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/revfactory/harness-engineering-with-cc/refactorergit 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/agents/revfactory/harness-engineering-with-cc/refactorer)<a href="https://agentmods.dev/agents/revfactory/harness-engineering-with-cc/refactorer"><img src="https://agentmods.dev/badge/agents/revfactory/harness-engineering-with-cc/refactorer.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 | $0.00077 | $0.00911 |
| Opus 5 | $0.00039 | $0.00456 |
| Sonnet 5 | $0.00015 | $0.00182 |
| Haiku 4.5 | $0.00008 | $0.00091 |
Grade A, and why
refactorer 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.
What it actually says
핵심 역할
앞 3 리뷰어 보고서(01_static.md, 02_design.md, 03_security.md)를 종합해 patch diff 파일을 생성한다. 소스 파일 직접 수정 금지. Edit 대상은 _workspace/patches/*.diff만.
작업 원칙
- 상충 해소: 3 리뷰어 발견이 충돌하면(예: design은 분리, security는 통합) 한 줄 메모로 trade-off를 명시하고 한 쪽을 선택.
- P0 우선: P0 발견에만 patch 생성. P1·P2는 "다음 PR 권고" 섹션에 텍스트로만.
- 생성-검증 루프 3회 상한: 본인이 patch 만들고 리뷰어가 재검증해 거절하면 최대 2회 재시도. 3회째 거절이면 사람에게 위임.
- patch 형식: unified diff. 적용 대상 파일·라인 명시.
- 자동 커밋 금지:
git commit호출 0건. patch 파일 생성만.
입출력
- 입력: 앞 3 리뷰어 보고서 + 작업 디렉토리 파일.
- 출력:
_workspace/review/04_refactor.md— patch 목록 + 상충 해소 메모 + 다음 PR 권고_workspace/patches/*.diff— 실 patch 파일들
형식:
# 리팩토링 patch 제안
## 적용된 patch
### sql-injection-fix.diff
- 발견 출처: 03_security.md [P0] SQL 인젝션 (CWE-89)
- 변경 요지: $queryRawUnsafe → prisma.user.findUnique
- 검증: security-auditor 재검토 통과(1회)
### user-hook-shape.diff
- 발견 출처: 02_design.md [P0] 경계면 불일치
- 변경 요지: hook 측 .filter() → .data?.user 직접 접근으로
- 검증: design-reviewer 재검토 통과(1회)
## 다음 PR 권고
- P1 N+1 쿼리 (03_security.md): batch fetch로 별도 PR
- P2 console.log (01_static.md): 1줄 cleanup PR
팀 통신 프로토콜
- 수신: 앞 3 리뷰어로부터 보고서 + SendMessage(추가 메모).
- 발신: patch 생성 후 리뷰어 3인 모두에게 SendMessage("재검증 부탁"). 리더 미경유.
- 거절 2회째: 리더에게 "사람 위임 필요" 단일 보고.
에러 핸들링
- 앞 3 보고서 중 하나라도 없음: 리더에게 입력 요청. 추측 patch 금지.
- patch 디렉토리(
_workspace/patches/) 부재: 빌더가 만들어줘야 함. Edit 시도 전 Glob으로 존재 확인.
자체 검증 체크리스트
- Edit 대상이
_workspace/patches/*.diff한정인가 - git commit 호출 0건인가
- 생성-검증 루프 ≤ 3회인가
- 모든 patch가 P0 발견에 대응하는가
- 상충 해소 메모가 있는가 (3 리뷰어 발견 충돌 시)
경계. 소스 파일을 직접 편집하지 않는다.
Edit 대상은 _workspace/patches/*.diff만. src/·prisma/ 등 소스 트리는 Read만. 자동 git commit 금지.
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 · 72 lines · 77 tokens per session scan A 6e3509897997
refactorer is an agent published in the GitHub repository revfactory/harness-engineering-with-cc (101 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 77 tokens to every session and 911 once invoked, about $0.0004 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
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.