review-language

review-language is a command for Claude Code from ayutaz/piper-plus. It costs 0 tokens per session (2,217 once invoked), scanned A, original, MIT.

A command for reviewing a newly added language in the Piper speech-synthesis project across its Python, Rust, C++, C# and JavaScript code.

In plain words
What is it for?
Checking phoneme rules, preprocessing and inference paths, language registration, generated configuration, and consistency across five platforms.
Why use it?
Adding a language can require matching pronunciation rules, language mappings and shared character codes in several parts of a project.

Command for Claude Code

Install

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.

agentmods
npx agentmods add commands/ayutaz/piper-plus/review-language
Clone the repo
git clone --depth 1 https://github.com/ayutaz/piper-plus

Made for: Claude Code.

Wrote 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.

agentmods badge for review-language

README.md
[![agentmods](https://agentmods.dev/badge/commands/ayutaz/piper-plus/review-language.svg)](https://agentmods.dev/commands/ayutaz/piper-plus/review-language)
Your own site
<a href="https://agentmods.dev/commands/ayutaz/piper-plus/review-language"><img src="https://agentmods.dev/badge/commands/ayutaz/piper-plus/review-language.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,217 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00000 $0.02217
Opus 5 $0.00000 $0.01108
Sonnet 5 $0.00000 $0.00443
Haiku 4.5 $0.00000 $0.00222

Measured 5d ago against content hash 29fece1d6f06, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

review-language 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 5d 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.

.claude/commands/review-language.md · 180 lines

How it starts

The opening of the file, as written. The whole thing — 180 lines — stays where its author put it; the contents beside it link to each section on GitHub.

新言語実装レビュー

piper-plus の新言語実装を徹底的にレビューするスキルです。引数 $ARGUMENTS に言語コード (例: sv, de) を指定してください。

前提条件

  • Python テストは uv run python -m pytest で実行
  • 10エージェント並列でレビュー実施
  • 全プラットフォーム (Python/Rust/C++/C#/JS) を検証

レビュー手順

Step 1: 10エージェント並列レビュー

以下の10エージェントを 並列 で起動してレビューを実施:

Agent 1: Python G2P 品質
  • src/python/piper_train/phonemize/$ARGUMENTS.py を読み、全G2Pルールの正確性を検証
  • 代表的な10単語のスポットチェック (言語固有の音韻規則に基づく)
  • 例外語リストの完全性確認
  • IPA シンボルの正確性 (ɡ≠g, ɧ≠ɕ 等)
Agent 2: Python 前処理・推論パス
  • src/python/piper_train/preprocess.py--language $ARGUMENTS が動作するか
  • src/python/piper_train/infer_onnx.py — ヘルプテキスト、_detect_dominant_language
  • src/python/piper_train/tools/prepare_multilingual_dataset.py — LANGUAGE_ID_MAP
  • src/python/piper_train/phonemize/registry.py — 登録確認
  • src/python/piper_train/phonemize/multilingual_id_map.py — LANGUAGE_PHONEMES
  • config.json 生成パス (phoneme_id_map, language_id_map, num_languages)
Agent 3: PUA 整合性 (全5プラットフォーム)
  • Python token_mapper.py — FIXED_PUA_MAPPING、_PUA_START
  • Rust token_map.rs — FIXED_PUA_MAP、PUA カウントテスト
  • C++ ソース — PUA 定数定義
  • C# OpenJTalkToPiperMapping.cs — TokenToChar エントリ
  • 全プラットフォームで同一コードポイントを使用しているか
  • 既存言語との PUA 衝突がないか
Agent 4: Rust 実装完全性
  • src/rust/piper-core/src/phonemize/$ARGUMENTS.rs — 全ルール実装
  • src/rust/piper-core/src/phonemize/mod.rs — module export
  • src/rust/piper-core/src/voice.rs — ケース処理 + default_latin
  • src/rust/piper-core/src/phonemize/multilingual.rs — 言語検出
  • src/rust/piper-cli/src/main.rs — SUPPORTED_LANGUAGES
  • TODO/FIXME/unimplemented! の有無
Agent 5: C++ 実装完全性
  • src/cpp/$ARGUMENTS_phonemize.cpp/.hpp — 全ルール実装
  • src/cpp/piper.cpp — ディスパッチ + #include
  • src/cpp/language_detector.cpp/.hpp — 言語検出
  • CMakeLists.txt — ビルド設定
  • src/cpp/tests/CMakeLists.txt — テストターゲット
  • ASCII化されたダイアクリティカルマーク (ö→o 等) がないか 要注意
Agent 6: C# 実装完全性
  • G2P エンジン — Python の全ルールが移植されているか
  • Phonemizer ラッパー — IPhonemizer 準拠
  • PUA マッピング — OpenJTalkToPiperMapping
  • UnicodeLanguageDetector — 言語検出
  • CLI Program.cs — ケース処理
  • スタブ実装でないことを確認 (TODO/character-level fallback 検出)

Read the full file on GitHub · 180 lines

Changes

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.

  1. 5d ago First seen · 180 lines · 0 tokens per session scan A 29fece1d6f06

Subscribe to this mod's changes

review-language is a command published in the GitHub repository ayutaz/piper-plus (204 stars, last pushed 3d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,217 tokens. 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.