What is fix-github-pr-comment?

A workflow for handling review comments on an existing GitHub pull request. A pull request is a proposed code change, and this workflow reads its comments, updates the code, pushes the changes, replies on GitHub, and marks addressed threads as resolved.

Use it when you need to respond to inline comments, review threads, or general feedback on an existing pull request. It is not for drafting a reply alone or creating a new pull request.

It joins the code change and the GitHub conversation, so review feedback is not left only in local files or answered without fixing the code. It also handles the required Git steps around the update.

fix-github-pr-comment — Skill for Claude Code and Codex by eaglesakura

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 eaglesakura/agent-skills --skill fix-github-pr-comment

Clone the repo

git clone --depth 1 https://github.com/eaglesakura/agent-skills

Made for: Claude Code, Codex.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/eaglesakura/agent-skills/fix-github-pr-comment/github.svg)](https://agentmods.dev/skills/eaglesakura/agent-skills/fix-github-pr-comment)

Your own site

<a href="https://agentmods.dev/skills/eaglesakura/agent-skills/fix-github-pr-comment"><img src="https://agentmods.dev/badge/skills/eaglesakura/agent-skills/fix-github-pr-comment/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/eaglesakura/agent-skills/fix-github-pr-comment"><img src="https://agentmods.dev/badge/skills/eaglesakura/agent-skills/fix-github-pr-comment.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 178 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 3,276 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.

Model	Per session	Once invoked
Fable 5.1	$0.00178	$0.03276
Opus 5.5	$0.00071	$0.01310
Sonnet 5.5	$0.00036	$0.00655
Haiku 4.5	$0.00018	$0.00328

Measured 2mo ago against content hash 360943aa8aa9, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

fix-github-pr-comment 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.

packages/ohitorisama/.apm/skills/fix-github-pr-comment/SKILL.md · 317 lines

How it starts

The opening of the file, as written. The whole thing — 317 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Fix GitHub PR Comment

既存 Pull Request 上のレビュー指摘を読み、コードを直し、コミットして push し、 GitHub 上で返信してスレッドを Resolved にする。Stacked PR の場合は後続 PR へ変更を伝搬する。

いつ使うか

ユーザーが 既存 PR 全体 のレビュー指摘対応を依頼したとき
ユーザーが 特定コメント / スレッド の修正を依頼したとき
「指摘を直して push まで」「Resolved にして」など、修正 + GitHub 返信 がセットのとき

いつ使わないか

返信文案だけ・コメント起草だけ → github-comment-rule
コミットメッセージだけ → git-commit-comment-rule
Stacked PR の rebase / sync / merge だけ → gh-stack
巨大 PR の分割・再スタック → decompose-fat-pr-to-stacked-prs
新規 PR 作成 → /github.create-pull-request

役割分担

役割	参照先
コミットメッセージ	`git-commit-comment-rule`（必読・必須）
GitHub 返信文案・署名	`github-comment-rule`（必読・必須）
Stacked PR の伝搬	`gh-stack` SKILL
ブランチ名・Issue 番号	`workspace-git-branch-rule`
本 SKILL	チェックアウト → 修正 → 検証 → コミット → push → 返信 → Resolved → 伝搬

開始時に同パッケージの git-commit-comment-rule と github-comment-rule を読む。

ハードルール

作業ツリーはクリーン必須: 未コミット変更（staged / unstaged / untracked で作業に干渉するもの）がある状態では checkout しない。エラーとして停止し、ユーザーに stash / commit / discard を促す。
PR ブランチの最新 HEAD で作業: checkout 後、origin の tip と fast-forward 同期する。
CI Success は待たない（ユーザーが明示指示した場合のみ待つ）。
破壊的 git は禁止: reset --hard、clean -fdx、force push、履歴書き換えはしない（明示承認なし）。
ステージは指名のみ: git add . / git add -A は使わない。
Resolved は対応済みスレッドだけ: 修正・返信したスレッドのみ resolve する。未対応の指摘を resolve しない。

前提

gh が認証済み
対象リポジトリの作業ディレクトリにいる（または --repo owner/name を明示）
Stacked PR 伝搬には gh extension install github/gh-stack が必要
gh stack は非対話で呼ぶ（view --json、submit --auto 等）。詳細は gh-stack SKILL

作業手順

0. 対象の特定

ユーザー入力から次を確定する。

項目	例
PR 番号 / URL	`#123`, `https://github.com/org/repo/pull/123`
スコープ	PR 全体 / 特定スレッド（URL・コメント ID・引用）
リポジトリ	カレント repo または `--repo`

PR=123
gh pr view "$PR" --json number,title,headRefName,baseRefName,url

1. 作業ツリーの検証（Checkout 前）

if [ -n "$(git status --porcelain)" ]; then
  echo "ERROR: Working tree is not clean. Commit, stash, or discard changes first."
  exit 1
fi

Read the full file on GitHub · 317 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

evals/evals.json 3.2 KB

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.

2mo ago First seen · 317 lines · 178 tokens per session scan A 360943aa8aa9

Subscribe to this mod's changes

fix-github-pr-comment is a skill published in the GitHub repository eaglesakura/agent-skills (2 stars, last pushed 1mo ago), licensed MIT. It adds 178 tokens to every session and 3,276 once invoked, about $0.0007 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 2026-09-05.

Code review Git and workflow

fix-github-pr-comment next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
fix-github-pr-commenteaglesakura/agent-skills	Skill	2	1mo ago	MIT	A	178	Claude Code, Codex
prYeachan-Heo/oh-my-claudecode	Skill	41k	today	MIT	A	47	Claude Code
merge-batchdiegosouzapw/OmniRoute	Skill	83k	6d ago	MIT	A	46	Claude Code
otto-pr-review-loopomnigent-ai/omnigent	Skill	11k	today	Apache-2.0	A	17	Claude Code, Codex
engram-branch-prGentleman-Programming/engram	Skill	7.8k	today	MIT	A	37	Claude Code, Codex
github-contributordaymade/claude-code-skills	Skill	1.5k	today	MIT	A	105	Claude Code, Codex
revdiffumputun/revdiff	Skill	947	2d ago	MIT	A	250	Claude Code