fact-check-x-authoritative-verify

fact-check-x-authoritative-verify is a skill for Claude Code, Codex from ASI2030/Fact-Check-X. It costs 117 tokens per session (1,918 once invoked), scanned A, original, Apache-2.0.

A workflow for checking individual factual claims against evidence from trusted or official sources. It can compare claims, classify whether they are supported or misleading, and produce an answer with an evaluation report.

In plain words
What is it for?
Use it to fact-check one knowledge point at a time, search for official evidence, reuse eligible evidence when available, and process multiple independent claims in parallel.
Why use it?
It helps separate verified claims from unsupported, accidentally matching, seriously misleading, or invented claims.

Skill for Claude CodeCodex

Written for Claude Code and Codex: shipped in a Claude Code plugin, but also agents/openai.yaml present. Also seen: mentions Claude Code; mentions Codex.

Part of the fact-check-x plugin — 5 skills shipped together

Good fit Use it to fact-check one knowledge point at a time, search for official evidence, reuse eligible evidence when available, and process multiple independent claims in parallel.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/asi2030/fact-check-x/fact-check-x-authoritative-verify
Install

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.

Any agent
npx skills add ASI2030/Fact-Check-X --skill fact-check-x-authoritative-verify
Clone the repo
git clone --depth 1 https://github.com/ASI2030/Fact-Check-X

Made for: Claude Code, Codex.

Or install fact-check-x, the plugin that ships this one along with the rest of its 5 skills.

Wrote 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.

agentmods badge for fact-check-x-authoritative-verify

README.md
[![agentmods](https://agentmods.dev/badge/skills/asi2030/fact-check-x/fact-check-x-authoritative-verify/github.svg)](https://agentmods.dev/skills/asi2030/fact-check-x/fact-check-x-authoritative-verify)
Your own site
<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.

agentmods 80×15 button for fact-check-x-authoritative-verify

Your own site · 80×15
<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>
Per session 117 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,918 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce 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

Measured 8d ago against content hash 86b8a7f87963, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

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.

The scan reads SKILL.md. This mod also ships 7 executable files (scripts/authority_verify.py, scripts/batch_search.py, scripts/common.py, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

skills/fact-check-x-authoritative-verify/SKILL.md · 119 lines

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_searchrequestCount=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:

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 supportedcontradictedinsufficientreason 必须非空;supportedcontradicted 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 verdictofficialAnswerplatformAssessment,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_evidenceevidenceGaps,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。

Read the full file on GitHub · 119 lines

Changes

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.

  1. 8d ago Changed 86b8a7f87963
  2. 12d ago First seen · 119 lines · 117 tokens per session scan A 423d13acb352

Subscribe to this mod's changes

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.