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-new-runtime-asset/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-new-runtime-asset)<a href="https://agentmods.dev/skills/ayutaz/piper-plus/check-new-runtime-asset"><img src="https://agentmods.dev/badge/skills/ayutaz/piper-plus/check-new-runtime-asset/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/ayutaz/piper-plus/check-new-runtime-asset"><img src="https://agentmods.dev/badge/skills/ayutaz/piper-plus/check-new-runtime-asset.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Agent Snooping · line 98 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
- medium Agent Snooping · line 100 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
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 | $0.00084 | $0.01437 |
| Opus 5 | $0.00042 | $0.00718 |
| Sonnet 5 | $0.00017 | $0.00287 |
| Haiku 4.5 | $0.00008 | $0.00144 |
Grade A, and why
check-new-runtime-asset scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.
新規ランタイムアセット配布チェック
新規 JSON/TOML データファイルを 1 つでも追加した PR で、各ランタイムの配布物
metadata に同期して載っているかを PR 提出前に 確認する。レビュアーが
毎回同じ指摘を出していた配布物欠落 (PR #397 で zh_en_loanword.json が
wheel 漏れ、PR #400 で Android assets DSL コメント、PR #438 で setup.py /
pyproject 分離) を local で潰すための skill。
何をチェックするか
git diff --name-only origin/dev...HEADから 新規追加されたデータ ファイル を検出する (data/dictionaries/、src/python*/g2p/data/、tests/fixtures/、Sources/.../Resources/、android/.../assets/等)- 検出された各ファイルについて、以下 7 箇所の更新有無を grep で確認:
MANIFEST.inまたはpyproject.toml [tool.setuptools.package-data]src/python/g2p/MANIFEST.in(G2P 独立 wheel)Cargo.tomlのincludeまたはfeatures.bundled-dicts- npm
package.jsonのfiles - C#
.csprojの<Content>/<EmbeddedResource> - Android
build.gradle.ktsのassets.srcDirs(asset auto-bundle なら自動) - SPM
Package.swiftの.process("Resources/...")
- 更新漏れがあれば file path と 修正例を提示
実行手順
1. 新規追加されたデータファイルを列挙
git diff --name-only --diff-filter=A origin/dev...HEAD | \
grep -E '\.(json|toml|tsv|txt)$' | \
grep -E '(data/|fixtures/|Resources/|assets/)' || \
echo "新規データファイルなし — このチェックは skip 可"
2. 検出されたファイルごとに 7 箇所の grep を回す
# 例: src/python/g2p/piper_plus_g2p/data/new_dict.json を追加した場合
BASENAME=$(basename src/python/g2p/piper_plus_g2p/data/new_dict.json)
echo "=== MANIFEST.in / pyproject ==="
grep -rn "$BASENAME" MANIFEST.in src/python/g2p/MANIFEST.in src/python_run/MANIFEST.in 2>/dev/null
grep -rn "$BASENAME" pyproject.toml src/python_run/pyproject.toml src/python/g2p/pyproject.toml 2>/dev/null
echo "=== Cargo.toml ==="
grep -rn "$BASENAME" src/rust/*/Cargo.toml src/rust/*/src/*.rs 2>/dev/null
echo "=== npm files ==="
grep -rn "$BASENAME" src/wasm/*/package.json 2>/dev/null
echo "=== C# csproj ==="
grep -rn "$BASENAME" src/csharp/**/*.csproj 2>/dev/null
echo "=== Android assets ==="
grep -rn "$BASENAME" android/**/build.gradle.kts android/**/src/main/assets/ 2>/dev/null
echo "=== SPM Package.swift ==="
grep -rn "$BASENAME" Package.swift Sources/**/Resources/ 2>/dev/null
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.
- 9d ago First seen · 101 lines · 84 tokens per session scan A 979d184b6e8e
check-new-runtime-asset is a skill published in the GitHub repository ayutaz/piper-plus (204 stars, last pushed 7d ago), licensed MIT. It adds 84 tokens to every session and 1,437 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.
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…
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…
single-cell-multi-omics-analysis-scvi
Probabilistic deep learning framework for single-cell multi-omics data analysis. Use this skill when: (1) Analyzing single-cell RNA-seq data with batch correction, (2) Integrating multi-modal data (CITE-seq, ATAC-seq, multi-omics), (3) Performing cell type annotation with scANVI, (4) Spatial transcriptomics…
deep-learning
Use when training or debugging a neural net in PyTorch — the forward/loss/backward/step loop and its silent bugs, mixed precision (AMP), AdamW/LR schedules, DDP/FSDP/ZeRO, checkpoints and seeds. NOT LoRA/QLoRA on a pretrained LLM (that is finetuning), NOT tabular sklearn/XGBoost (that is machine-learning), NOT…
graphsignal-profiler
Set up the Graphsignal Profiler for inference workloads — vLLM, SGLang, PyTorch, and dstack services. Use when the user wants GPU profiling, tracing, or monitoring for inference, asks about graphsignal-run or graphsignal.watch(), or asks about CUPTI / Prometheus / OTLP setup.
atc-model-converter
Complete toolkit for Huawei Ascend NPU model conversion and end-to-end inference adaptation. Workflow 1 auto-discovers input shapes and parameters from user source code. Workflow 2 exports PyTorch models to ONNX. Workflow 3 converts ONNX to .om via ATC with multi-CANN version support. Workflow 4 adapts the user's full…