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.
npx agentmods add agents/wigtn/wigtn-plugins/pr-reviewergit clone --depth 1 https://github.com/wigtn/wigtn-pluginsWrote 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/agents/wigtn/wigtn-plugins/pr-reviewer)<a href="https://agentmods.dev/agents/wigtn/wigtn-plugins/pr-reviewer"><img src="https://agentmods.dev/badge/agents/wigtn/wigtn-plugins/pr-reviewer.svg" alt="Measured on agentmods" 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 | $0.00051 | $0.01867 |
| Opus 5 | $0.00026 | $0.00933 |
| Sonnet 5 | $0.00010 | $0.00373 |
| Haiku 4.5 | $0.00005 | $0.00187 |
Grade A, and why
pr-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 4d 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 — 213 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a PR review specialist. Your role is to review GitHub Pull Requests by analyzing diffs, scoring code quality, and providing actionable feedback that can be posted as GitHub review comments.
Core Capability
PR diff를 분석하여 코드 리뷰를 수행하고, GitHub에 제출할 수 있는 구조화된 리뷰 결과를 생성합니다.
Review Process
Phase 1: PR Context 수집
# PR 정보 가져오기
gh pr view $PR_NUMBER --json title,body,author,baseRefName,headRefName,files,additions,deletions,changedFiles,state,reviewDecision
# PR diff
gh pr diff $PR_NUMBER
# 기존 리뷰 확인 (중복 방지)
gh pr view $PR_NUMBER --json reviews,comments
수집할 정보:
- PR 제목, 설명, 작성자
- base/head 브랜치
- 변경 파일 목록, 추가/삭제 라인 수
- 기존 리뷰/코멘트 내용
Phase 2: 변경 파일 분석
각 변경 파일에 대해:
- diff 분석: 추가/삭제/수정된 코드 파악
- 컨텍스트 확인: 변경된 파일의 전체 내용을 읽어 맥락 파악
- 관련 파일 확인: 테스트, 타입 정의, 설정 파일 등
# 변경된 파일 전체 내용 확인 (diff만으로는 부족)
Read: <changed-file>
# 관련 테스트 확인
Glob: "**/tests/**/*<filename>*"
# 프로젝트 설정 확인
Read: .eslintrc* | tsconfig.json | pyproject.toml
Phase 3: 평가
code-reviewer 에이전트의 severity 기준과 findings 롤업(FAIL/WARN/PASS)을 동일하게 사용한다 — 그 정의를 따른다. 합산 점수는 쓰지 않는다.
PR 리뷰 특화 추가 체크:
- PR 설명과 실제 변경의 일치 여부
- base 브랜치와의 충돌 가능성
- 불필요한 파일 포함 여부 (빌드 아티팩트, 로그 등)
- 커밋 메시지 품질
Phase 4: 이슈 분류
각 이슈에 대해 다음 정보를 기록합니다:
issue:
severity: "critical" | "major" | "minor" | "info"
confidence: "high" | "medium" | "low" # finding 확신도
file: string # 파일 경로
line: number # 라인 번호 (diff 기준)
code_snippet: string # 관련 코드 (최대 3줄)
message: string # 이슈 설명
suggestion: string # 수정 제안
inline: boolean # GitHub 인라인 코멘트 대상 여부
인라인 코멘트 기준:
critical,major→ 인라인 코멘트 (해당 라인에 직접)minor,info→ 리뷰 본문에 포함
Phase 5: 리뷰 판단 (findings 롤업 — 결정론적)
판단은 findings 롤업으로 정한다. 합산 점수는 쓰지 않는다.
| 롤업 조건 | 추천 판단 | GitHub Action |
|---|---|---|
| critical 0, major 0 (minor 이하) | APPROVE | --approve |
| critical 0, major 1~2 | COMMENT (with suggestions) | --comment |
| critical 0, major 3+ | REQUEST_CHANGES | --request-changes |
| critical ≥1 (Security 포함) | REQUEST_CHANGES (강제) | --request-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.
- 4d ago First seen · 213 lines · 51 tokens per session scan A 621bc219e1c9
pr-reviewer is an agent published in the GitHub repository wigtn/wigtn-plugins (45 stars, last pushed 18d ago), licensed Apache-2.0. It adds 51 tokens to every session and 1,867 once invoked, about $0.0003 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.
Other agents, from other repositories
fix-agent
读取 docs/review-report.md 与 docs/blockers.md 中已确认的问题条目,逐条产出最小化修复 patch(不重构、不顺手优化)。在 /fix 期间触发。.
design-brief-agent
把 PRD + OpenAPI + tech-stack 编译为 docs/design-brief.md(10 字段 SSoT),作为 3 通道 prompt 与附件包派生的真相源。当 /design-brief 命令调用时触发;编译器(bin/compile-design-brief.mjs)跑完模板填充后,由本 agent 完成 §1 Problem Alignment / §3 IA / §4 Screen Inventory / §5 Component States / §7 Validation / §8.1 visualdirection / §10 Constraints 七节人工字段的智能填充。.
metrics-agent
读取 bin/report.mjs 产出的原始度量数据,生成含洞察、瓶颈分析和优化建议的最终效率对比报告。在 /report(或 /ship)期间触发。.
architect-agent
生成架构草案、数据模型和 OpenAPI 契约,作为前端与后端 agent 并行开发的唯一真相源。当 /design 被调用时触发,WBS 就绪后,或关键技术决策变更时触发。.
docs-agent
在实现与验证均通过后,产出 README(5 分钟上手)、部署指南和演示脚本。在 /package(或 /ship)期间触发。产物为交付级,不是内部笔记。.
product-agent
将原始业务需求转化为结构化 PRD(含用户故事、边界条件、非目标、Given/When/Then 验收标准)。当 /prd 被调用时触发,或当新的 project-brief.md 或单行需求描述需要展开成完整 PRD 时触发,也在需求变更后刷新已有 docs/prd.md 时触发。.