A procedure for reviewing a GitHub pull request, which is a proposed set of code changes, for problems and missing tests.

Use it to inspect a pull request's changes and report issues that require fixes, either from its number, URL, or the current branch.

It focuses review on bugs, security risks, breaking changes, performance issues, edge cases, and tests that the change needs.

review-pr — Skill for Claude Code by fcakyon: A procedure for reviewing a GitHub pull request, which…

About the project

claude-codex-settings is a collection of configurations and reusable extensions for Claude Code, OpenAI Codex, Cursor, and related coding tools. Developers use its skills, commands, hooks, agents, plugins, and MCP servers to shape coding-agent workflows and connect alternative model APIs. The catalogue entries are components of this collection that can be installed into supported coding tools.

fcakyon/claude-codex-settings · 1,129 stars · on GitHub · claudesettings.com

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.

agentmods

npx agentmods add skills/fcakyon/claude-codex-settings/review-pr

Any agent

npx skills add fcakyon/claude-codex-settings --skill review-pr

Clone the repo

git clone --depth 1 https://github.com/fcakyon/claude-codex-settings

Made for: Claude Code.

Or install github-dev, the plugin that ships this one along with the rest of its 6 skills, 4 agents.

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/fcakyon/claude-codex-settings/review-pr.svg)](https://agentmods.dev/skills/fcakyon/claude-codex-settings/review-pr)

Your own site

<a href="https://agentmods.dev/skills/fcakyon/claude-codex-settings/review-pr"><img src="https://agentmods.dev/badge/skills/fcakyon/claude-codex-settings/review-pr.svg" alt="Measured on agentmods" height="20"></a>

Per session 36 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 480 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. Scan, not verified.

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	$0.00036	$0.00480
Opus 5	$0.00018	$0.00240
Sonnet 5	$0.00007	$0.00096
Haiku 4.5	$0.00004	$0.00048

Measured 6d ago against content hash d6e0884e79e8, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

review-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 6d 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.

plugins/github-dev/skills/review-pr/SKILL.md · 47 lines

What it actually says

Review PR

Review a pull request for bugs, regressions, missing tests, and risky changes.

When explicitly invoked with extra text, treat that text as the PR number or URL. If no PR reference is provided, infer it from the current branch.

Process

Preferred execution
- If subagents are available, use github-dev:pr-reviewer and pass the PR reference.
- Otherwise follow the manual steps below.
Parse PR reference
- If a PR number or URL is provided, extract owner, repo, and PR number.
- If not, auto-detect the PR from the current branch with gh pr view --json number,headRefName.
Fetch PR data
- Use gh pr diff <number> for the full diff.
- Use gh pr view <number> --json files for the changed file list.
- Skip generated or vendored files such as .lock, .min.js, .min.css, dist/, build/, vendor/, node_modules/, _pb2.py, and images.
Review focus
- Only report issues that require fixes.
- Only review PR changes, never pre-existing issues in unchanged code.
- Prioritize bugs, security issues, breaking changes, performance issues, edge cases, and missing tests.
- Combine related issues that share the same root cause.
- Keep the list short and high signal.
Review comment rules
- Only create pending PR comments, never submit or confirm the review automatically.
- Use gh for GitHub operations.
- Start comments in lowercase, keep them short, avoid end punctuation when possible.
- Use simple language for both bot-facing and human-facing comments.

Output Format

If issues are found, report them in descending severity with file references and a final recommendation of NEEDS_CHANGES.

If no issues are found, return APPROVE - No fixes required.

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.

6d ago First seen · 47 lines · 36 tokens per session scan A d6e0884e79e8

Subscribe to this mod's changes

review-pr is a skill published in the GitHub repository fcakyon/claude-codex-settings (1,129 stars, last pushed today), licensed Apache-2.0. It adds 36 tokens to every session and 480 once invoked, about $0.0002 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.

Code review Git and workflow claude-code commit-message cursor gemini-cli github pull-requests

github-pr-workflow

Prepare a GitHub pull request from a feature branch — branch hygiene, commit shape, title/body, verification notes, screenshots for UI work, and replies to review comments.

paperclipai/paperclip · 39 tokens

github

Create issues, PRs, clone repos, and manage git workflows.

initializ/forge · 15 tokens

lov-maintain-partners

Maintain the Skill Publisher website's partners section AND align partner logo rows on event posters / hero strips: reuse lov-find-logo for brand logo discovery, normalize collected logos to a 240px-tall content canvas (retina-ready), rasterize SVGs via rsvg-convert before normalizing (so SVG viewBox padding gets…

lovstudio/skills · 294 tokens

dsh-plugin-publisher

Publish a validated DSH plugin package (@deepseek-ai/dsh- or @lovstudio/dsh-) to npm, git, or tarball channels and verify it loads in the DeepSeek Harness. Use when the user asks to publish, release, or ship a plugin. 触发：发布插件 / 上架插件 / release dsh 插件。.

lovstudio/skills · 82 tokens

lov-publish-event-onto-hdx

诊断并修改活动行已发布活动：核查分类页可见性与排名、替换详情正文配图，并守住后台保存会清空分类这一平台陷阱。Trigger: 活动行分类找不到、活动行分类没了、活动行排名、活动行曝光、活动行换海报、hdx category not showing, hdx category reset。.

lovstudio/skills · 92 tokens

lov-skill-pricing

为一个或多个 Agent Skill 生成可解释的 Skill Pricing Card：结合创作者时间与维护成本、用户价值、稀缺性、购买信心和生态潜力，输出建议价、价格区间、渠道策略及证据缺口；触发语包括“给这个 Skill 定价”和 “price this Skill”。.

lovstudio/skills · 78 tokens