piper-plus: Skill for Claude Code

.claude/skills/bump-deps/SKILL.md

bump-deps is a skill for Claude Code from ayutaz/piper-plus. It costs 101 tokens per session (1,752 once invoked), scanned A, original, MIT.

A helper for updating selected dependencies that are repeated across several project files. A dependency is an external library or tool that the project relies on.

In plain words
What is it for?
Use it to update ONNX Runtime, openjtalk, ruff, or all supported dependencies, check their existing version consistency, and produce or apply the required edits.
Why use it?
It shows where a new version must be applied and helps prevent the main version and its copies from drifting apart. It previews changes by default and applies them only with --apply.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: positional $N argument.

This is ayutaz/piper-plus's own configuration. It tells Claude Code how to work on piper-plus itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything piper-plus configures →

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is uv run python scripts/check_ort_versions.py --verbose 2>&1 | head -30.

Reuse

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.

Copy the file
curl -O https://raw.githubusercontent.com/ayutaz/piper-plus/dev/.claude/skills/bump-deps/SKILL.md
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 bump-deps

README.md
[![agentmods](https://agentmods.dev/badge/skills/ayutaz/piper-plus/bump-deps.svg)](https://agentmods.dev/skills/ayutaz/piper-plus/bump-deps)
Your own site
<a href="https://agentmods.dev/skills/ayutaz/piper-plus/bump-deps"><img src="https://agentmods.dev/badge/skills/ayutaz/piper-plus/bump-deps.svg" alt="Measured on agentmods" height="20"></a>
Per session 101 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,752 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00101 $0.01752
Opus 5 $0.00051 $0.00876
Sonnet 5 $0.00020 $0.00350
Haiku 4.5 $0.00010 $0.00175

Measured 8d ago against content hash 3a035bf12783, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

bump-deps scanned grade A with 1 finding 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 8d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

allowed-tools: Bash(uv run *) Bash(grep *) Bash(rg *) Bash(curl -s *) Bash(jq *) Bash(awk *) Bash(git diff *) Bash(git status *) Read Edit Grep
.claude/skills/bump-deps/SKILL.md · 145 lines

How it starts

The opening of the file, as written. The whole thing — 145 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Cross-Runtime Dependency Bump Skill

ORT / openjtalk / ruff のような「複数ファイル散在 / canonical source あり」 系の依存関係を、 canonical を更新したら mirror 箇所も同時に提案する skill。

既存の sync gate (check_*_sync.py) は drift を検出するだけ、 本 skill は drift を 解消する diff を提示する。

memory feedback_conservative_changes.md に従い、 デフォルト dry-run、 markdown diff の提示のみ。 --apply で Edit を実行。

対象依存

名前 Canonical Mirror 数 既存 gate
ONNX Runtime cmake/OnnxRuntime.cmake (ONNXRUNTIME_VERSION) 6+ ファイル check_ort_versions.py / check_ort_version_drift.py
openjtalk cmake/ExternalDeps.cmake (URL 内の version) 3+ ファイル check_openjtalk_version_sync.py
ruff pyproject.toml (dev group の最初の出現) 6 箇所 check_ruff_version_sync.py
(将来) cmake/... (新 dep) TBD (新 gate)

引数

  • $1 (必須): ort / openjtalk / ruff / all
  • --target X.Y.Z (必須): 新 version
  • --apply: dry-run の確認後 Edit を実行 (default は dry-run)

現在の状態

  • ブランチ: !git rev-parse --abbrev-ref HEAD
  • 引数: $ARGUMENTS

フェーズ 1: 現状 + drift 確認

uv run python scripts/check_ort_versions.py --verbose 2>&1 | head -30
uv run python scripts/check_openjtalk_version_sync.py --verbose 2>&1 | head -20
uv run python scripts/check_ruff_version_sync.py 2>&1 | head -20

drift があれば「先に解消」を提案、 なければ「新 target への bump 案」を作る。

フェーズ 2: ORT bump 案 (ort の場合)

# 6 ファイルの diff を生成
TARGET="$2"  # 例 1.18.0

# 1. cmake/OnnxRuntime.cmake
rg "set\(ONNXRUNTIME_VERSION" cmake/OnnxRuntime.cmake

# 2. .github/workflows/{ort-version-sync,release-shared-lib,android-build,release-kotlin-g2p,kotlin-g2p-ci,build-piper,_build-test-cpp}.yml
rg "ONNXRUNTIME_VERSION:" .github/workflows/ -l

# 3. docker/cpp-dev/Dockerfile
rg "ONNXRUNTIME_VERSION" docker/cpp-dev/Dockerfile

# 4. src/python/pyproject.toml + src/python_run/requirements*.txt
rg "onnxruntime[<>=~]" src/python/ src/python_run/

# 5. src/csharp/*.csproj
rg "Microsoft.ML.OnnxRuntime" src/csharp/

# 6. src/go/go.mod
rg "github.com/yalue/onnxruntime_go" src/go/go.mod

# 7. src/wasm/openjtalk-web/package.json
rg "onnxruntime-web" src/wasm/openjtalk-web/

Read the full file on GitHub · 145 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. 8d ago First seen · 145 lines · 101 tokens per session scan A 3a035bf12783

Subscribe to this mod's changes

bump-deps is a skill published in the GitHub repository ayutaz/piper-plus (204 stars, last pushed 6d ago), licensed MIT. It adds 101 tokens to every session and 1,752 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). 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

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

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…

NVIDIA/physicsnemo · 124 tokens

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…

PharMolix/OpenBioMed · 94 tokens

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…

ericrisco/rsc-harness · 102 tokens

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.

graphsignal/graphsignal-profiler · 74 tokens

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…

ascend-ai-coding/awesome-ascend-skills · 142 tokens