piper-plus: Skill for Claude Code

.claude/skills/reply-review/SKILL.md

reply-review is a skill for Claude Code from ayutaz/piper-plus. It costs 153 tokens per session (3,893 once invoked), scanned A, original, MIT.

A helper for responding to unresolved GitHub pull-request review comments and closing their discussion threads. It can distinguish already-outdated comments and certain repetitive Copilot style comments from comments that may still block the change.

In plain words
What is it for?
Use it with a pull-request number and optionally a commit hash to review unresolved comments. It can flag stale comments, omit selected Copilot-style comments, and automatically reply to and resolve only the configured safe categories.
Why use it?
It reduces manual work after fixes have been committed while avoiding automatic replies to potentially important human feedback. Dry-run mode lets you inspect the proposed replies and resolutions first.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: mentions CLAUDE.md; 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 →

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/reply-review/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 reply-review

README.md
[![agentmods](https://agentmods.dev/badge/skills/ayutaz/piper-plus/reply-review.svg)](https://agentmods.dev/skills/ayutaz/piper-plus/reply-review)
Your own site
<a href="https://agentmods.dev/skills/ayutaz/piper-plus/reply-review"><img src="https://agentmods.dev/badge/skills/ayutaz/piper-plus/reply-review.svg" alt="Measured on agentmods" height="20"></a>
Per session 153 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,893 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. 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 $0.00153 $0.03893
Opus 5 $0.00077 $0.01946
Sonnet 5 $0.00031 $0.00779
Haiku 4.5 $0.00015 $0.00389

Measured 7d ago against content hash f12eafe0b756, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

reply-review 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 7d 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/reply-review/SKILL.md · 292 lines

How it starts

The opening of the file, as written. The whole thing — 292 lines — stays where its author put it; the contents beside it link to each section on GitHub.

PR レビューコメント自動返信 + Resolve

修正コミット後に呼び出して、未解決の review comment に対応内容を返信し、thread を resolve します。

引数

  • $1 (必須): PR 番号 (例: 349)
  • $2 (任意): 返信に記載するコミットハッシュ。省略時は git rev-parse HEAD の短縮 hash を使用。
  • --stale-check (任意): 各コメントの originalCommit.oid と HEAD を比較し、該当ファイルが以降に更新済の場合 stale flag を立てる (フェーズ 1.5 で表示)
  • --skip-copilot-style (任意): Copilot の定型ノイズコメント (style/lint 系の "Consider using" "Consider renaming" 等) を一覧から除外 (フェーズ 1.7 で適用)
  • --auto-safe (任意): 安全カテゴリ ((a) stale 判定済 + (b) Copilot 定型ノイズ + (c) Copilot stale-on-style 重複) のみ 自動 reply + resolve。 非 stale な human reviewer / blocker 候補は dry-run と同様にユーザに提示するのみ。 --stale-check--skip-copilot-style を内部で自動有効化。 /loop /watch-pr から chain 起動される想定。 memory feedback_pr_body_over_comments / feedback_merge_caution と整合 (review thread への reply ≠ PR body 改変 ≠ merge)。
  • --dry-run (任意): 投稿・resolve を実行せず計画のみ表示

実行前の確認

  • ブランチ: !git rev-parse --abbrev-ref HEAD
  • 最新コミット: !git log -1 --oneline
  • 引数: $ARGUMENTS

手順

フェーズ 1: Review Thread の取得

GraphQL で 未解決 の review thread を取得:

gh api graphql -f query='
query($pr: Int!) {
  repository(owner: "ayutaz", name: "piper-plus") {
    pullRequest(number: $pr) {
      reviewThreads(first: 50) {
        nodes {
          id
          isResolved
          comments(first: 1) {
            nodes {
              id
              databaseId
              path
              line
              body
              author { login }
              originalCommit { oid }
              commit { oid }
            }
          }
        }
      }
    }
  }
}' -F pr=<PR_NUMBER> --jq '.data.repository.pullRequest.reviewThreads.nodes[] | select(.isResolved == false) | {thread_id: .id, comment: .comments.nodes[0]}'

各 thread について:

  • thread_id: GraphQL mutation で resolve するための ID
  • comment.databaseId: REST API で reply するための ID
  • comment.path + comment.line: どのファイルのどの行のコメントか
  • comment.body: レビュー本文 (対応内容を判定する材料)
  • comment.originalCommit.oid: コメントが付けられた commit SHA (stale check に使用)
  • comment.commit.oid: コメントが現在指している commit SHA (rebase 後の最新位置)

Read the full file on GitHub · 292 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. 7d ago First seen · 292 lines · 153 tokens per session scan A f12eafe0b756

Subscribe to this mod's changes

reply-review is a skill published in the GitHub repository ayutaz/piper-plus (204 stars, last pushed 5d ago), licensed MIT. It adds 153 tokens to every session and 3,893 once invoked, about $0.0008 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

github

GitHub operations via gh CLI: issues, PRs, CI runs, code review, API queries. Use when: (1) checking PR status or CI, (2) creating/commenting on issues, (3) listing/filtering PRs or issues, (4) viewing run logs. NOT for: complex web UI interactions requiring manual browser flows (use browser tooling when available)…

opensquilla/opensquilla · 101 tokens

meta-codereview-current-diff

Read the current uncommitted diff, run three independent reviewers (safety + tests-coverage + style) in parallel, then arbitrate a single BLOCK / BLOCKWITHOVERRIDE / PASSWITHNOTES verdict. Use before commit when you want a multi-perspective second-opinion instead of a single-reviewer agent loop.

opensquilla/opensquilla · 73 tokens

submit-github-pr

Use when publishing an existing TensorRT-Model-Connect change as a GitHub pull request. Verifies authenticated repository access, branch and diff scope, validation evidence, commit identity, reviewer-facing text, exact pushed head, and the created draft PR without merging it.

NVIDIA/TensorRT-Model-Connect · 58 tokens

write-git-messages

Draft, revise, or review Git commit messages, PR titles, PR descriptions, and squash or rebase merge messages. Use when Codex needs to summarize a diff for reviewers, convert rough notes into a commit or PR message, check a message against Git and Conventional Commits style, or prepare repository contribution text…

NVIDIA/TensorRT-Model-Connect · 75 tokens

review-implement-phase

Implements triaged review actions, commits focused fixes, and posts Done plus resolves threads. Use when the user wants only the implementation phase of the review-framework workflow.

prisma/orm · 38 tokens

engram-branch-pr

PR creation workflow for Engram following the issue-first enforcement system. Trigger: When creating a pull request, opening a PR, or preparing changes for review.

Gentleman-Programming/engram · 37 tokens