check-runtime-parity

check-runtime-parity is a skill for Claude Code, Codex from ayutaz/piper-plus. It costs 78 tokens per session (1,532 once invoked), scanned A, original, MIT.

A pull-request check for changes to the canonical Python inference path, verifying that matching inference code in five other runtimes was updated too. Inference is the part of a system that produces output from a model.

In plain words
What is it for?
Use it before submitting changes to the Python model export or inference definitions. It compares the related inference paths across all six listed runtimes.
Why use it?
It catches cases where Python accepts a changed model input or output shape but Rust, Go, C#, C++, or WebAssembly still expects the old one.

Skill for Claude CodeCodex

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 skills/ayutaz/piper-plus/check-runtime-parity
Any agent
npx skills add ayutaz/piper-plus --skill check-runtime-parity
Clone the repo
git clone --depth 1 https://github.com/ayutaz/piper-plus

Made for: Claude Code, Codex.

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 check-runtime-parity

README.md
[![agentmods](https://agentmods.dev/badge/skills/ayutaz/piper-plus/check-runtime-parity.svg)](https://agentmods.dev/skills/ayutaz/piper-plus/check-runtime-parity)
Your own site
<a href="https://agentmods.dev/skills/ayutaz/piper-plus/check-runtime-parity"><img src="https://agentmods.dev/badge/skills/ayutaz/piper-plus/check-runtime-parity.svg" alt="Measured on agentmods" height="20"></a>
Per session 78 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,532 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 5.1 $0.00078 $0.01532
Opus 5 $0.00039 $0.00766
Sonnet 5 $0.00016 $0.00306
Haiku 4.5 $0.00008 $0.00153

Measured 6d ago against content hash 262e28f19092, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

check-runtime-parity 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 6d 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/skills/check-runtime-parity/SKILL.md · 118 lines

How it starts

The opening of the file, as written. The whole thing — 118 lines — stays where its author put it; the contents beside it link to each section on GitHub.

ランタイム推論 parity チェック

src/python/piper_train/export_onnx.pysrc/python/piper_train/vits/models.pyVitsModel.infer (ONNX グラフ入出力定義) を変更した PR で、他 5 ランタイムの inference path も同じ変更を反映しているかを PR 提出前に 確認する。

何をチェックするか

PR #391 → PR #443 の事故パターン:

  • PR #391 は Python ランタイムだけ speaker_embedding 形状を修正
  • 他 5 ランタイム (Rust / Go / C# / C++ / WASM 推論) は古い形状のまま放置
  • PR #443 で気付くまで silent regression 状態

このパターンを検出するため、カノニカルファイル が触られている PR で 他ランタイムの inference path も同 PR で触れているかを確認する:

Canonical (Python) 対応する他ランタイム file
src/python/piper_train/export_onnx.py (ONNX export 自体は Python 専用、ただし出力スキーマを変える場合は下記の loader も更新必要)
src/python/piper_train/vits/models.py:VitsModel.infer src/python_run/piper_plus/voice.py (Python runtime)
ONNX グラフ入出力名 (speaker_embedding / prosody_features / language_id) src/rust/piper-core/src/engine.rs (Rust)
同上 src/go/piperplus/synth.go (Go)
同上 src/csharp/PiperPlus.Core/Inference/PiperSession.cs (C#)
同上 src/cpp/piper_plus.cpp (C++)
同上 src/wasm/openjtalk-web/src/index.js または piper-wasm (WASM)

実行手順

1. canonical ファイルが触られているか確認

CANONICAL_TOUCHED=$(git diff --name-only origin/dev...HEAD | \
  grep -E '^(src/python/piper_train/(export_onnx|vits/models)\.py)$')

if [ -z "$CANONICAL_TOUCHED" ]; then
  echo "canonical inference file は変更されていない — このチェックは skip 可"
  exit 0
fi

echo "Canonical 変更検出: $CANONICAL_TOUCHED"

2. 他 6 ランタイムの inference path も触られているか確認

RUNTIME_FILES=(
  "src/python_run/piper_plus/voice.py"
  "src/rust/piper-core/src/engine.rs"
  "src/go/piperplus/synth.go"
  "src/csharp/PiperPlus.Core/Inference/PiperSession.cs"
  "src/cpp/piper_plus.cpp"
  "src/wasm/openjtalk-web/src/index.js"
)

echo "=== 他ランタイム inference path の touch 状況 ==="
for f in "${RUNTIME_FILES[@]}"; do
  if git diff --name-only origin/dev...HEAD | grep -q "^${f}$"; then
    echo "  TOUCHED  $f"
  else
    echo "  UNTOUCHED $f  ← 追随必要かもしれない"
  fi
done

Read the full file on GitHub · 118 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. 6d ago First seen · 118 lines · 78 tokens per session scan A 262e28f19092

Subscribe to this mod's changes

check-runtime-parity is a skill published in the GitHub repository ayutaz/piper-plus (204 stars, last pushed 3d ago), licensed MIT. It adds 78 tokens to every session and 1,532 once invoked, about $0.0004 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.

Related

Other skills, from other repositories

model-integration

Use when adding a new model or pipeline to diffusers, setting up file structure for a new model, converting a pipeline to modular format, or converting weights for a new version of an already-supported model.

huggingface/diffusers · 45 tokens

custom-blocks

Use when the user has written (or wants to write) a ModularPipelineBlocks subclass in a local Python file and needs to package it into a Hub-uploadable directory. Covers the workflow from a single block.py file to a published custom-block repo that consumers can load via ModularPipeline.frompretrained( …

huggingface/diffusers · 79 tokens

diffusers-cli

Use when the user wants to run a diffusers pipeline from a terminal (one-off generation, batch jobs, smoke-testing a new model), run on HF Sandbox hardware via --remote, introspect a pipeline's input schema before calling it, or attach a LoRA at inference time. Prefer this over writing ad-hoc Python scripts for…

huggingface/diffusers · 75 tokens

self-review

Use before opening a PR, or whenever asked to self-review a diffusers contribution. Applies the same rubric as the @claude CI (checks the diff against references/review-rules.md, traces call paths for dead code). Reports findings grouped by severity, flagging what to fix before submitting (blocking issues + dead code)…

huggingface/diffusers · 88 tokens

hf-release-notes

Generate Hugging Face Hub (huggingfacehub) release notes from cached PR JSON files. Use when asked to draft release notes from PR files.

huggingface/huggingface_hub · 36 tokens

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…

NVIDIA/physicsnemo · 152 tokens