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-unifiedgit 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-unified)<a href="https://agentmods.dev/skills/asi2030/fact-check-x/fact-check-x-unified"><img src="https://agentmods.dev/badge/skills/asi2030/fact-check-x/fact-check-x-unified/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-unified"><img src="https://agentmods.dev/badge/skills/asi2030/fact-check-x/fact-check-x-unified.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 | $0.00070 | $0.02370 |
| Opus 5 | $0.00035 | $0.01185 |
| Sonnet 5 | $0.00014 | $0.00474 |
| Haiku 4.5 | $0.00007 | $0.00237 |
Grade A, and why
fact-check-x-unified 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 — 154 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Fact-Check-X 统一入口
本技能只做编排,不内嵌三个业务层。它按以下顺序调用兄弟技能:
llm-answer-reference-compare:多平台回答、引用与现场存证采集。fact-check-x-knowledge-compare:本地知识点结构化对比,可选。fact-check-x-authoritative-verify:逐知识点并发权威核验与平台表现报告。
所有语义拆解和证据裁决由当前承载技能的智能体完成。脚本不调用任何模型 API。
依赖定位
四个技能放在同一目录时可直接运行。也可设置:
export FACTCHECK_SKILLS_DIR="<四个技能的父目录>"
检查依赖:
python3 scripts/fact_check_x.py locate
完整流程
先采集 results.json,然后准备知识点对比:
python3 scripts/fact_check_x.py prepare-comparison \
--results <results.json> \
--run-dir <run>
命令会同步生成“各方答案汇总”,在运行目录顶层生成 01-capture-report.html,并通过 deliverables 返回用户可见路径。调用方必须先用该路径发送真正的 Markdown 文件链接,再继续知识点对比;禁止只显示反引号路径。
默认交互模式下,程序会把阶段状态写入 stage-checkpoints.json。调用方发送本阶段产物并收到用户“继续下一步”后,必须使用 checkpoint.acknowledgement.token 执行:
python3 scripts/fact_check_x.py acknowledge-stage \
--run-dir <run> --stage <checkpoint.stage> \
--token <checkpoint.acknowledgement.token> --decision continue
未确认时,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,也必须依次展示每个阶段产物并取得确认;不存在可绕过确认的自动推进模式。
当前智能体读取 <run>/comparison-task.json,写入 <run>/comparison-analysis.json,再执行:
拆解时,原子性同时约束知识点和各平台 claim。一个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;平台独有的实质新增事实也要另起无锚点知识点,不能并入宽泛知识点后复用深知晓锚点免查。
python3 scripts/fact_check_x.py complete-comparison \
--results <results.json> \
--run-dir <run>
命令会在运行目录顶层生成 02-comparison-report.html,并通过 deliverables 返回路径;调用方必须把它作为独立可点击文件展示给用户。报告必须包含明确标为“未核验”的综合草案。默认交互模式下,用户确认继续后才能进入权威核验。
生成每个知识点的独立云端请求并并发取证:
python3 scripts/fact_check_x.py prepare-authority --run-dir <run>
python3 scripts/fact_check_x.py search-authority --run-dir <run> --max-workers 12
知识点已有深知晓/深知晓(深度溯源)本次回答所附的官方材料,或其他平台本次回答所附的 gov.cn 材料,且原文确实支持当前主张时,直接复用为官方证据,不调用可信搜索。只有不属于上述情形或已有材料不足以裁决时,才是非免查知识点。
若存在非免查知识点但本机尚无可信搜索配置,prepare-authority 和 search-authority 会返回 status=configuration_required、userPrompt 与 configuration.command 并以非零状态退出。调用方先展示登录提示,再前台执行该命令。用户只需在自动打开的深知 MaaS 页面完成登录;组件会自动复用已有完整 Key,没有时创建 Fact-Check-X 专用 Key,验证后保存到 ~/.fact-check-x/credentials/trusted-search-key。Codex、Claude Code、WorkBuddy 等载体共享该配置,检测到已有 Key 时直接跳过登录。配置成功后调用方自动重跑 prepare-authority,不得要求用户复制 Key、编辑 shell 配置、回复“已配置”,也不得改用深知晓来源或普通搜索绕过。
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.
- agents/openai.yaml 303 B
- references/acceptance-criteria.md 2.8 KB
- references/contracts.md 1.4 KB
- scripts/common.py 832 B runs code
- scripts/fact_check_x.py 65 KB runs code
- scripts/trusted_search_config.py 10 KB runs code
- tests/multi_platform_test.py 13 KB runs code
- tests/smoke_test.py 32 KB runs code
- tests/stage_checkpoint_test.py 3.6 KB runs code
- tests/trusted_search_config_test.py 5.7 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 3abf1de82570
- 12d ago First seen · 154 lines · 70 tokens per session scan A e02b907cfb35
fact-check-x-unified is a skill published in the GitHub repository ASI2030/Fact-Check-X (1 stars, last pushed yesterday), licensed Apache-2.0. It adds 70 tokens to every session and 2,370 once invoked, about $0.0003 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.