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 skills add revfactory/harness-engineering-with-cc --skill pr-review-orchestratorgit clone --depth 1 https://github.com/revfactory/harness-engineering-with-ccWrote 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/revfactory/harness-engineering-with-cc/pr-review-orchestrator)<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.
<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>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 | $0.00119 | $0.01337 |
| Opus 5 | $0.00060 | $0.00668 |
| Sonnet 5 | $0.00024 | $0.00267 |
| Haiku 4.5 | $0.00012 | $0.00134 |
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.
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_path또는 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
- 변경 파일 목록을 읽고 리뷰 범위를 확정한다.
_workspace/pr-review/디렉터리 존재를 확인한다.- diff가 없거나 변경 파일이 0개면 사용자에게 중단 사유를 보고한다.
- 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.
static-pass: static-reviewer 담당. diff 전체의 버그·성능·스타일 검토.security-pass: security-reviewer 담당. 외부 입력·권한·비밀 노출 검토.test-pass: test-reviewer 담당. 변경 파일과 테스트 매핑, 누락 테스트 검토.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"
}
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.
- 11d ago First seen · 121 lines · 119 tokens per session scan A 1a57c268d1f9
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.
Other skills, from other repositories
autoreview
Pre-commit/ship code review: Codex default; optional Claude or Pi.
omh-code-review
This is a Hermes-native code-review workflow skill.
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
code-reviewer
Code review specialist focused on patterns, bugs, security, and performance.
full-repo-review
Comprehensive four-wave review of all repo source files, producing a prioritized issue backlog.
agent-teams-simplify-and-harden
Implementation + audit loop using parallel agent teams with structured simplify, harden, and document passes. Spawns implementation agents to do the work, then audit agents to find complexity, security gaps, and spec deviations, then loops until code compiles cleanly, all tests pass, and auditors find zero issues or…