fact-check-x-complete

fact-check-x-complete is a skill for Claude Code, Codex from ASI2030/Fact-Check-X. It costs 180 tokens per session (8,361 once invoked), scanned A, original, Apache-2.0.

A Chinese-language fact-checking skill that collects complete answers and evidence from selected AI platforms, compares them, and optionally checks claims against trusted search sources.

In plain words
What is it for?
Use it to investigate a question with one or more supported AI platforms, compare their answers, preserve reports, and produce an evidence-based conclusion when verification is requested.
Why use it?
It keeps original answers, citations, screenshots, disagreements, and evidence limits visible instead of presenting partial results as certainty.

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.

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is python3 scripts/fact_check_x.py locate.

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

Good fit Use it to investigate a question with one or more supported AI platforms, compare their answers, preserve reports, and produce an evidence-based conclusion when verification is requested.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/ASI2030/Fact-Check-X
agentmods
npx agentmods add skills/asi2030/fact-check-x/fact-check-x-complete

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-complete

README.md
[![agentmods](https://agentmods.dev/badge/skills/asi2030/fact-check-x/fact-check-x-complete/github.svg)](https://agentmods.dev/skills/asi2030/fact-check-x/fact-check-x-complete)
Your own site
<a href="https://agentmods.dev/skills/asi2030/fact-check-x/fact-check-x-complete"><img src="https://agentmods.dev/badge/skills/asi2030/fact-check-x/fact-check-x-complete/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-complete

Your own site · 80×15
<a href="https://agentmods.dev/skills/asi2030/fact-check-x/fact-check-x-complete"><img src="https://agentmods.dev/badge/skills/asi2030/fact-check-x/fact-check-x-complete.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 180 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 8,361 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 $0.00180 $0.08361
Opus 5 $0.00090 $0.04181
Sonnet 5 $0.00036 $0.01672
Haiku 4.5 $0.00018 $0.00836

Measured yesterday against content hash 9657e4395ab0, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

fact-check-x-complete 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 yesterday.

The scan reads SKILL.md. This mod also ships 39 executable files (modules/fact-check-x-authoritative-verify/scripts/authority_verify.py, modules/fact-check-x-authoritative-verify/scripts/batch_search.py, modules/fact-check-x-authoritative-verify/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-complete/SKILL.md · 330 lines

How it starts

The opening of the file, as written. The whole thing — 330 lines — stays where its author put it; the contents beside it link to each section on GitHub.

全知晓(Fact-Check-X)

Fact-Check-X 多平台事实核验:完整采集、知识点对比、权威核验与答案生成、平台表现评估

把同一个问题交给一个或多个 AI 平台,完整保留每家的回答和引用,再把关键事实逐点对齐、核验并评估各平台表现。第三步会基于权威证据生成最终答案,但不会用“答案生成”代替完整事实核验:证据冲突会被保留,证据不足的内容不会写入确定结论。用户只需说出问题和要比较的平台,不需要学习平台 ID、内部流程编号或报告术语。

支持平台

当前内置以下网页端平台,按用户本次输入动态选择任意 N≥1 个:

平台 能力
深知晓 标准问答、引用与官方来源采集
深知晓(深度溯源) 等待普通回答完成后在同一会话启动深度溯源,并作为独立结果采集
豆包 回答、引用与页面存证
DeepSeek 回答、引用、逐条来源正文与页面存证
通义千问 回答、引用与页面存证
腾讯元宝 回答、引用、逐条来源正文与页面存证
平台由用户选择,不存在固定“五平台模式”。N=1 可完成单平台事实核验;N≥2 会额外比较各平台的共识、冲突和来源差异。网页结构变化时,技能会明确报告失败并停在当前阶段,不会用部分结果冒充完整报告。

使用体验

  • 用户只需提供核验问题和想比较的平台;没有指定平台时,立即列出“深知晓、深知晓(深度溯源)、豆包、DeepSeek、通义千问、腾讯元宝”供用户选择,不得漏掉深度溯源,也不要求用户记平台 ID。
  • 第一次使用某个平台时打开浏览器,由用户本人完成登录或验证码;会话保存后自动复用。
  • 每一步都交付可打开的独立报告:各方答案汇总、各方答案聚合(未核验)、权威核验后的最终答案、各方答案测评报告。
  • 每份阶段报告展示后都必须等待用户明确选择继续、修正或结束;最初要求完整执行不能替代逐阶段确认。
  • 第二步在概览和逐知识点明细中分别展示直接答案与补充参考;第三步只保留权威最终答案;第四步以一个锁定明细区承接第三步结果并分区测评。
  • 第三步只展示最终答案、权威证据和证据边界;第四步只消费已锁定的第三步数据,负责平台裁决、指标与表现对比,不重算第三步。
  • 多平台采集与知识点对比不需要 API Key。只有用户继续进行权威证据核验,且现有材料不足以直接裁决时,才检查可信搜索配置。
  • 可信搜索未配置时,只引导用户登录深知智能平台;技能自动获取或创建专用 Key 并安全保存在本机,不要求用户复制粘贴密钥。
  • 语义分析由 Codex、Claude Code、WorkBuddy 等当前运行载体完成,不调用外部大模型 API。

