pr-feedback-fetch

pr-feedback-fetch is a skill for Claude Code from MH4GF/claude-code. It costs 74 tokens per session (2,309 once invoked), scanned A, original, MIT.

A GitHub pull-request feedback collector that gathers top-level comments, inline comments, and review summaries into one structured report.

In plain words
What is it for?
Use it with a pull-request number, URL, or the current branch to collect the latest feedback for planning fixes.
Why use it?
It prevents review feedback from being missed when it is spread across GitHub's different comment and review sections.

Skill for Claude Code

Written for Claude Code: context: fork in frontmatter.

Good fit Use it with a pull-request number, URL, or the current branch to collect the latest feedback for planning fixes.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/mh4gf/claude-code/pr-feedback-fetch
Install

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.

Any agent
npx skills add MH4GF/claude-code --skill pr-feedback-fetch
Clone the repo
git clone --depth 1 https://github.com/MH4GF/claude-code

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 pr-feedback-fetch

README.md
[![agentmods](https://agentmods.dev/badge/skills/mh4gf/claude-code/pr-feedback-fetch/github.svg)](https://agentmods.dev/skills/mh4gf/claude-code/pr-feedback-fetch)
Your own site
<a href="https://agentmods.dev/skills/mh4gf/claude-code/pr-feedback-fetch"><img src="https://agentmods.dev/badge/skills/mh4gf/claude-code/pr-feedback-fetch/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 pr-feedback-fetch

Your own site · 80×15
<a href="https://agentmods.dev/skills/mh4gf/claude-code/pr-feedback-fetch"><img src="https://agentmods.dev/badge/skills/mh4gf/claude-code/pr-feedback-fetch.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 74 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,309 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.
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 $0.00074 $0.02309
Opus 5.5 $0.00030 $0.00924
Sonnet 5.5 $0.00015 $0.00462
Haiku 4.5 $0.00007 $0.00231

Measured 2mo ago against content hash a8df6ee8d97b, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

pr-feedback-fetch 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 2mo 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.

user-scope/skills/pr-feedback-fetch/SKILL.md · 152 lines

How it starts

The opening of the file, as written. The whole thing — 152 lines — stays where its author put it; the contents beside it link to each section on GitHub.

pr-feedback-fetch

指定された PR について、GitHub の 3 channel (top-level comment / inline review comment / review summary) を順序固定で取得する。出力は 1 つの structured markdown としてまとめる。

gh pr view --comments は top-level comment しか返さないため、inline review comment と review summary を独立に取得する必要がある。本 skill は 3 エンドポイントを不可分に呼び、取得 channel: 3/3 を必ず明示する。

前提

  • gh CLI が認証済み (gh auth status で Logged in になっている)
  • 現 branch (引数なし時) または引数から PR 番号と repo (owner/repo) を解決できる
  • 出力は structured markdown。呼び出し元が workpad / レポート / 判断材料に直接転記できる形

スコープ外

  • feedback への返信 / 対応コミット / push。本 skill は「取得して並べる」までで止める
  • bot コメント (Actions / dependabot 等) のフィルタ判定。actionable かどうかの判断は呼び出し側に委ねる
  • 過去の feedback 履歴の差分管理。常に最新 snapshot を全件取得する
  • CI ステータス確認。gh pr checks は別経路で扱う

手順

1. 引数を解決する

呼び出し時の引数は 0 〜 1 個。次のいずれか。

  • 引数なし — 現 branch をそのまま対象に gh pr view --json number,url,headRefName,baseRepository で PR 番号を解決する
  • 数字 (例 200) — PR 番号として扱う。repo は gh repo view --json nameWithOwner で現 repo を採用する
  • URL (例 https://github.com/MH4GF/claude-code/pull/10) — URL から <owner>/<repo> と PR 番号を分解する

引数を解決できない場合 (現 branch の PR が無い等) は即停止し、「PR 未解決」と書いた出力を返す。

2. 3 channel を順に取得する

解決した <owner>/<repo> と <pr> を使い、次の 3 コマンドを順に実行する。順序は固定。途中で止めない。

# 2-1. top-level の PR comment (issue comment と等価)
gh api repos/<owner>/<repo>/issues/<pr>/comments \
  --jq '.[] | {id, user: .user.login, type: .user.type, created_at, updated_at, body}'

# 2-2. inline review comment (diff 上の行コメント)
gh api repos/<owner>/<repo>/pulls/<pr>/comments \
  --jq '.[] | {id, user: .user.login, type: .user.type, path, line, original_line, side, created_at, updated_at, body, in_reply_to_id, pull_request_review_id}'

# 2-3. review summary (Approve / Request changes / Comment レビュー単位)
gh api repos/<owner>/<repo>/pulls/<pr>/reviews \
  --jq '.[] | {id, user: .user.login, type: .user.type, state, submitted_at, body}'

3 channel すべてが空でも 3 コマンドとも実行する。1 つでも省略すると本 skill の意味が失われる。

gh api が失敗した channel は、> ERROR: <message> として出力へ残し、呼び出し側に明示する。残り channel の取得は続行する。

Read the full file on GitHub · 152 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. 2mo ago First seen · 152 lines · 74 tokens per session scan A a8df6ee8d97b

Subscribe to this mod's changes

pr-feedback-fetch is a skill published in the GitHub repository MH4GF/claude-code (2 stars, last pushed 5d ago), licensed MIT. It adds 74 tokens to every session and 2,309 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-08-31.

Related

Other skills, from other repositories

pr

Draft a PR body from OMC's paper trail — the smallest visual that proves the change, evidence consumed from the verify protocol (never re-collected), reversibility from the ADR test on the diff, glossary language throughout.

Yeachan-Heo/oh-my-claudecode · 47 tokens

merge-batch

Prepare and merge an owner-selected PR batch with contributor credit and exact-candidate admission. Use for a pasted PR list; combined focused validation is diagnostic, and every actual landing still requires its applicable checks and authorization.

diegosouzapw/OmniRoute · 46 tokens

otto-pr-review-loop

Run Polly and OCR on a PR until all findings settle.

omnigent-ai/omnigent · 17 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

github-contributor

A step-by-step guide for contributing code, tests, documentation, or build changes to open-source projects you do not maintain. It explains how to prepare a pull request that follows the project’s rules and is easier for maintainers to review.

daymade/claude-code-skills · 105 tokens

revdiff

Review diffs, files, and documents with inline annotations in a TUI overlay, or answer questions about revdiff usage, configuration, themes, and keybindings. Opens revdiff in agterm/tmux/zellij/herdr/kitty/wezterm/cmux/ghostty/iterm2/emacs-vterm, captures annotations, and addresses them. Works in git, hg, and jj repos…

umputun/revdiff · 248 tokens