pr-review-orchestrator

pr-review-orchestrator is a skill for Claude Code from revfactory/harness-engineering-with-cc. It costs 119 tokens per session (1,337 once invoked), scanned A, original, Apache-2.0.

A pull-request review coordinator. A pull request is a proposed set of code changes; this tool reviews its diff and changed-file list through separate checks for code quality, security, and tests, then combines the findings.

In plain words
What is it for?
Use it to inspect pull requests or diffs, check security and regression risks, and produce static-analysis, security, testing, and final review files.
Why use it?
It gathers several review perspectives into one report and highlights risky changes without modifying the code.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Good fit Use it to inspect pull requests or diffs, check security and regression risks, and produce static-analysis, security, testing, and final review files.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/revfactory/harness-engineering-with-cc/pr-review-orchestrator
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.

Any agent
npx skills add revfactory/harness-engineering-with-cc --skill pr-review-orchestrator
Clone the repo
git clone --depth 1 https://github.com/revfactory/harness-engineering-with-cc

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 pr-review-orchestrator

README.md
[![agentmods](https://agentmods.dev/badge/skills/revfactory/harness-engineering-with-cc/pr-review-orchestrator/github.svg)](https://agentmods.dev/skills/revfactory/harness-engineering-with-cc/pr-review-orchestrator)
Your own site
<a href="https://agentmods.dev/skills/revfactory/harness-engineering-with-cc/pr-review-orchestrator"><img src="https://agentmods.dev/badge/skills/revfactory/harness-engineering-with-cc/pr-review-orchestrator/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 pr-review-orchestrator

Your own site · 80×15
<a href="https://agentmods.dev/skills/revfactory/harness-engineering-with-cc/pr-review-orchestrator"><img src="https://agentmods.dev/badge/skills/revfactory/harness-engineering-with-cc/pr-review-orchestrator.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 119 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,337 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 $0.00119 $0.01337
Opus 5 $0.00060 $0.00668
Sonnet 5 $0.00024 $0.00267
Haiku 4.5 $0.00012 $0.00134

Measured 11d ago against content hash 1a57c268d1f9, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

pr-review-orchestrator 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 11d 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.

ex-06-12-pr-review-skill-md/.claude/skills/pr-review-orchestrator/SKILL.md · 121 lines

How it starts

The opening of the file, as written. The whole thing — 121 lines — stays where its author put it; the contents beside it link to each section on GitHub.

PR Review Orchestrator

목표

변경사항 하나를 네 에이전트 팀으로 검토한다. 오케스트레이터는 직접 코드를 고치지 않는다. 팀을 만들고, 작업 큐를 배치하고, 팀원 간 직접 메시지를 허용하고, 최종 리포트만 통합한다.

입력

  • diff_path 또는 PR diff 텍스트
  • 변경 파일 목록
  • 선택 입력: 리뷰 기준, 금지된 변경 영역, 릴리스 위험도

산출물

  • _workspace/pr-review/static.md
  • _workspace/pr-review/security.md
  • _workspace/pr-review/tests.md
  • _workspace/pr-review/final-review.md
  • _workspace/pr-review/team-log.jsonl

Phase 0. 사전 조건

  1. 변경 파일 목록을 읽고 리뷰 범위를 확정한다.
  2. _workspace/pr-review/ 디렉터리 존재를 확인한다.
  3. diff가 없거나 변경 파일이 0개면 사용자에게 중단 사유를 보고한다.
  4. 파일 수가 40개를 넘으면 먼저 범위를 나누고, 이번 실행에서는 가장 위험도가 높은 묶음 하나만 리뷰한다.

Phase 1. 팀 생성

TeamCreate로 pr-review-team을 만든다. 팀원 네 명을 AgentTool로 스폰한다.

이름 역할 출력
static-reviewer 버그·성능·스타일 검토 _workspace/pr-review/static.md
security-reviewer 입력 검증·권한·비밀 노출 검토 _workspace/pr-review/security.md
test-reviewer 테스트 영향·누락 회귀 검토 _workspace/pr-review/tests.md
review-integrator 세 리포트 병합·중복 제거 _workspace/pr-review/final-review.md

각 팀원 프롬프트에는 공통 규칙을 넣는다.

  • 발견 즉시 관련 팀원에게 SendMessage로 알린다.
  • 최종 판단은 파일에 저장한다.
  • Critical 발견 시 오케스트레이터와 관련 팀원에게 동시에 보고한다.
  • 코드 수정은 하지 않는다.

Phase 2. 작업 큐 배치

TaskCreate로 네 작업을 만든다.

  1. static-pass: static-reviewer 담당. diff 전체의 버그·성능·스타일 검토.
  2. security-pass: security-reviewer 담당. 외부 입력·권한·비밀 노출 검토.
  3. test-pass: test-reviewer 담당. 변경 파일과 테스트 매핑, 누락 테스트 검토.
  4. integrate-review: review-integrator 담당. 앞 세 작업 완료 후 실행. depends_on = ["static-pass", "security-pass", "test-pass"].

Phase 3. 팀원 간 메시지 규칙

SendMessage는 리더를 거치지 않는다.

  • static-reviewer가 데이터 구조(shape) 변경을 발견하면 test-reviewer에게 테스트 영향 확인을 요청한다.
  • security-reviewer가 인증·권한 변경을 발견하면 test-reviewer에게 보안 회귀 테스트 존재 여부를 묻는다.
  • test-reviewer가 테스트 불가능한 설계를 발견하면 static-reviewer에게 구조 리스크 확인을 요청한다.
  • Critical 이슈는 오케스트레이터에도 요약 메시지를 보낸다.

메시지 형식은 고정한다.

{
    "type": "finding",
    "severity": "Critical|High|Medium|Low",
    "file": "path/to/file.ts",
    "line": 42,
    "claim": "문제를 주장하는 한 문장",
    "request": "상대 팀원이 확인할 질문"
}

Read the full file on GitHub · 121 lines

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. 11d ago First seen · 121 lines · 119 tokens per session scan A 1a57c268d1f9

Subscribe to this mod's changes

pr-review-orchestrator is a skill published in the GitHub repository revfactory/harness-engineering-with-cc (106 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 119 tokens to every session and 1,337 once invoked, about $0.0006 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.