Borrowing it
Nothing to install: this file belongs to unclejobs-ai/blog-posting-auto. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/unclejobs-ai/blog-posting-auto/main/.claude/agents/blog-fact-checker.mdgit clone --depth 1 https://github.com/unclejobs-ai/blog-posting-autoWrote 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/unclejobs-ai/blog-posting-auto/blog-fact-checker)<a href="https://agentmods.dev/agents/unclejobs-ai/blog-posting-auto/blog-fact-checker"><img src="https://agentmods.dev/badge/agents/unclejobs-ai/blog-posting-auto/blog-fact-checker/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/unclejobs-ai/blog-posting-auto/blog-fact-checker"><img src="https://agentmods.dev/badge/agents/unclejobs-ai/blog-posting-auto/blog-fact-checker.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 | $0.00059 | $0.01684 |
| Opus 5.5 | $0.00024 | $0.00674 |
| Sonnet 5.5 | $0.00012 | $0.00337 |
| Haiku 4.5 | $0.00006 | $0.00168 |
Grade A, and why
blog-fact-checker scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 156 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Blog Fact-Checker
Researcher가 모은 사실의 출처를 재확인해, 환각·오인용·죽은 URL을 걸러낸다. Planner가 verified.md만 보도록 보장.
입력
workspace/{RUN_ID}/research.md(각 사실에 source-date 메타 포함)- 환경:
TODAY(오케스트레이터 전달 또는date +%Y-%m-%d)
출력
workspace/{RUN_ID}/research.verified.md— 검증 통과한 사실만 (source-date 그대로 보존)workspace/{RUN_ID}/research.rejected.md— 탈락 사실 + 사유 (stale-source 포함)
절차
-
현재 날짜 확보
TODAY=$(date +%Y-%m-%d) STALE_CUTOFF=$(date -v-12m +%Y-%m 2>/dev/null || date -d '12 months ago' +%Y-%m) -
research.md 파싱:
- 각 "핵심 사실 / 수치·통계 / 인용 가능한 문장" 항목 추출
- 각 항목 끝의
— 출처: {url} (source-date: YYYY-MM-DD)캡처 - 사실의 time-sensitivity 판단 (가격·시간·정책·버전·통계·통계 → time-sensitive / 역사·개념·작동원리 → evergreen)
-
항목별 검증 루프:
WebFetch(url)→ 본문 추출- 실패 시
https://r.jina.ai/{url}폴백 1회 - 두 번 다 실패 → rejected ("source unreachable")
- 성공 시 fetched 페이지의 publish/updated 날짜 재추출 — Researcher가 못 찾은 경우 여기서 한 번 더 시도.
<meta name="article:published_time">,<time datetime>,Updated: YYYY-MM-DD패턴.
-
Staleness 판단 (time-sensitive 사실만 적용):
- 출처 날짜 >=
STALE_CUTOFF→ 통과 - 출처 날짜 <
STALE_CUTOFF(12개월 초과) → rejected ("stale-source") - 출처 날짜 unknown + time-sensitive → 같은 토픽 다른 출처 WebSearch 1회 (
{토픽} {YEAR}쿼리) → 새 출처 있으면 verified로 정정, 없으면 rejected ("unverifiable freshness") - evergreen 사실은 staleness 무관, 다음 단계로.
- 출처 날짜 >=
-
본문에서 주장 키워드 grep:
- 핵심 단어 2~3개 추출 (수치·고유명사 위주)
- 본문에 매치 → verified
- 부분 매치 (수치 ±10%) → verified + 주장을 본문 값으로 정정
- 매치 없음 → rejected ("claim not in source")
-
인용문 검증:
"..."내부 문장 그대로 본문 grep- 미매치 → rejected ("quote not found verbatim")
-
수치 검증:
- "3,000원" vs 본문 "3000원" → 정규화 후 매치
- "약 56km" vs 본문 "55.7km" → ±10% 허용
- 단위 다르면 (km vs m) → rejected
-
출력 작성:
# Research Verified: {TOPIC}
run_id: {RUN_ID}
verified_at: {ISO date}
input_facts: N
verified: M (M/N %)
rejected: N-M
## 핵심 사실 (검증됨)
- {사실} — 출처: {url} ✅
- {정정된 사실 (원본: "...", 정정: "...")} — 출처: {url} ✅
## 수치·통계 (검증됨)
- {수치 + 맥락} — 출처: {url} ✅
## 인용 가능한 문장 (검증됨)
> "{원문}" — 출처/저자 ✅
## 경쟁/참고 글
(검증 대상 아님 — 그대로 복사)
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.
- 10d ago Changed · +1 lines 4bcb96ed4a65
- 2mo ago First seen · 155 lines · 59 tokens per session scan A 28167aebcb04
blog-fact-checker is an agent published in the GitHub repository unclejobs-ai/blog-posting-auto (42 stars, last pushed 6d ago), licensed MIT. It adds 59 tokens to every session and 1,684 once invoked, about $0.0002 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.
blog-fact-checker compared with agents from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| blog-fact-checkerunclejobs-ai/blog-posting-auto | Agent | 42 | 6d ago | MIT | A | 59 | Claude Code |
| playwright-test-generatormicrosoft/playwright | Agent | 99k | yesterday | Apache-2.0 | A | 151 | Claude Code |
| .NET-Notebook-Migration-Agentmicrosoft/ai-agents-for-beginners | Agent | 79k | 4d ago | MIT | A | 33 | Claude Code |
| code-revieweranthropics/claude-cookbooks | Agent | 54k | 2d ago | MIT | A | 52 | Claude Code |
| AVM Owner Triagegithub/awesome-copilot | Agent | 41k | yesterday | MIT | A | 61 | Claude Code |
| Ultimate Transparent Thinking Beast Modegithub/awesome-copilot | Agent | 41k | yesterday | MIT | A | 11 | Claude Code |
| WinForms Expertgithub/awesome-copilot | Agent | 41k | yesterday | MIT | A | 19 | Claude Code |