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.
npx agentmods add skills/ayutaz/piper-plus/prepare-releasenpx skills add ayutaz/piper-plus --skill prepare-releasegit 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/prepare-release)<a href="https://agentmods.dev/skills/ayutaz/piper-plus/prepare-release"><img src="https://agentmods.dev/badge/skills/ayutaz/piper-plus/prepare-release.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 | $0.00095 | $0.02969 |
| Opus 5 | $0.00048 | $0.01484 |
| Sonnet 5 | $0.00019 | $0.00594 |
| Haiku 4.5 | $0.00010 | $0.00297 |
Grade A, and why
prepare-release 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 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
allowed-tools: Bash(cat *) Bash(grep *) Bash(jq *) Bash(rg *) Bash(awk *) Bash(curl -s *) Bash(npm view *) Bash(git diff *) Bash(git log *) Bash(git status *) Bash(swift package compute-checksum *) Read Edit Grep How it starts
The opening of the file, as written. The whole thing — 197 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Release Preparation Skill (Bump 適用版)
release-prep (read-mostly な確認) の続きとして、 実際の version bump 差分 を全 manifest にわたり生成する skill。
ユーザは memory feedback_conservative_changes.md / feedback_merge_caution.md に従い、 適用は明示確認を取ってから (デフォルト dry-run、 markdown diff 提示のみ)。
カバー範囲
| 段階 | 対応 |
|---|---|
| Version 散在検出 | 9 manifest を一括 bump 案として markdown 出力 |
| Lockfile 再生成 | uv.lock / Cargo.lock / package-lock.json の更新コマンド提示 |
| Swift checksum | xcframework artifact 取得後の swift package compute-checksum 手順 |
| CHANGELOG 昇格 | [Unreleased] → [X.Y.Z] - YYYY-MM-DD の markdown diff |
| Tag 順序ガイド | npm tag (g2p 先行) / shared-lib tag / 内部 chain tag の順序 |
| 公開後検証 | 各 registry で publish 完了確認の手順 |
引数
$ARGUMENTS1 つ目:all/python/rust/csharp/npm/swift/kotlin--target-version X.Y.Z: 次回リリース version (必須)--dry-run(default): markdown 出力のみ、 ファイル変更しない--apply: dry-run の確認後にユーザが追加で渡す flag。 これがある時のみ Edit を実行
現在の状態
- ブランチ: !
git rev-parse --abbrev-ref HEAD - 引数: $ARGUMENTS
- 直近 tag: !
git tag --sort=-v:refname | head -3
フェーズ 1: 現 manifest version 読み出し (9 ファイル)
並列で Read し、 各 manifest の現 version を抽出:
| Runtime | Manifest | 抽出キー |
|---|---|---|
| Python | VERSION |
ファイル全体 |
| Python (g2p) | src/python/g2p/pyproject.toml |
[project].version |
| Rust | src/rust/Cargo.toml |
[workspace.package].version |
| C# Core | src/csharp/PiperPlus.Core/PiperPlus.Core.csproj |
<Version> |
| C# Cli | src/csharp/PiperPlus.Cli/PiperPlus.Cli.csproj |
<Version> |
| npm synth | src/wasm/openjtalk-web/package.json |
.version |
| npm g2p | src/wasm/g2p/package.json |
.version |
| Swift | Package.swift |
let version = 行 + let g2pVersion = 行 |
| Kotlin | android/gradle.properties |
VERSION_NAME= |
フェーズ 2: 既存 sync gate との交差確認
uv run python scripts/check_voice_catalog_parity.py 2>&1 | tail -3
uv run python scripts/check_ort_versions.py 2>&1 | tail -3
uv run python scripts/check_openjtalk_version_sync.py 2>&1 | tail -3
uv run python scripts/check_ruff_version_sync.py 2>&1 | tail -3
uv run python scripts/check_migration_changelog_parity.py 2>&1 | tail -3
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.
- 5d ago First seen · 197 lines · 95 tokens per session scan A a6e4dfbd808c
prepare-release is a skill published in the GitHub repository ayutaz/piper-plus (204 stars, last pushed 3d ago), licensed MIT. It adds 95 tokens to every session and 2,969 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.
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.
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( …
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…
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)…
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.
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…