A detailed pull-request review skill for the moving-frontend monorepo, a repository that contains multiple related projects or packages.

Use it when reviewing pull requests, checking GitHub Copilot or CodeRabbit comments, analyzing a teammate’s code, or preparing structured review documents.

It checks the actual changed code and project conventions while focusing review feedback on correctness, broken flows, architecture, tests, and developer learning.

pr-review — Skill for Claude Code by junyoung2015

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 junyoung2015/pr-review-skill --skill pr-review

Clone the repo

git clone --depth 1 https://github.com/junyoung2015/pr-review-skill

Made for: Claude Code.

Or install pr-review, the plugin that ships this one along with the rest of its 1 skill, 1 command.

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/junyoung2015/pr-review-skill/pr-review/github.svg)](https://agentmods.dev/skills/junyoung2015/pr-review-skill/pr-review)

Your own site

<a href="https://agentmods.dev/skills/junyoung2015/pr-review-skill/pr-review"><img src="https://agentmods.dev/badge/skills/junyoung2015/pr-review-skill/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/junyoung2015/pr-review-skill/pr-review"><img src="https://agentmods.dev/badge/skills/junyoung2015/pr-review-skill/pr-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 151 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 9,061 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	$0.00151	$0.09061
Opus 5	$0.00076	$0.04530
Sonnet 5	$0.00030	$0.01812
Haiku 4.5	$0.00015	$0.00906

Measured 9d ago against content hash e35e4acd3ae9, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

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 9d ago.

The scan reads SKILL.md. This mod also ships 8 executable files (scripts/fetch-pr.sh, scripts/generate-decisions-json.sh, scripts/post-ai-review-comments.sh, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

skills/pr-review/SKILL.md · 571 lines

How it starts

The opening of the file, as written. The whole thing — 571 lines — stays where its author put it; the contents beside it link to each section on GitHub.

PR Review Skill

Help Eddie (team leader) efficiently review PRs through independent deep code analysis. Produce structured review documents with git-truth validation, scope-aware findings, educational feedback, and developer growth tracking.

Settings

On startup, check for a settings file at .claude/pr-review.local.md (relative to the project root). If it exists, read the YAML frontmatter to configure behavior:

output_language — review feedback language (default: ko)
default_review_source — default --review-source value (default: all)
default_repo_path — default --repo-path for auto mode (avoids passing it every time)
full_review_dimensions / quick_review_dimensions — which of the 9 dimensions to check per mode
fix_forward_exclusions — file patterns that fix-forward should never auto-modify
track_developer_profiles — whether to create/update developer profiles

If the settings file doesn't exist, use the defaults defined in this skill. Settings from the file override the defaults. CLI flags (e.g., --review-source copilot) override settings.

Output language: Determined by output_language setting. Default: Korean with English technical terms (component names, TypeScript types, React concepts).

Modes

Full Review (default) — Complete PR review: git-truth validation, deep code review, AI review triage (GitHub Copilot and/or CodeRabbit), developer tracking
Quick Review (--quick) — Skip AI review triage + developer history. Focused git-truth validation and streamlined code review. Use for fast turnaround when provider output is unavailable or irrelevant. The output document must completely omit the AI review triage section (not include it with a "skipped" note — omit it entirely). Quick mode also reduces review depth: focus on the top 5 dimensions (Bugs & Correctness, Architecture/FSD, React & TypeScript, Error Handling, Performance) and skip Sibling Consistency, DRY/Duplication, UI/Design System, and Accessibility unless an obvious issue is spotted. This produces a meaningfully shorter and faster review, not just the same review minus the triage section.
Triage Only (--triage-only) — Only process GitHub Copilot and/or CodeRabbit comments without deep code review
Developer History (--history <github-id>) — Show a developer's accumulated review patterns
Auto Review (--auto <PR#>) — Worktree-aware end-to-end pipeline: fetch PR data, run the full review, prepare a managed Round N record, generate provider-neutral artifacts, preview mutations safely, and only perform live commit/push/reply/resolve when --live is explicitly present. Auto mode executes the workflow; it does not invent autonomous review judgment. See Step 11.

Read the full file on GitHub · 571 lines

Files

What ships with it

16 files 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.

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.

9d ago First seen · 571 lines · 151 tokens per session scan A e35e4acd3ae9

Subscribe to this mod's changes

pr-review is a skill published in the GitHub repository junyoung2015/pr-review-skill (4 stars, last pushed 5mo ago), licensed MIT. It adds 151 tokens to every session and 9,061 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 2026-08-31.

Claude Code Code review claude-skills coderabbit copilot-review

review-work

Post-implementation gate review: run manual QA on the real surface yourself, then launch ONE gate reviewer (never a panel) to audit goal, constraints, code quality, security, missed context, and QA evidence. Use before a PR handoff or when the user explicitly asks to review completed work.

code-yeongyu/oh-my-openagent · 63 tokens

one-way-door

Flags irreversible decisions before commit. Use for data models, infra, auth boundaries, API contracts, event schemas, CI/CD.

jamditis/claude-skills-journalism · 29 tokens

map-codebase

Deep architecture report that fans out parallel inspections across different aspects of the codebase (structure, tech stack, APIs, patterns, data flow, dependencies, testing) and synthesizes findings into a comprehensive document at .turbo/codebase-map.md and .turbo/codebase-map.html. Use when the user asks to "map…

tobihagemann/turbo · 106 tokens

critical-code-reviewer

Rigorously review code or pull requests for correctness, security, accessibility, maintainability, tests, and edge cases. Use when users request a critical code review, want a guided walkthrough of findings, need implementer-facing feedback, or want to prepare, create, or submit a GitHub pull request review.

posit-dev/skills · 67 tokens

reply-to-pr-threads

Draft, confirm, and post replies to GitHub PR review threads. Handles per-category reply formatting, re-fetches thread resolution state so auto-resolved threads are skipped, and posts via GraphQL. Use when the user asks to "reply to PR threads", "post PR thread replies", or "draft PR reply messages".

tobihagemann/turbo · 71 tokens

answer-reviewer-questions

For each reviewer question on a PR, recall implementation reasoning and compose a raw answer. Use when the user asks to "answer reviewer questions", "draft answers to PR questions", or "explain reviewer questions".

tobihagemann/turbo · 48 tokens