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 commands/wigtn/wigtn-plugins/review-prgit 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/commands/wigtn/wigtn-plugins/review-pr)<a href="https://agentmods.dev/commands/wigtn/wigtn-plugins/review-pr"><img src="https://agentmods.dev/badge/commands/wigtn/wigtn-plugins/review-pr.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 | $0.00068 | $0.02749 |
| Opus 5 | $0.00034 | $0.01375 |
| Sonnet 5 | $0.00014 | $0.00550 |
| Haiku 4.5 | $0.00007 | $0.00275 |
Grade A, and why
review-pr 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 — 282 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Review PR
GitHub Pull Request를 터미널에서 리뷰하고 피드백을 남깁니다.
Pipeline Position
[/prd] → [/implement] → [/auto-commit] → PR 생성 이후, 동료가 [/review-pr #123]으로 리뷰 결과 + 코멘트를 남기는 단계.
Usage
/review-pr 123 # PR #123 리뷰
/review-pr 123 --level 3 # 심층 리뷰 (Level 3)
/review-pr 123 --level 4 # 아키텍처 리뷰 (Level 4)
/review-pr 123 --approve # 리뷰 후 자동 승인 (findings PASS 시)
/review-pr 123 --comment-only # GitHub에 코멘트만, 승인/거절 안함
/review-pr https://github.com/org/repo/pull/123 # URL로도 가능
Parameters
$ARGUMENTS: PR 번호 또는 GitHub PR URL (필수)--level <1-4>: 리뷰 깊이 (기본: 2)--approve: findings 롤업 PASS(critical 0, major 0) 시 자동 Approve--comment-only: GitHub에 코멘트만 남기고 승인/거절 판단 안함--no-comment: GitHub에 코멘트 남기지 않음 (로컬 결과만)--files <glob>: 특정 파일만 리뷰 (예:"src/**/*.ts")
Protocol
Step 1: PR 정보 수집
# PR 메타데이터 가져오기
gh pr view $PR_NUMBER --json title,body,author,baseRefName,headRefName,files,additions,deletions,changedFiles,reviewDecision,reviews,state
# PR diff 가져오기
gh pr diff $PR_NUMBER
# PR에 달린 기존 리뷰/코멘트 확인
gh pr view $PR_NUMBER --json comments,reviews
PR 상태 확인:
state: MERGED→ "이미 머지된 PR입니다. 리뷰를 계속할까요?" (AskUserQuestion)state: CLOSED→ "닫힌 PR입니다. 리뷰를 계속할까요?" (AskUserQuestion)state: OPEN→ 정상 진행
정보 요약 출력:
┌─────────────────────────────────────────────────────────────┐
│ PR #123: Add user authentication API │
├─────────────────────────────────────────────────────────────┤
│ Author: @username │
│ Branch: feature/user-auth → main │
│ Files: 5 changed (+234, -12) │
│ Status: OPEN | Reviews: 0 approved, 0 changes requested │
└─────────────────────────────────────────────────────────────┘
Step 2: 변경사항 분석
연동:
pr-reviewer에이전트를 호출합니다.
리뷰 레벨별 동작:
| Level | 분석 범위 | 에이전트 |
|---|---|---|
| 1 (Quick) | 린트 수준, 포맷팅, 명명 규칙 | pr-reviewer 단독 |
| 2 (Standard) | 5-Category 전체 평가 | pr-reviewer (병렬 이득이 크면 병렬) |
| 3 (Deep) | 호출 체인, 에지 케이스, 보안 | pr-reviewer + deep-review 스킬 |
| 4 (Architecture) | SOLID, 계층 위반, 확장성 | pr-reviewer + architecture-review 스킬 |
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 · 282 lines · 68 tokens per session scan A 0f5b503cb94d
review-pr is a command published in the GitHub repository wigtn/wigtn-plugins (45 stars, last pushed 18d ago), licensed Apache-2.0. It adds 68 tokens to every session and 2,749 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 commands, from other repositories
kickoff
新项目起手 · 串行跑 /prd → /wbs → /design;默认 interactive(每步决策门),--auto 跳过决策门。.
verify
并行验证 · 同一轮对话同时派发 test-agent 与 review-agent。.
ship
交付出包 · 串行跑 /package → /report,并打包所有交付产物。.
build-web
前端实现 · main thread + 6-phase(EXPLORE→PLAN→APPROVE→IMPLEMENT→VERIFY→SUMMARY),不再黑盒派发 subagent.
design-execute
通道执行器 · 派生 3 通道(claude-design / figma / v0)附件包,引导用户投喂工具并回贴结果.
design
架构师命令 · 生成架构草案 + OpenAPI 契约 + 数据模型。.