. G2P / phonemizer | src/python/g2p/piper_plus_g2p/*.py (japanese.py, chinese.py, multilingual.py, ssml.py 等) |
Rust piper-plus-g2p / Go phonemize / C# Phonemize / WASM g2p / C++ *_phonemize.cpp / Kotlin / Swift G2P |
| C. モデルエクスポート / 学習 | src/python/piper_train/*.py (export_onnx.py / vits/models.py / infer_onnx.py) |
ONNX I/O 変更なら /check-runtime-parity を使う。 それ以外の周辺ロジック (chunking / scaling / sentence split 等) が本 skill 対象 |
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.
- 7d ago First seen · 348 lines · 100 tokens per session scan A 540707ba406c
check-cross-runtime is a skill published in the GitHub repository ayutaz/piper-plus (204 stars, last pushed 5d ago), licensed MIT. It adds 100 tokens to every session and 5,334 once invoked, about $0.0005 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
physicsnemo-shard-tensor
Official NVIDIA-authored guidance for PhysicsNeMo ShardTensor domain parallelism — integrate domain parallelism into training/inference scripts (new or existing) with DDP or FSDP2, write and register shard patches to enable new layers/ops, and bootstrap multi-GPU correctness tests. Use when working with ShardTensor…
github
GitHub operations via gh CLI: issues, PRs, CI runs, code review, API queries. Use when: (1) checking PR status or CI, (2) creating/commenting on issues, (3) listing/filtering PRs or issues, (4) viewing run logs. NOT for: complex web UI interactions requiring manual browser flows (use browser tooling when available)…
physicsnemo-discover
Official NVIDIA-authored guidance for navigating PhysicsNeMo — pick the model, datapipe, or example for a SciML/AI4Science task (surrogates, forecasting, downscaling, physics-informed, inverse, generative). Points at existing files via live repo search; never writes code. Do NOT use for installation or environment…
meta-codereview-current-diff
Read the current uncommitted diff, run three independent reviewers (safety + tests-coverage + style) in parallel, then arbitrate a single BLOCK / BLOCKWITHOVERRIDE / PASSWITHNOTES verdict. Use before commit when you want a multi-perspective second-opinion instead of a single-reviewer agent loop.
pr-babysitter
Use when monitoring GitHub pull request CI, diagnosing failed checks, rebasing branches onto github/main, applying narrowly scoped fixes, and updating PRs until their latest checks are green or a human blocker is identified.
submit-github-pr
Use when publishing an existing TensorRT-Model-Connect change as a GitHub pull request. Verifies authenticated repository access, branch and diff scope, validation evidence, commit identity, reviewer-facing text, exact pushed head, and the created draft PR without merging it.