git-review

git-review is a skill for Claude Code, Codex from scroogy-dev/scroogy-agent-skills. It costs 35 tokens per session (3,093 once invoked), scanned A, original, Apache-2.0.

A two-stage workflow for reviewing a pull request or your own pending code changes. A pull request is a proposed code change, and the workflow checks both its fit with business rules and its technical quality.

In plain words
What is it for?
Use it for PR reviews and self-reviews to check requirements, domain behavior, code correctness, affected call flows, and consistency with documented architecture.
Why use it?
A code review can miss product requirements or implementation problems when it focuses on only one side. This records the final review result and compares the changes with project contracts, domain documents, code paths, and architecture decisions.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

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/scroogy-dev/scroogy-agent-skills/git-review
Any agent
npx skills add scroogy-dev/scroogy-agent-skills --skill git-review
Clone the repo
git clone --depth 1 https://github.com/scroogy-dev/scroogy-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.

agentmods badge for git-review

README.md
[![agentmods](https://agentmods.dev/badge/skills/scroogy-dev/scroogy-agent-skills/git-review.svg)](https://agentmods.dev/skills/scroogy-dev/scroogy-agent-skills/git-review)
Your own site
<a href="https://agentmods.dev/skills/scroogy-dev/scroogy-agent-skills/git-review"><img src="https://agentmods.dev/badge/skills/scroogy-dev/scroogy-agent-skills/git-review.svg" alt="Measured on agentmods" height="20"></a>
Per session 35 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,093 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00035 $0.03093
Opus 5 $0.00017 $0.01546
Sonnet 5 $0.00007 $0.00619
Haiku 4.5 $0.00003 $0.00309

Measured 6d ago against content hash b7bfdc31fdd7, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

git-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 6d ago.

The scan reads SKILL.md. This mod also ships 2 executable files (scripts/classify-risk.sh, tests/run-tests.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.

git-review/SKILL.md · 204 lines

How it starts

The opening of the file, as written. The whole thing — 204 lines — stays where its author put it; the contents beside it link to each section on GitHub.

개요

PR 리뷰와 Self 리뷰 모두 비즈니스 리뷰테크 리뷰 두 단계로 진행합니다. 리뷰 결과는 .ai/99_workspace/temp_review_result.md에 최종 의견·요약을 맨 위에 두는 역피라미드 구조로 기록합니다 (구조는 "결과 기록 형식" 참조).

관련 skill

  • git-review-context (선택): 사용자가 별도로 요청한 경우에만 실행합니다. git-review가 자동으로 호출하지 않습니다.
  • ai-workspace (권장): .ai/30_contract/, .ai/40_domain/ 경로의 문서를 비즈니스 리뷰에 참조합니다.

참조 문서

  • 공통 규칙: .ai/10_rules/context-loading.md — 있으면 따르며, 이미 적재되어 있으면 재로딩하지 않습니다.
  • 스킬 고유 추가 참조:
    • .ai/30_contract/index.md, .ai/40_domain/index.md — 비즈니스 리뷰 (index 먼저 → 관련 파일만 선택적으로)
    • .ai/60_codebase/index.md — 테크 리뷰 호출 흐름 파악
    • .ai/50_adr/index.md — 테크 리뷰에서 관련 ADR 정합성 대조 (index 먼저 → 관련 ADR만 선택적으로)
    • .ai/10_rules/writing-principles.md·.ai/10_rules/writing-principles-local.md — 있으면 산출물 작성 원칙으로 참조 (충돌 시 local 우선; 없으면 본문의 "산출물 접기 기준"이 기본값)

리뷰 모드

PR 리뷰(타인의 PR을 리뷰)와 Self 리뷰(PR 올리기 전 작성자 본인이 수행) 모두 아래 비즈니스 리뷰 → 테크 리뷰 공통 절차를 따릅니다.


비즈니스 리뷰

목적: 변경 사항이 .ai/30_contract/.ai/40_domain/에 기록된 소프트웨어 계약·도메인 지식과 일치하는지 검증하고, 차이가 있는 경우 AI가 이해한 내용을 정리하여 해당 문서에 반영합니다.

1단계: 참조 문서 확보

아래 순서로 비즈니스 리뷰에 필요한 참조 문서를 확보합니다.

  1. .ai/30_contract/index.md.ai/40_domain/index.md를 읽어 각 파일의 내용을 파악합니다.
    • index.md는 디렉토리 내 파일별 요약 목차입니다.
    • 리뷰 대상 변경사항과 관련 있는 파일만 선택적으로 읽어옵니다.
    • 사용자가 특정 .md 파일을 직접 지정한 경우 해당 파일도 읽어옵니다.
  2. index.md가 없거나 참조할 문서가 부족한 경우 → 문서 부재 시 처리 진행

문서 부재 시 처리

index.md나 관련 문서가 없어 도메인/계약 정보를 참조할 수 없는 경우:

  1. 리뷰 대상 변경 파일(소스 파일 포함)을 읽어 도메인 지식과 소프트웨어 계약을 추정합니다.
  2. 추정 내용을 아래 임시 파일에 정리합니다.
    • .ai/99_workspace/temp_domain.md — 도메인 관련 내용
    • .ai/99_workspace/temp_contract.md — 소프트웨어 계약 관련 내용
  3. 사용자와 내용을 검토하고 확정합니다.
  4. 확정된 내용을 아래 위치로 이동합니다. 파일명과 하위 경로는 내용에 맞게 선택합니다.
    • .ai/30_contract/ 하위 적절한 위치
    • .ai/40_domain/specs/ 또는 .ai/40_domain/policies/ 하위 적절한 위치
  5. 이동 완료 후 temp_domain.md, temp_contract.md를 삭제합니다.
  6. 1단계로 돌아가 확보된 문서를 기반으로 비즈니스 리뷰를 진행합니다.

2단계: 비즈니스 리뷰 수행

Read the full file on GitHub · 204 lines

Files

What ships with it

3 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.

  1. 6d ago First seen · 204 lines · 35 tokens per session scan A b7bfdc31fdd7

Subscribe to this mod's changes

git-review is a skill published in the GitHub repository scroogy-dev/scroogy-agent-skills (2 stars, last pushed 5d ago), licensed Apache-2.0. It adds 35 tokens to every session and 3,093 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 2026-08-31.

Related

Other skills, from other repositories

review-implement-phase

Implements triaged review actions, commits focused fixes, and posts Done plus resolves threads. Use when the user wants only the implementation phase of the review-framework workflow.

prisma/orm · 38 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

verify-behavior

Verify or reproduce visible product behavior by driving the real UI with pi-computer-use's checked tools, requiring verified expect postconditions and durable state evidence for meaningful UI flows. Use when triage needs visual reproduction, implementation needs behavioral proof, review needs interactive confirmation…

nicknisi/dotfiles · 68 tokens

github-contributor

End-to-end playbook for shipping high-quality pull requests to open-source projects you don't maintain — discovery, CONTRIBUTING compliance, PR-size check, minimal-diff implementation, PR description with AI-assisted disclosure, conflict resolution, and post-submission maintainer interaction. Use whenever creating…

daymade/claude-code-skills · 133 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

write-pr

Reference standards for writing pull request titles and descriptions in the tldraw repository, plus the pre-flight comment sweep over the diff. Use as supporting guidance when another skill or workflow needs PR content standards, not as the user-facing create/update PR workflow.

tldraw/tldraw · 53 tokens