Borrowing it
Nothing to install: this file belongs to easyhooon/dari. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/easyhooon/dari/main/.claude/skills/resolve-coderabbit-review/SKILL.mdgit clone --depth 1 https://github.com/easyhooon/dariWrote 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.
[](https://agentmods.dev/skills/easyhooon/dari/resolve-coderabbit-review)<a href="https://agentmods.dev/skills/easyhooon/dari/resolve-coderabbit-review"><img src="https://agentmods.dev/badge/skills/easyhooon/dari/resolve-coderabbit-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.
<a href="https://agentmods.dev/skills/easyhooon/dari/resolve-coderabbit-review"><img src="https://agentmods.dev/badge/skills/easyhooon/dari/resolve-coderabbit-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00038 | $0.04291 |
| Opus 5.5 | $0.00015 | $0.01716 |
| Sonnet 5.5 | $0.00008 | $0.00858 |
| Haiku 4.5 | $0.00004 | $0.00429 |
Grade A, and why
resolve-coderabbit-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 3d 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.
How it starts
The opening of the file, as written. The whole thing — 397 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CodeRabbit 리뷰 반영 Skill
현재 브랜치의 PR에 달린 CodeRabbit 미해결 코멘트를 수집하고, 각 코멘트를 분석하여 코드를 수정하거나 거절 사유를 댓글로 남긴다.
인자
$ARGUMENTS— PR 번호 (선택). 생략하면 현재 브랜치의 PR을 자동 감지한다.--brief— 최종 요약에서 코드레벨 수정 상세 설명을 생략한다. 기본값은 코드레벨 상세 설명 포함.
실행 절차
1단계: PR 정보 확인
PR 번호가 인자로 주어지면 그것을 사용하고, 없으면 현재 브랜치의 PR을 자동 감지한다.
# 인자가 없을 때 자동 감지
gh pr view --json number,headRefName,baseRefName,url,isDraft
PR이 없으면 사용자에게 알리고 중단한다.
Draft PR인 경우 (isDraft == true): "Draft PR에는 리뷰 반영을 수행하지 않습니다." 메시지를 출력하고 중단한다.
1.5단계: 학습 패턴 로드
learned-patterns.md 파일이 존재하면 읽어서, 이전에 반복된 패턴 정보를 4단계 판단에 참고한다. 이전에 일관되게 반영 또는 거절한 패턴이 있다면 같은 방향으로 판단하는 것을 기본으로 한다.
2단계: 미해결 CodeRabbit 코멘트 수집
아래 GraphQL 쿼리로 미해결(isResolved=false) 스레드 중 CodeRabbit가 작성한 것만 필터링한다.
gh api graphql -f query='
{
repository(owner: "{OWNER}", name: "{REPO}") {
pullRequest(number: {PR_NUMBER}) {
reviewThreads(first: 100) {
nodes {
id
isResolved
comments(first: 10) {
nodes {
databaseId
author { login }
body
path
line
originalLine
diffHunk
}
}
}
}
}
}
}'
필터 조건:
isResolved == false- 스레드의 첫 번째 코멘트 작성자가
coderabbitai[bot]또는coderabbitai - CodeRabbit의 PR 요약 코멘트(리뷰 본문이 아닌 일반 요약)는 제외
- 이미 처리된 코멘트는 스킵: 스레드 내 대댓글에 아래 문구가 포함되어 있으면 이전 실행에서 이미 처리된 것이므로 수집 대상에서 제외한다:
✅ Addressed in— 이미 반영됨 (현행 영어 템플릿)✅+반영완료— 이미 반영됨 (구 한글 템플릿, 하위 호환)Thanks for the suggestion. After review, we've decided not to apply this change.— 이미 거절됨 (현행 영어 템플릿)해당 제안은 검토 결과 현재 반영하지 않았습니다— 이미 거절됨 (구 한글 템플릿, 하위 호환)
수집된 코멘트가 없으면 "미해결 CodeRabbit 코멘트가 없습니다." 출력 후 종료한다.
3단계: 중요도별 정렬
CodeRabbit 코멘트 본문에서 중요도를 판단하여 우선순위순으로 정렬한다:
- 보안/크래시 관련 — 최우선 (NPE, 인젝션, 메모리릭 등 키워드 감지)
- 버그/로직 오류 관련 — 높음
- 코드 품질/가독성 관련 — 보통
- 스타일/컨벤션 관련 — 낮음
코멘트 본문에 명시적 심각도 라벨이 있으면 해당 라벨을 우선 사용한다.
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.
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.
- 3d ago First seen · 397 lines · 38 tokens per session scan A a908c88d6359
resolve-coderabbit-review is a skill published in the GitHub repository easyhooon/dari (38 stars, last pushed today), licensed Apache-2.0. It adds 38 tokens to every session and 4,291 once invoked, about $0.0002 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 2026-10-26.
Other skills, from other repositories
shepherd
Use when asked to shepherd, babysit, monitor, or poll open pull requests or merge requests, including triaging review feedback, CI failures, and routine follow-up.
kotlin-concurrency-and-flow
Use when writing or reviewing Kotlin coroutine scope ownership, raw Thread or Executor work, init launches, non-suspending launch APIs, runBlocking, cancellation, StateFlow, SharedFlow, Channel, stateIn, SharingStarted, state updates, or one-shot events.
kotlin-api-design
Use when designing or reviewing Kotlin function ownership, member or extension functions, factories, single-field domain types, value classes, data classes, Kotlin Multiplatform expect/actual declarations, or platform service boundaries.
solid-expert
Kotlin & Compose Multiplatform SOLID Expert. Applies SOLID principles with a strong preference for composition over inheritance (COI) to build professional, clean, maintainable, and testable mobile/multiplatform applications. Use when: designing architectures, refactoring deep class hierarchies, debugging class…
nightly-audit-engineer-ops
A workflow for reviewing code for reproducible quality problems and recording the evidence behind each finding. It follows data through inputs, permissions, storage, asynchronous work, and recovery, then suggests the smallest authorized fix.
engineer-bot-evidence
A local checker for confirming that delivery checks and supporting evidence belong to the current software version. It does not contact Git, continuous-integration systems, or the internet.