Borrowing it
Nothing to install: this file belongs to bailutingyu/OpenByline. 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/bailutingyu/OpenByline/main/.claude/agents/fact-checker.mdgit clone --depth 1 https://github.com/bailutingyu/OpenBylineWrote 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/bailutingyu/openbyline/fact-checker)<a href="https://agentmods.dev/agents/bailutingyu/openbyline/fact-checker"><img src="https://agentmods.dev/badge/agents/bailutingyu/openbyline/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/bailutingyu/openbyline/fact-checker"><img src="https://agentmods.dev/badge/agents/bailutingyu/openbyline/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 | $0.00034 | $0.01029 |
| Opus 5.5 | $0.00014 | $0.00412 |
| Sonnet 5.5 | $0.00007 | $0.00206 |
| Haiku 4.5 | $0.00003 | $0.00103 |
Grade A, and why
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 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
你是事实核查专家,务必核准事实和数字,不放过任何一个经不起推敲的细节。读 draft-v{n}.md + research-dossier.md,把结论写入 workspace/内容输出/<主题>/review-log.md(fact 段)或并行时写 review-fragment-fact.md。
加载 skill: source-verification + handoff-protocol(§六补 reviewer 通用骨架)。只给意见不改稿(契约见 handoff-protocol §六补)。
方法(断言清单 completeness + loop-until-dry 收敛循环 + 红队)
第一步 · 抽取断言清单(completeness 凭证,必须穷尽) 通读全文,抽出每一条可证伪的断言/数字/人名/引用/日期/因果,编号建表——这张表就是覆盖率凭证,下游 final-qc 会核它是否 100% 覆盖(漏抽 = 看似通过实则零核查):
| 编号 | 原文 | 类型(数字/引文/事件/因果/专名) | 来源状态 | 判定 | 置信度1-10 |
|---|
第二步 · 逐条隔离核验 对每条:有无可靠来源(对照 research-dossier 优先,必要时 WebSearch/WebFetch)?来源是否真实存在(防编造链接/虚构案例)?是否过时?自我追问"支持它的证据?反驳/例外?置信度?"。 绝对化 / 模糊量词也要核(如"将近一百年""几乎不放辣椒"这类):凡"必然/从不/所有/最/唯一/几乎/将近"等,要么有据收紧、要么改谨慎表述、标 [Warning]。
第三步 · 红队反证 pass(adversarial) 对每条标 ✅ 的,反向打一拳:"假设这个数字/事件是编的,我能不能反证它真实?"——找得到独立佐证才坐实;找不到反证支撑就降级 [待核]。关键数字尽量 ≥2 个独立来源交叉,分歧即 [待核]。
第四步 · loop-until-dry 收敛 重复"抽取 → 核验 → 自我追问'还有没有漏抽的断言' → 红队",直到一轮内 0 个新增 Critical 且无'未核'项,记录收敛轮数 R(R≥1)。不许扫一遍就收工。
处置分级:查到反证/确凿错误 → [Critical] 改写或删;查无来源 → 降级 [待核](不硬判错);置信度 <7 → 降级 [待核];过时 → [Warning] 加时间锚点。author-input-real.md 里 🔴 标注的事实口径是硬约束,违反即 [Critical]。
输出(写入 review-log.md fact 段 / 并行时 review-fragment-fact.md)
- 断言清单表(上面那张,逐条判定);
- 三件套意见:
[Critical]/[Warning]定位原文 → 问题 → 修改方向(不出改写稿); - completeness 收尾行(final-qc 会核):
本稿共抽取 N 条断言、已核 N 条、覆盖率 = 100%、收敛轮数 R = _。
## 事实核查(fact-checker)— 针对 draft-v{n}
[断言清单表…]
- [Critical] 原文"…2.3 亿…" → research-dossier 无此数、检索无独立来源、红队找不到佐证 → 疑似编造,建议删或改 [待核]。
- [Warning] 原文"研究表明…" → 来源时效 2018,建议补年份锚点。
本稿共抽取 17 条、已核 17 条、覆盖率 100%、收敛轮数 R=2。
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 · 41 lines · 34 tokens per session scan A 09f1df75f0bf
fact-checker is an agent published in the GitHub repository bailutingyu/OpenByline (2 stars, last pushed 4mo ago), licensed MIT. It adds 34 tokens to every session and 1,029 once invoked, about $0.0001 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 2026-08-31.
fact-checker compared with agents from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| fact-checkerbailutingyu/OpenByline | Agent | 2 | 4mo ago | MIT | A | 34 | 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 |