What is fact-check-x-knowledge-compare?

A local tool for comparing several AI answers by breaking them into individual claims and checking how each answer uses its stated evidence. It produces structured comparison data and a visual report without calling search services or outside model APIs.

Use it to compare research answers, track each answer's supporting evidence, and create an unverified synthesis draft for later checking.

It separates agreement, disagreement, missing support, and source-matching problems that are easy to overlook when reading answers side by side.

fact-check-x-knowledge-compare — Skill for Claude Code and Codex by AS

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-knowledge-compare

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/asi2030/fact-check-x/fact-check-x-knowledge-compare/github.svg)](https://agentmods.dev/skills/asi2030/fact-check-x/fact-check-x-knowledge-compare)

Your own site

<a href="https://agentmods.dev/skills/asi2030/fact-check-x/fact-check-x-knowledge-compare"><img src="https://agentmods.dev/badge/skills/asi2030/fact-check-x/fact-check-x-knowledge-compare/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/asi2030/fact-check-x/fact-check-x-knowledge-compare"><img src="https://agentmods.dev/badge/skills/asi2030/fact-check-x/fact-check-x-knowledge-compare.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 79 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 906 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.

Model	Per session	Once invoked
Fable 5.1	$0.00079	$0.00906
Opus 5	$0.00039	$0.00453
Sonnet 5	$0.00016	$0.00181
Haiku 4.5	$0.00008	$0.00091

Measured 11d ago against content hash 5add71ee98bb, 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-knowledge-compare 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 11d ago.

The scan reads SKILL.md. This mod also ships 5 executable files (scripts/common.py, scripts/knowledge_compare.py, scripts/render_comparison.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-knowledge-compare/SKILL.md · 60 lines

What it actually says

知识点结构化对比

本技能是独立、可选的本地中间层。它回答“各家说了什么、哪里相同或不同、各自有没有依据、是否忠实于自己的依据”，不回答外部世界中谁最终正确。

当前承载技能的智能体（Codex、Claude Code 等）直接完成知识点拆解和语义判断。脚本只生成任务包、校验证据约束、标准化结构并渲染报告，不调用模型 API。

第一步：生成分析任务包

python3 scripts/knowledge_compare.py \
  --input <run>/results.json \
  --task-output <run>/comparison-task.json

阅读 comparison-task.json 后，由当前智能体写出 comparison-analysis.json。必须遵守：

合并所有成功平台中可独立核验的事实，每个知识点只表达一个事实变量。
原子性同时约束知识点和各平台 claim；原句包含多个独立义务、条件、对象、数值或后果时必须拆点，每个 claim 只保留当前事实，answerExcerpt 可以复用原句。
仅个别平台提出的实质新增事实也要单独成点，其他平台标为未覆盖；不得把新增事实并入宽泛知识点后借用深知晓锚点免查。
同一事实的不同数值或条件放在同一知识点下，不拆成两点。
direct 是缺失后就没有直接回答用户问题；reference 是背景、提醒或延伸。
每个平台逐点写明主张、所附依据和来源忠实性。
有显式引用标记的平台，只能使用该回答实际标出的来源；不得从未标出的来源中补证。
无显式引用标记的平台，才可以在该平台完整原始来源集合中寻找依据。
只使用原始答案采集阶段已捕获的 URL 与正文，不搜索、不换链、不引入外部事实。
若确认深知晓该知识点使用可信搜索且所附官方证据支持同一个原子事实，可声明 trustedAnchor；锚点只能覆盖该事实变量，超出部分必须另起无锚点知识点，由下游可信搜索核验。
顶层必须生成 synthesisDraft：status 固定为 unverified，正文基于全部相关知识点合并并保留冲突、条件和缺口，basisKnowledgePointIds 只能引用当前知识点。它是独立可交付的“综合草案（未核验）”，不能冒充权威最终答案。

第二步：验收并渲染

python3 scripts/knowledge_compare.py \
  --input <run>/results.json \
  --analysis <run>/comparison-analysis.json \
  --output <run>/comparison.json

python3 scripts/render_comparison.py \
  --results <run>/results.json \
  --comparison <run>/comparison.json \
  --output <run>/comparison.html

comparison.html 按实际平台数展示全部原始答案与来源、知识点对比概览和 “综合草案（未核验）”；下方展示逐知识点完整对照。

交付门禁

python3 tests/smoke_test.py
python3 "${CODEX_HOME:-$HOME/.codex}/skills/.system/skill-creator/scripts/quick_validate.py" .

数据形状见数据契约，分类和引用规则见验收标准。

Files

What ships with it

10 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.

11d ago First seen · 60 lines · 79 tokens per session scan A 5add71ee98bb

Subscribe to this mod's changes

fact-check-x-knowledge-compare is a skill published in the GitHub repository ASI2030/Fact-Check-X (1 stars, last pushed today), licensed Apache-2.0. It adds 79 tokens to every session and 906 once invoked, about $0.0004 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.

Analytics and metrics Claude Code Research agent-skills ai-agents codex evidence fact-checking

fact-check-x-knowledge-compare

Getting it into your agent

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

What it actually says

知识点结构化对比

第一步：生成分析任务包

第二步：验收并渲染

交付门禁

What ships with it

What this file has done since we first saw it

Other skills, from other repositories

academic-writing

accessibility-compliance

one-way-door

crisis-communications

newsletter-publishing

photo-metadata