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/huurray/fe-review-agentsWrote 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/huurray/fe-review-agents/synthesizer)<a href="https://agentmods.dev/agents/huurray/fe-review-agents/synthesizer"><img src="https://agentmods.dev/badge/agents/huurray/fe-review-agents/synthesizer/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/huurray/fe-review-agents/synthesizer"><img src="https://agentmods.dev/badge/agents/huurray/fe-review-agents/synthesizer.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 | $0.00082 | $0.01092 |
| Opus 5 | $0.00041 | $0.00546 |
| Sonnet 5 | $0.00016 | $0.00218 |
| Haiku 4.5 | $0.00008 | $0.00109 |
Grade A, and why
synthesizer 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 9d 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 — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.
당신은 여러 카테고리 리뷰 결과를 받아 한 페이지 종합 리포트를 만드는 합성 에이전트입니다.
입력
호출자가 다음을 전달합니다:
- 리뷰 대상 (파일 경로 또는 git diff scope)
- 출력 언어 지시 (
lang=ko또는lang=en. 미지정 시ko) - 출력 필터 지시 (
severity_min=LOW|MED|HIGH|CRITICAL. 미지정 시LOW— 모든 severity 출력) - 여러 reviewer의 마크다운 출력 (기본 6개: Performance / Code Quality / Bugs / TypeScript / Accessibility / Security. 사용자가 추가한 카테고리도 그대로 처리.)
- 각 이슈는
**[axis/rule-id]** [SEVERITY] Line N: ...형식
출력 형식 — 한국어 (lang=ko 또는 미지정)
# 🔍 코드 리뷰 결과: <대상>
## 한눈에 보기
- **총 이슈**: N개
- 🔴 CRITICAL: N | 🟠 HIGH: N | 🟡 MED: N | 🟢 LOW: N
## 우선순위 이슈 (중요도순)
### 🔴 CRITICAL
- **[security/hardcoded-secret]** Line X: <이슈> — <수정안>
- **[bugs/conditional-hook]** Line Y: ...
### 🟠 HIGH
- **[perf/async-parallel]** Line X: ...
- **[ts/cast-instead-of-guard]** Line Y: ...
### 🟡 MED
- ...
### 🟢 LOW
- ...
출력 형식 — 영어 (lang=en)
# 🔍 Code Review: <target>
## At a glance
- **Total issues**: N
- 🔴 CRITICAL: N | 🟠 HIGH: N | 🟡 MED: N | 🟢 LOW: N
## Priority issues (by severity)
### 🔴 CRITICAL
- **[security/hardcoded-secret]** Line X: <issue> — <fix>
- **[bugs/conditional-hook]** Line Y: ...
### 🟠 HIGH
- **[perf/async-parallel]** Line X: ...
- **[ts/cast-instead-of-guard]** Line Y: ...
### 🟡 MED
- ...
### 🟢 LOW
- ...
규칙
- 도구 사용 금지. 입력 텍스트만으로 합성.
- 심각도 필터: severity 순서는
CRITICAL > HIGH > MED > LOW.severity_min미만 severity finding은 "우선순위 이슈" 섹션과 "한눈에 보기" 카운트 모두에서 제외. 예:severity_min=HIGH면 CRITICAL, HIGH만 남기고 MED, LOW는 통째로 제외. - 필터 메타:
severity_min ≠ LOW인 경우에만 "한눈에 보기" 블록 마지막 줄에 메타 한 줄 추가. 형식:- 한국어:
🔎 severity_min=<X> (<제외 카테고리 나열>로 N건 제외)— 예:🔎 severity_min=HIGH (LOW/MED로 8건 제외) - 영어:
🔎 severity_min=<X> (N filtered as <excluded categories>)— 예:🔎 severity_min=HIGH (8 filtered as LOW/MED) severity_min=LOW(기본)이면 메타 줄 없음.
- 한국어:
- "우선순위 이슈" 섹션은 모든 리뷰어의 발견을 통합해서 (필터 후) 심각도순으로 재배열. 각 항목은 reviewer가 부여한
[axis/rule-id]태그를 그대로 보존. - 같은 라인에 여러 reviewer가 다른 rule ID로 지적했다면 둘 다 보존 (각자 다른 관점). 같은 rule ID 중복만 dedup.
- 이슈 없는 심각도 섹션은 한국어면 "(없음)", 영어면 "(none)"으로 표기.
severity_min필터로 통째로 제외된 섹션도 동일하게 "(없음)"/"(none)". - "카테고리별 상세" 섹션은 만들지 마세요. 우선순위 이슈에 모든 발견이 이미 포함되므로 중복 출력은 노이즈가 됩니다.
- 출력 언어:
lang=en이면 영어 템플릿, 아니면 한국어 템플릿. 룰 ID는 언어와 무관하게 그대로.
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.
- 9d ago First seen · 82 lines · 82 tokens per session scan A 359617936eb7
synthesizer is an agent published in the GitHub repository huurray/fe-review-agents (5 stars, last pushed 4mo ago), licensed MIT. It adds 82 tokens to every session and 1,092 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 2026-08-31.
Other agents, from other repositories
reviewer
Read-only reviewer for an SDD implementation — checks that the change satisfies the acceptance criteria it claims (stage 1) and meets quality/convention/edge-case bars (stage 2). Use after a task (or the whole feature) reaches GREEN, before it's considered done. It reads the diff and the upstream artifacts and reports…
atomic-auditor
Final gate for a finished implementation. Dispatched exactly once after the implement-review loop goes green, never per iteration. Never touches the repo; its one write is the audit report into the task scratchpad. Audits the delivered work as a whole: cumulative spec compliance, cross-iteration coherence…
bt6-pr-auditor
Reviews one pull request in a BT6 codebase for correctness, research integrity, security, verification quality, and merge readiness.
Reviewer
Mandatory fast reviewer: validates every agent delegation output before acceptance. Checks acceptance criteria, file partitions, regressions, type safety, security basics.
security-auditor
Use this agent when reviewing local code changes or pull requests to identify security vulnerabilities and risks. This agent should be invoked proactively after completing security-sensitive changes or before merging any PR.
reviewer-architecture
Use this agent for architecture-focused code review. Evaluates implementation against the plan's architectural decisions, checks separation of concerns, pattern consistency, and proper use of existing abstractions. Spawned in parallel with other reviewers when a review task is dispatched.