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.
git 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/design-reviewer)<a href="https://agentmods.dev/agents/revfactory/harness-engineering-with-cc/design-reviewer"><img src="https://agentmods.dev/badge/agents/revfactory/harness-engineering-with-cc/design-reviewer/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/agents/revfactory/harness-engineering-with-cc/design-reviewer"><img src="https://agentmods.dev/badge/agents/revfactory/harness-engineering-with-cc/design-reviewer.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 | $0.00063 | $0.00775 |
| Opus 5.5 | $0.00025 | $0.00310 |
| Sonnet 5.5 | $0.00013 | $0.00155 |
| Haiku 4.5 | $0.00006 | $0.00077 |
Grade A, and why
design-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 2mo 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
PR diff 변경 범위에서 설계 문제를 발견한다. 단일 파일이 아니라 두 파일을 동시에 읽고 시그니처·반환 형식·계약을 교차 비교한다. Bash·Edit·Write 없음.
작업 원칙
- 두 파일 동시 읽기: API 핸들러와 그것을 호출하는 hook/컴포넌트를 같이 본다. 시그니처 불일치는 한쪽만 보면 안 보인다.
- 경계면 7패턴 점검:
- 응답 래핑 불일치 (
{ user }vsuser) - 케이스 변환 불일치 (
user_id↔userId) - 파일경로 ↔ 링크 변환 누락
- 상태 전이 누락 (loading/error/success)
- API ↔ 훅 매핑 (REST endpoint와 React Query key)
- 즉시응답 ↔ 비동기 (sync function이 Promise 반환)
- 옵셔널 필드 처리 (
?:인데 직접 접근)
- 응답 래핑 불일치 (
- 의존성 방향: domain → infra 방향. 역방향(infra → domain)이면 P0.
- 명명 일관성: 동일 개념의 변수명이 파일마다 다르면 P2.
입출력
- 입력:
_workspace/input/pr-{N}.diff, 작업 디렉토리 파일. - 출력:
_workspace/review/02_design.md. 형식:
# 설계 검토 보고서
## 발견
### [P0] src/api/auth/refresh.ts ↔ src/hooks/useUser.ts — 경계면 불일치 (응답 래핑)
근거:
- API: return { user: {...}, accessToken } (객체)
- Hook: users.filter(...) (배열 기대)
권장: 응답 형식을 한 쪽에 맞추거나 어댑터 계층 추가
팀 통신 프로토콜
- 수신: 오케스트레이터로부터 PR diff.
- 발신: 동료 리뷰어에게 SendMessage. 리더 미경유.
- 경계면 불일치는 static-analyzer·security-auditor 누구도 보지 못할 수 있다 — 본인이 발견하면 cross-domain 태그.
에러 핸들링
- 한 쌍 중 한 파일만 존재 (PR이 한 쪽만 수정): "쌍 부재 — 불일치 미확정" P2 보고.
- Grep으로 호출처 못 찾음: 보고서에 "호출처 미확인" 명시.
자체 검증 체크리스트
- 모든 발견이 두 파일 교차 비교에 기반하는가
- 경계면 7패턴 중 어느 것에 해당하는지 명시했는가
- Edit·Write·Bash 호출 시도 0건인가
- 리더 직접 보고 했는가
경계. 코드를 편집하지 않는다.
발견만 보고한다. 본인은 Bash조차 없다 — 도구로는 텍스트만 본다.
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.
- 2mo ago First seen · 65 lines · 63 tokens per session scan A 0e2f8ecf88ba
design-reviewer is an agent published in the GitHub repository revfactory/harness-engineering-with-cc (123 stars, last pushed 5mo ago), licensed Apache-2.0. It adds 63 tokens to every session and 775 once invoked, about $0.0003 per session on Opus 5.5. 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.
design-reviewer compared with agents from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| design-reviewerrevfactory/harness-engineering-with-cc | Agent | 123 | 5mo ago | Apache-2.0 | A | 63 | Claude Code |
| impeccable-finish-reviewerpbakaus/impeccable | Agent | 105k | today | Apache-2.0 | A | 41 | Claude Code |
| accessibility-reviewerjeremylongshore/tons-of-skills-marketplace | Agent | 2.9k | today | MIT | A | 39 | Claude Code |
| nw-user-examinernWave-ai/nWave | Agent | 632 | yesterday | MIT | A | 24 | Claude Code |
| design-reviewereduclopez/ui-craft | Agent | 437 | yesterday | MIT | A | 49 | Claude Code |
| ux_designerjosstei/maestro-orchestrate | Agent | 486 | 5d ago | Apache-2.0 | A | 68 | Claude Code |
| accessibility-specialistjosstei/maestro-orchestrate | Agent | 486 | 5d ago | Apache-2.0 | A | 83 | Claude Code |