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/create-prnpx skills add ayutaz/piper-plus --skill create-prgit 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/create-pr)<a href="https://agentmods.dev/skills/ayutaz/piper-plus/create-pr"><img src="https://agentmods.dev/badge/skills/ayutaz/piper-plus/create-pr.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 | $0.00103 | $0.04055 |
| Opus 5 | $0.00051 | $0.02027 |
| Sonnet 5 | $0.00021 | $0.00811 |
| Haiku 4.5 | $0.00010 | $0.00405 |
Grade A, and why
create-pr 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 4d 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 — 239 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PR 作成 + CI 監視 + レビュー対応 (end-to-end)
/create-pr 1 コマンドで PR ライフサイクル全体を完結する skill:
push → PR 作成 → CI 監視ループ → review thread 返信 + resolve → 報告
過去 /create-pr → /watch-pr → /reply-review を別々の skill 呼び出しで連鎖していたが、 「次の skill を Skill ツールで呼べ」 という散文 handoff は LLM が実行を飛ばすと工程が抜ける (PR #496 / #505 で発生)。 本 skill は全工程を inline フェーズ として持ち、 skill 間 handoff をゼロにする。
単体利用: CI 監視のみ →
/watch-pr <PR#>、 review 対応のみ →/reply-review <PR#>、 backlog 集計 →/check-review-backlog。 これらは本 skill のフェーズ 5 / 6 と同一手順の standalone 版。
自動発動条件
- 「PR を作って / 出して」「pull request を作って」「この変更で PR にして」「branch を push して PR にして」
明示呼び出し: /create-pr / /create-pr <base-branch> / /create-pr --no-watch (PR 作成のみ、 監視ループに入らない)
引数
$ARGUMENTS空: base =dev(memoryfeedback_merge_caution: 通常 dev を base)<base-branch>: 明示指定 (例:main)--title <title>: title 上書き (デフォルトは最新コミット message から抽出)--no-watch: フェーズ 5/6 (CI 監視・review 対応) を skip し PR 作成で終了
制約 (memory 参照)
- マイルストーン非付与 (
feedback_pr_no_milestones):--milestoneを付けない。 本文に「M1」等も書かない - auto-merge 禁止 (
feedback_merge_caution):gh pr merge --auto等を使わない。 マージはユーザー判断 - 本文書き換えは body-file (
feedback_pr_body_over_comments): 既存 PR 更新はgh pr edit --body-file。 新規コメント追記しない。 review thread への reply はこの制約の対象外 - --no-verify 禁止 (CLAUDE.md): hook bypass 系を使わない
- review thread の自動 reply は SAFE 系のみ: stale / Copilot style noise のみ自動 reply+resolve。 人間 reviewer・logic/security 指摘は user 判断 (フェーズ 6)
PR 本文フォーマット (重要 — テンプレート準拠必須)
PR 本文は .github/pull_request_template.md の必須セクションをすべて含むこと。 validate-pr-body CI ゲートが以下を検査し、 欠けると PR が必ず red になる (PR #505 で発生した既知バグ — 旧フォーマットはこのゲートを通らなかった):
## Test Planセクションが存在し非空 (大文字 P。## Test planは grep^## Test Planに不一致で fail)## Risk Levelセクションでチェックボックスがちょうど 1 個- [x]## Affected Componentsセクションでチェックボックス最低 1 個- [x]
PR title は 70 文字以内、 type(scope): prefix (例 fix(g2p): ci: feat(workflow):)。
PR 本文は以下を この順 で含める (1-8 は template 準拠の必須セクション、 9-10 は create-pr 独自の value-add):
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.
- 4d ago First seen · 239 lines · 103 tokens per session scan A 1b1076539b11
create-pr is a skill published in the GitHub repository ayutaz/piper-plus (202 stars, last pushed 6d ago), licensed MIT. It adds 103 tokens to every session and 4,055 once invoked, about $0.0005 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
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…