强制执行门禁(任何动作前先读)

  1. 语言硬门禁:读取本技能后的第一句话、过程更新、命令说明、阶段检查点、错误说明和最终答复全部只使用简体中文;不得输出英文句子。命令、路径、平台 ID 和数据字段名可以保留原文。第一条回复直接使用“我会核验这个问题:先采集您选择的平台原回答和引用,再比较共识与分歧;如需权威结论,最后用可信搜索逐点核验。每一步都会给您一份可打开的报告。”,不得先用英文介绍技能或内部流程编号。
  2. 执行任何命令前先检查当前会话可调用的工具。完整在线采集优先由包内 Playwright 直接启动并控制系统 Chrome、Microsoft Edge、Brave 或 Chromium;Computer Use 不是正常采集的前置条件,只是自动化失败后的恢复手段。只有命令工具时可以前台执行一次 login 验证可见浏览器,但没有真实成功输出前不得声称浏览器已启动。
  3. 所有流水线命令必须前台直接执行并等待真实退出状态,包括 loginrunprepare-comparisoncomplete-comparisonprepare-authoritysearch-authorityfinalize-authoritydeliver。执行工具因等待用户操作而返回可轮询的运行会话 ID 时,应保留并轮询该会话;禁止使用 shell 后台任务,禁止给任何流水线命令添加 | tail| tee|| true 或其他会掩盖退出码的包装。
  4. login 是可见浏览器命令,必须严格按本技能给出的参数执行,不得添加 --headed 或其他未列出的参数。精确命令尚未失败时,不得先检查 CLI 帮助、源码或浏览器环境;精确命令失败后只按错误与 capture-recovery.json 恢复。
  5. 未看到 login 成功、可提问页面已建立或 results.json 全平台成功证据前,禁止告诉用户“浏览器已启动”“采集已在后台运行”或“将自动进入后续流程”。
  6. loginrun 运行期间出现登录、短信验证码、人机验证或 CAPTCHA 时,保持命令和当前 Playwright 页面运行,立即提示用户本人处理;检测到处理完成后自动继续,不得关闭页面、重输问题或提前结束任务。
  7. loginrun 非零退出、浏览器意外关闭、人工处理超时或采集失败时,立即读取 capture-recovery.json。运行载体有 Computer Use 时调用它恢复;没有时明确说明“当前载体无法调用 Computer Use,原始答案采集已停止”,停在原始答案采集阶段。
  8. 进入 Computer Use 恢复后,禁止改用 headless/无头浏览器、清理锁文件、修改启动参数或用命令行诊断规避接管。允许使用原持久化配置重新打开同一平台,并直接复用 capture-recovery.json.question
  9. capture-gate.json 未证明所有指定平台均成功前,禁止进入知识点对比和后续流程。不得用已有材料、搜索结果、空回答或部分成功结果替代失败平台。
  10. 分阶段交付门禁:原始答案采集、知识点对比和权威证据核验各自完成后,必须先向用户发送本阶段真实可打开的独立产物,再询问用户选择“继续下一步”“修正当前结果”或“到此结束并保留产物”。程序会在 stage-checkpoints.json 记录产物摘要和一次性确认令牌;收到用户“继续下一步”后,必须用 acknowledge-stage --decision continue 提交该令牌,否则下一阶段命令会直接失败。即使用户最初要求完整连续执行,也不能跳过阶段产物展示和用户确认。证据不足属于可交付结论,不阻断后续报告。

Read the full file on GitHub · 330 lines

Files

What ships with it

60 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.

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. yesterday Changed · +2 lines 9657e4395ab0
  2. 7d ago Changed · +2 lines eafdeec40305
  3. 11d ago First seen · 326 lines · 180 tokens per session scan A 24fc4122e003

Subscribe to this mod's changes

fact-check-x-complete is a skill published in the GitHub repository ASI2030/Fact-Check-X (1 stars, last pushed yesterday), licensed Apache-2.0. It adds 180 tokens to every session and 8,361 once invoked, about $0.0009 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.