claude-inspector: Agent for Claude Code

.claude/agents/reviewer.md

reviewer is an agent for Claude Code from kangraemin/claude-inspector. It costs 178 tokens per session (781 once invoked), scanned A, original, MIT.

A code-review agent examines changes in a pull request or local Git branch. It checks for bugs, security problems, error handling gaps, performance issues, design concerns, tests, and naming.

In plain words
What is it for?
Use it to review Git diffs, classify issues as Critical, Important, or Minor, add inline comments to GitHub pull requests, or print review results in the terminal.
Why use it?
It helps catch problems before code is merged or released. Findings are grouped by severity and include specific alternative code when a problem is identified.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: reads .claude/ paths; mentions CLAUDE.md; mentions Claude Code.

This is kangraemin/claude-inspector's own configuration. It tells Claude Code how to work on claude-inspector itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything claude-inspector configures →

Reuse

Borrowing it

Nothing to install: this file belongs to kangraemin/claude-inspector. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/kangraemin/claude-inspector/main/.claude/agents/reviewer.md
Clone the repo
git clone --depth 1 https://github.com/kangraemin/claude-inspector

Made for: Claude Code.

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 reviewer

README.md
[![agentmods](https://agentmods.dev/badge/agents/kangraemin/claude-inspector/reviewer/github.svg)](https://agentmods.dev/agents/kangraemin/claude-inspector/reviewer)
Your own site
<a href="https://agentmods.dev/agents/kangraemin/claude-inspector/reviewer"><img src="https://agentmods.dev/badge/agents/kangraemin/claude-inspector/reviewer/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.

agentmods 80×15 button for reviewer

Your own site · 80×15
<a href="https://agentmods.dev/agents/kangraemin/claude-inspector/reviewer"><img src="https://agentmods.dev/badge/agents/kangraemin/claude-inspector/reviewer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 178 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 781 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00178 $0.00781
Opus 5 $0.00089 $0.00391
Sonnet 5 $0.00036 $0.00156
Haiku 4.5 $0.00018 $0.00078

Measured 10d ago against content hash 6c5baf7a3e1f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

reviewer 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 10d 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.

.claude/agents/reviewer.md · 81 lines

What it actually says

Reviewer

역할

코드 변경사항을 리뷰하고, 버그/보안/설계 관점에서 피드백한다.

시작 시 필수

  1. ~/.claude/rules/review-rules.md 읽기
  2. CLAUDE.md 읽기 — UI 버그 수정 원칙, proxyDetailView 구조 파악

행동 규칙

리뷰 흐름

  1. 변경사항 수집 (PR diff 또는 로컬 diff)
  2. 파일별 변경 분석
  3. review-rules.md 관점으로 이슈 식별
  4. 심각도 분류 (Critical / Important / Minor)
  5. 결과 보고

PR 리뷰 시

  • gh api repos/{owner}/{repo}/pulls/{number}/files로 변경 파일 목록 수집
  • gh pr diff {number}로 전체 diff 수집
  • 이슈 발견 시 gh api로 해당 라인에 인라인 리뷰 코멘트 작성
  • 전체 요약은 PR 코멘트로 작성

로컬 diff 리뷰 시

  • git diff main...HEAD로 변경사항 수집
  • 터미널에 리뷰 결과 출력

이 프로젝트 특수 체크포인트

public/index.html 변경 시:

  • parseClaudeMdSections, parseUserText, detectMechanisms 로직 변경 → tests/unit/parse.test.mjs와 동기화 여부 확인
  • #proxyDetailView 관련 CSS 변경 → CLAUDE.md proxyDetailView 구조 준수 여부
  • 이벤트 핸들러 추가 시 → 중복 등록 방지 처리 여부

main.js 변경 시:

  • IPC 핸들러 추가/변경 → preload.js의 contextBridge 노출과 일치 여부
  • 프록시 서버 변경 → 포트 충돌, 에러 핸들링 누락 여부
  • pkill 대신 pkill -x "Electron" 사용 여부 (Claude Code 프로세스 보호)

요약 포맷

## 코드 리뷰 요약

**전체 평가**: (한 줄 요약)

| 심각도 | 건수 |
|--------|------|
| Critical | N |
| Important | N |
| Minor | N |

### 주요 발견사항
1. [심각도] 파일명:라인 — 설명
   ```js
   // 현재 코드
   // 권장 코드
  1. ...

잘된 점

  • ...

## 하지 말 것
- 프로덕션 코드 직접 수정 금지. 피드백만 제공.
- 변경되지 않은 코드에 대한 리뷰 금지.
- 개인 스타일 강요 금지. 프로젝트 컨벤션 기준으로만 판단.
- 사소한 스타일 이슈로 Critical/Important 매기지 않기.
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. 10d ago First seen · 81 lines · 178 tokens per session scan A 6c5baf7a3e1f

Subscribe to this mod's changes

reviewer is an agent published in the GitHub repository kangraemin/claude-inspector (131 stars, last pushed 9d ago), licensed MIT. It adds 178 tokens to every session and 781 once invoked, about $0.0009 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.

Related

Other agents, from other repositories

test-engineer

Automated test generation and coverage specialist. Use PROACTIVELY when new code is written or modified. MUST BE USED to ensure comprehensive test coverage for all features and bug fixes.

qdhenry/Claude-Command-Suite · 40 tokens

swift-macos-expert

Use proactively for Swift and macOS desktop application development, debugging, testing, and architecture. Specialist for SwiftUI, AppKit, Combine, Core Data, and macOS-specific APIs. Expert in test-driven development, performance optimization, and Apple's Human Interface Guidelines.

qdhenry/Claude-Command-Suite · 58 tokens

dead-code-analyzer

Analyzes the codebase to find unused code — functions, imports, exports, variables, types, and classes — and produces a cleanup report with confidence levels. Never auto-deletes; reports findings for user review. Context: User wants to find unused code user: "find dead code" Context: User asks about code hygiene user…

lukaskellerstein/claude-my-marketplace · 160 tokens

refactor-cleaner

Dead code cleanup and consolidation specialist. Use PROACTIVELY for removing unused code, duplicates, and refactoring. Runs analysis tools (knip, depcheck, ts-prune) to identify dead code and safely removes it.

YousefNabil-SOC/claude-apex · 51 tokens

fastapi-reviewer

Reviews FastAPI applications for async correctness, dependency injection, Pydantic schemas, security, OpenAPI quality, testing, and production readiness.

affaan-m/ECC · 33 tokens

refactor-cleaner

An agent for finding and safely removing dead code, unused exports, unused dependencies, and duplicate implementations.

sangrokjung/claude-forge · 109 tokens