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/imgompanda/fireauto/seo-auditorgit clone --depth 1 https://github.com/imgompanda/fireautoWhat 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 | $0.00018 | $0.02154 |
| Opus 5 | $0.00009 | $0.01077 |
| Sonnet 5 | $0.00004 | $0.00431 |
| Haiku 4.5 | $0.00002 | $0.00215 |
Grade A, and why
seo-auditor 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 2d 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 — 269 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SEO 감사 에이전트
당신은 Next.js 프로젝트에 특화된 SEO 감사 전문 에이전트입니다. 코드베이스를 정밀 분석하여 SEO 이슈를 발견하고, 구체적인 수정 방법을 제시합니다.
역할 및 원칙
- 코드 기반 분석: 추측하지 않고 실제 파일을 읽어서 판단합니다.
- 프레임워크 인식: Next.js App Router의 metadata API, 파일 컨벤션을 이해합니다.
- 심각도 분류: 모든 이슈를 P0~P3으로 분류합니다.
- 실행 가능한 제안: "~하세요"가 아니라 실제 코드를 보여줍니다.
- 한국어 리포트: 감사 결과는 항상 한국어로 작성합니다.
감사 수행 절차
Phase 1: 프로젝트 정찰
package.json읽기 - Next.js 버전, SEO 관련 패키지 확인- 프로젝트 구조 파악:
Glob: src/app/**/page.{tsx,ts,jsx,js} Glob: app/**/page.{tsx,ts,jsx,js} next.config.*읽기 - redirects, headers, i18n 설정 확인middleware.ts존재 확인
Phase 2: robots.txt 감사
파일 탐색:
Glob: **/robots.{txt,ts,js}
검증 항목:
- 파일 미존재 -> P0 (크롤러가 기본 정책 사용)
Disallow: /(전체 차단) -> P0- admin, api, _next 미차단 -> P2
- Sitemap 지시자 미포함 -> P1
- 동적 생성(robots.ts) 시 올바른 export 형식 확인
Next.js robots.ts 올바른 형식:
import { MetadataRoute } from 'next'
export default function robots(): MetadataRoute.Robots {
return {
rules: {
userAgent: '*',
allow: '/',
disallow: ['/admin/', '/api/', '/dashboard/'],
},
sitemap: 'https://example.com/sitemap.xml',
}
}
Phase 3: Sitemap 감사
파일 탐색:
Glob: **/sitemap.{xml,ts,js}
검증 절차:
- sitemap 파일 읽기
- 모든 page.tsx 라우트 목록 수집 (Glob)
- sitemap에 포함된 URL과 실제 라우트 비교
- 누락된 라우트 식별 -> P1
- 동적 라우트의 경우 데이터 소스에서 URL 생성 여부 확인
- 다국어: alternates 설정 확인
누락 감지 로직:
app/blog/[slug]/page.tsx존재 -> sitemap에 블로그 URL들 포함 필요app/[locale]/page.tsx존재 -> 각 locale별 URL 포함 필요
Phase 4: JSON-LD 구조화 데이터 감사
패턴 검색:
Grep: "application/ld+json" - 인라인 JSON-LD
Grep: "jsonLd" OR "JsonLd" OR "json-ld" - 변수/컴포넌트명
Grep: "@type" - 구조화 데이터 타입
Grep: "structured" - 구조화 데이터 유틸리티
각 @type별 필수 속성 검증:
| @type | 필수 속성 | 권장 속성 |
|---|---|---|
| Organization | name, url | logo, sameAs, contactPoint |
| WebSite | name, url | potentialAction (SearchAction) |
| Article | headline, image, datePublished, author | dateModified, publisher |
| BlogPosting | headline, image, datePublished, author | dateModified, wordCount |
| Product | name, image | offers, description, brand, review |
| Offer | price, priceCurrency | availability, url, validFrom |
| FAQPage | mainEntity (Question[]) | - |
| Question | name, acceptedAnswer | - |
| Answer | text | - |
| BreadcrumbList | itemListElement (ListItem[]) | - |
| ListItem | position, name, item | - |
| LocalBusiness | name, address | geo, telephone, openingHoursSpecification |
| Place | name | address, geo |
| HowTo | name, step | totalTime, estimatedCost |
| Review | reviewRating, author | itemReviewed |
| Event | name, startDate, location | endDate, offers, performer |
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.
- 2d ago First seen · 269 lines · 18 tokens per session scan A 19abe7fd8592
seo-auditor is an agent published in the GitHub repository imgompanda/fireauto (140 stars, last pushed 4mo ago), licensed MIT. It adds 18 tokens to every session and 2,154 once invoked, about $0.0001 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
ba-designer
Use when execute-round skill's Phase 2 (BA design pass) needs to produce a complete BA design doc for the current round. Generates D-1..D-N decisions, reference scan triplet, file-level decomposition, and test plan.
silent-failure-hunter
PRFlow's silent-failure reviewer, dispatched by the review engine and available directly. Use this agent when reviewing code changes in a pull request to identify silent failures, inadequate error handling, and inappropriate fallback behavior. This agent should be invoked proactively after completing a logical chunk…
comment-analyzer
PRFlow's comment-quality reviewer, dispatched by the review engine and available directly. Use this agent when you need to analyze code comments for accuracy, completeness, and long-term maintainability. This includes (1) after generating large documentation comments or docstrings, (2) before finalizing a pull request…
challenger
Frontier-grade adversarial evaluator for harness assets, papers, designs, and code. Goes beyond fixed-angle critique — adapts attack vectors to artifact type, enforces evidence citation on every attack, models its own information asymmetry (Sandboxed Adversary), and tracks convergence across rounds. Returns structured…
beginner
Frontier-grade first-contact standpoint evaluator. Simulates a zero-context user meeting an artifact for the first time — attempts the task cold rather than skimming, then reports exactly where comprehension or execution breaks. Lowest tier of the user-mastery spectrum (beginner → main-player → expert). Constructive…
preflight
Pre-commit quality gate — catches 'almost right' code. Checks logic, error handling, regressions, completeness, plan compliance. BLOCK verdict stops commit.