actions-mention-to-slack: Skill for Claude Code

.claude/skills/run-pr-review/SKILL.md

run-pr-review is a skill for Claude Code from abeyuya/actions-mention-to-slack. It costs 107 tokens per session (3,115 once invoked), scanned A, original, MIT.

A workflow guide for carrying out a complete GitHub pull-request review, from identifying the pull request to writing comments, posting the review, and closing completed old threads.

In plain words
What is it for?
Use it to run an end-to-end review with optional limits on inline comments and configurable rules for which previous threads may be closed.
Why use it?
It brings the review steps together so the process follows the project’s review style and does not leave outdated threads unresolved.

Skill for Claude Code

Written for Claude Code: installed under .claude/. Also seen: mentions CLAUDE.md; mentions Claude Code; mentions AGENTS.md.

This is abeyuya/actions-mention-to-slack's own configuration. It tells Claude Code how to work on actions-mention-to-slack 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 actions-mention-to-slack configures →

Reuse

Borrowing it

Nothing to install: this file belongs to abeyuya/actions-mention-to-slack. 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/abeyuya/actions-mention-to-slack/master/.claude/skills/run-pr-review/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/abeyuya/actions-mention-to-slack

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 run-pr-review

README.md
[![agentmods](https://agentmods.dev/badge/skills/abeyuya/actions-mention-to-slack/run-pr-review/github.svg)](https://agentmods.dev/skills/abeyuya/actions-mention-to-slack/run-pr-review)
Your own site
<a href="https://agentmods.dev/skills/abeyuya/actions-mention-to-slack/run-pr-review"><img src="https://agentmods.dev/badge/skills/abeyuya/actions-mention-to-slack/run-pr-review/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.

agentmods 80×15 button for run-pr-review

Your own site · 80×15
<a href="https://agentmods.dev/skills/abeyuya/actions-mention-to-slack/run-pr-review"><img src="https://agentmods.dev/badge/skills/abeyuya/actions-mention-to-slack/run-pr-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 107 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,115 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 $0.00107 $0.03115
Opus 5 $0.00053 $0.01558
Sonnet 5 $0.00021 $0.00623
Haiku 4.5 $0.00011 $0.00312

Measured 13d ago against content hash 2a51854402ff, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

run-pr-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 13d 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/run-pr-review/SKILL.md · 99 lines

How it starts

The opening of the file, as written. The whole thing — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.

run-pr-review skill

PR レビュー一式 (スタイル参考ガイド読み込み → PR 確認 → レビュー作成 → 投稿 → 過去スレッド resolve) を 1つの skill 呼び出しで完結 させるためのオーケストレーション skill。

入力 (任意, caller から prompt 経由で渡される想定)

すべて省略可。省略時の挙動は各項目に記載。

  • OWNER / REPO / PR_NUMBER: 対象 PR の識別情報。省略時は後述の手順で自動取得する。
  • MAX_INLINE_COMMENTS: インライン指摘の総数上限。正の整数または unlimited。省略時は unlimited 扱い (=/pr-review-style-reference 引数なしのデフォルト)。Step 2 で /pr-review-style-reference max-inline-comments=<値> として渡す。
  • THREAD_RESOLVE_SCOPE: resolve-pr-threads skill に渡す resolve 範囲。all / own / none のいずれか。省略時は all
  • SELF_LOGIN (任意, THREAD_RESOLVE_SCOPE=own 時): 自身を判定するための author.login。caller が判明していれば渡す。Step 7 でそのまま resolve-pr-threads に転送される。

caller プロジェクト固有の方針 (技術観点 / スタイル上書き / 全方針置換) は プロジェクト指示ファイル (Step 3 で定義) に置く運用に固定する。個別パス指定の引数は持たない。

手順

Step 1. PR 識別情報を確定する

caller から OWNER / REPO / PR_NUMBER が渡されていればそれを使う。揃っていない値だけ以下で補う:

  • OWNER / REPO: gh repo view --json nameWithOwner -q .nameWithOwnerOWNER/REPO 形式を取得し分解する。
  • PR_NUMBER: gh pr view --json number -q .number で現在のブランチに紐づく PR 番号を取得する。紐づく PR が無い場合はエラーとして停止し、caller に明示的に PR 番号を渡すよう促す。

