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 skills add ASI2030/Fact-Check-X --skill fact-check-x-authoritative-verifygit clone --depth 1 https://github.com/ASI2030/Fact-Check-XWrote 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/skills/asi2030/fact-check-x/fact-check-x-authoritative-verify)<a href="https://agentmods.dev/skills/asi2030/fact-check-x/fact-check-x-authoritative-verify"><img src="https://agentmods.dev/badge/skills/asi2030/fact-check-x/fact-check-x-authoritative-verify/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/skills/asi2030/fact-check-x/fact-check-x-authoritative-verify"><img src="https://agentmods.dev/badge/skills/asi2030/fact-check-x/fact-check-x-authoritative-verify.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 | $0.00117 | $0.01918 |
| Opus 5 | $0.00059 | $0.00959 |
| Sonnet 5 | $0.00023 | $0.00384 |
| Haiku 4.5 | $0.00012 | $0.00192 |
Grade A, and why
fact-check-x-authoritative-verify 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 8d 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 — 119 lines — stays where its author put it; the contents beside it link to each section on GitHub.
权威证据核验
本技能一次只核验一个知识点。多个知识点必须拆成多个独立请求并发执行,不能把完整回答或全部知识点塞进一个请求。
可信搜索只负责返回官方材料。知识点含义、证据是否支持主张和最终裁决由当前承载技能的智能体完成;技能内不调用模型 API。
单知识点取证
请求必须符合 数据契约。传给云端的用户内容只有:总标题、当前知识点,以及仅在各家说法不同时才出现的差异主张。
python3 scripts/authority_verify.py search \
--request <K1-request.json> \
--output <K1-evidence.json> \
--service-area "<可选地区>"
若请求内有经知识点对比阶段严格验收的 trustedAnchor.eligible=true,程序直接复用本次回答已返回且支持当前主张的官方证据:深知晓或深知晓(深度溯源)材料输出 searchMode=dknow_exempt,其他平台的 gov.cn 材料输出 searchMode=gov_exempt,两者均为 requestCount=0。只有非深知且非 gov.cn 的材料,或现有官方原文不足以支持当前主张时,才调用一次可信搜索,输出 searchMode=trusted_search、requestCount=1。
通过 Fact-Check-X 统一入口调用时,可信搜索配置由跨载体配置组件自动注入:用户首次只需登录深知 MaaS,组件自动获取或创建专用 Key;以后 Codex、Claude Code、WorkBuddy 等直接复用本机共享配置。批量执行前先复用本次回答已有的深知官方材料和 gov.cn 材料;仍存在非免查知识点且当前进程没有收到可用 Key 时,程序才在任何搜索开始前失败。不得让用户在对话中粘贴 Key;只有官方材料正文已定位并支持当前原子主张时才可免查,不能只凭官方标签自动判定正确。
并行取证
python3 scripts/batch_search.py \
--requests-dir <authority-requests> \
--output-dir <authority-evidence> \
--max-workers 12 \
--service-area "<可选地区>"
11 个知识点会形成 11 个互不依赖的任务并行执行;其中有深知晓权威锚点的任务不发云端请求。
当前智能体裁决
阅读单点请求和证据后,当前智能体写出:
当 searchMode=dknow_exempt|gov_exempt 时,request.trustedAnchor.officialAnswer 是当前知识点的权威结论,证据列表承担来源追溯作用。各平台主张与 officialAnswer 语义一致或可由其直接推出时,裁决为 supported 并引用当前锚点中的有效证据 ID;只有主张增加了官方原文不能支持的实质事实,或确实无法判定时,才使用 insufficient。
知识点对比阶段已独立保存平台引用忠实性。本阶段只裁决事实正确性:平台自己的引用不充分但结论被权威锚点证实时,仍裁决为 supported,最终分类由程序结合原忠实性形成 coincidental。
{
"authoritativeFinding": "官方证据支持的有界结论",
"verdicts": {
"doubao": {
"verdict": "supported",
"reason": "主张与官方证据一致",
"evidenceIds": ["E1"]
}
}
}
authoritativeFinding 必须非空;每个已覆盖平台都必须有裁决,verdict 只能是 supported、contradicted 或 insufficient;reason 必须非空;supported 和 contradicted 必须至少引用一个当前证据包中真实存在的 evidenceId。程序不接受顶层 verdict、officialAnswer 或 platformAssessment,也不会把错误结构静默降级为证据不足。
若可信搜索正常返回但没有取得权威材料,输出 no_evidence;单点裁决写入 resolution=insufficient_evidence 和 evidenceGaps,并以 status=completed 完成。没有检索到材料不构成对主张的反证,禁止自动归类为“编造”,对应主张不进入确定答案或准确率分母。服务异常由程序自动重试,重试后仍失败则返回技术错误,不生成事实裁决。
What ships with it
17 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- agents/openai.yaml 327 B
- references/acceptance-criteria.md 2.1 KB
- references/contracts.md 3.3 KB
- references/final-report-baseline.html 105 KB
- scripts/authority_verify.py 25 KB runs code
- scripts/batch_search.py 5.6 KB runs code
- scripts/common.py 967 B runs code
- scripts/platform/participants.json 869 B
- scripts/render_authority_report.py 25 KB runs code
- scripts/render_final_report.py 21 KB runs code
- scripts/render_platform_report.py 50 KB runs code
- tests/fixtures/K1-assessment.json 335 B
- tests/fixtures/K1-request.json 1.5 KB
- tests/fixtures/K2-assessment.json 370 B
- tests/fixtures/K2-evidence-fixture.json 173 B
- tests/fixtures/K2-request.json 903 B
- tests/smoke_test.py 45 KB runs code
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.
- 8d ago Changed 86b8a7f87963
- 12d ago First seen · 119 lines · 117 tokens per session scan A 423d13acb352
fact-check-x-authoritative-verify is a skill published in the GitHub repository ASI2030/Fact-Check-X (1 stars, last pushed yesterday), licensed Apache-2.0. It adds 117 tokens to every session and 1,918 once invoked, about $0.0006 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 skills, from other repositories
academic-writing
Scholarly writing and research compliance. Use for CRediT, preregistration, Plan S, Nelson Memo, preprints, ORCID, LLM disclosure.
accessibility-compliance
Web accessibility patterns for news and academic sites. Use for WCAG audits, alt text, accessible data viz, and assistive tech.
one-way-door
Flags irreversible decisions before commit. Use for data models, infra, auth boundaries, API contracts, event schemas, CI/CD.
newsletter-publishing
Email newsletter workflows. Use when creating newsletters, building subscriber lists, designing templates, or tracking engagement.
photo-metadata
Embeds photo IPTC/EXIF/XMP metadata, caption, credit, alt text, license, AI-source label, GPS stripping, and C2PA credentials.
crisis-communications
Crisis communication and rapid-response workflows. Use when covering breaking news or coordinating fast fact-checking on deadline.