Step 2. スタイル参考ガイドを読み込む

/pr-review-style-reference slash command を実行し、スタイル参考ガイド (重要度ラベル / ノイズ抑制 / 粒度ガイド / 重複回避 / CI 扱い) を本セッションのレビュー方針の参考として読み込む。

レビュー方針は caller プロジェクトに委ねる前提。Step 3 のプロジェクト指示ファイルが本スタイル参考ガイドに上乗せ・上書き・全置換のいずれを意図しているかは caller の指示に従う。プロジェクト指示ファイルが無ければ本スタイル参考ガイドをそのまま採用する。

MAX_INLINE_COMMENTS が指定されている場合は /pr-review-style-reference max-inline-comments=<値> として渡す。未指定なら引数なしで呼ぶ。

Step 3. プロジェクト指示ファイルを読み込む (任意)

リポジトリ root の以下を上から順に存在チェックし、最初に見つかった 1 つだけRead ツールで読み込み、本セッションのレビュー方針として適用する。以後この skill では総称して プロジェクト指示ファイル と呼ぶ。

  1. REVIEW.md — レビュー専用の最上位指示
  2. AGENTS.md — agent 全般向けの fallback
  3. .claude/CLAUDE.md — Claude Code 全般向けの fallback (.claude/ 配下に置く流儀)
  4. CLAUDE.md — Claude Code 全般向けの fallback (リポジトリ root に置く流儀)

いずれも存在しなければ skip する。複数存在しても下位は読まない / 連結しない。

Step 2 のスタイル参考ガイドと矛盾する箇所はプロジェクト側を優先し、矛盾しない箇所は両者を併用する。プロジェクト側で「スタイル参考ガイドを使わない」旨が明示されていればそれに従う。

Read the full file on GitHub · 99 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. 13d ago First seen · 99 lines · 107 tokens per session scan A 2a51854402ff

Subscribe to this mod's changes

run-pr-review is a skill published in the GitHub repository abeyuya/actions-mention-to-slack (58 stars, last pushed yesterday), licensed MIT. It adds 107 tokens to every session and 3,115 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.

Related

Other skills, from other repositories

robin

Use whenever an agent creates, updates, reviews, or completes a GitHub pull request. Detect whether Robin is installed in the repository; when it is, automatically drive the PR through a bounded review, verified-fix, reply, thread-resolution, re-review, authorized-merge, and cleanup loop without requiring the user to…

antongulin/robin · 92 tokens

bellwether

Bring the current PR to a mergeable state: CI green, all review comments resolved, no merge conflicts. Self-contained — watches CI, fixes issues, watches again until merge-ready. Use when the user wants to keep a PR green, auto-fix CI, resolve review comments, or says "get this merged".

roderik/bellwether · 68 tokens

pr-review

AI-assisted review of one or more GitHub Pull Requests. Offloads deterministic checks (lint, complexity, duplication, security, perf) to repo linters via self-contained scripts, then applies LLM judgment to what linters cannot catch and posts high-signal findings after a single human approval. Pass one or many PRs…

CiscoDevNet/essentials · 121 tokens

pr-address-comments

Read a remote GitHub PR's review comments, implement fixes on the PR branch, then reply to and resolve addressed threads (REST reply + GraphQL resolveReviewThread). Use for /pr-address-comments, a single PR URL or number, when not using the parallel batch skill pr-address-comments-all. Requires gh and a git checkout…

CiscoDevNet/essentials · 74 tokens

watch-pr

Watch a GitHub pull request for CI status, reviews, comments, merge conflicts, and terminal states using the gh-watch extension. Use when the user wants to monitor a PR, wait for CI, or track PR progress.

justincampbell/gh-watch · 48 tokens

manage-merge-queue

Prepare, review, enqueue, and land GitHub pull requests through a provider-neutral agent merge queue. Use when a PR becomes ready, configured review feedback must be addressed, the user says deploy, or queued changes need safe conflict-aware ordering.

Forward-Future/DeployBot · 54 tokens