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 konglong87/xuanxue-skills --skill qimengit clone --depth 1 https://github.com/konglong87/xuanxue-skillsWrote 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/konglong87/xuanxue-skills/qimen)<a href="https://agentmods.dev/skills/konglong87/xuanxue-skills/qimen"><img src="https://agentmods.dev/badge/skills/konglong87/xuanxue-skills/qimen/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/konglong87/xuanxue-skills/qimen"><img src="https://agentmods.dev/badge/skills/konglong87/xuanxue-skills/qimen.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 | $0.00059 | $0.00942 |
| Opus 5 | $0.00030 | $0.00471 |
| Sonnet 5 | $0.00012 | $0.00188 |
| Haiku 4.5 | $0.00006 | $0.00094 |
Grade A, and why
qimen scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
奇门外部局盘判读
核心原则
本技能只接收外部 APP 已起好的局盘截图或用户提供的手工转录，不自行起局。宿主先逐宫转录，再把对象交给 lib/chart.js 的 normalizeChart(transcribed)；不得调用 flyStars，不得用模型心算补盘。
执行流程
- 确认来源为“外部APP”或“手工转录”，记录来源名称。截图由宿主读取；代码不声称具备图片识别能力。
- 按 methodology.md 转录盘级
月令、值符、值使，以及八方加中宫共九宫的方向、天盘干、地盘干、八门、九星、八神、标记。 - 每个标记都在审计
chart中保留raw、source、school。门破和门迫按不同原词分别记录，不互换、不归并。 - 调用
normalizeChart(transcribed)。errors非空时只展示结构化 safe errors 与一次性补录清单并停止奇门判读；未知字段名属于untrusted-audit-only输入，不进入公共错误，错误只给父容器下稳定$unexpected[n]引用。每容器未知字段、公共错误总数、九宫数量和单宫标记数量均受冻结常量限制；超限分别给固定unexpected_fields_truncated、errors_truncated、palace_count_exceeded或marker_count_exceeded，不深遍历越界内容。chart仅供本地审计，不进入模型上下文或报告。 errors为空时，只把safeChart交给判读和报告。safeChart只含确认枚举、存在标志及稳定provenanceRef，不含来源名称、raw、source、school自由文本；表达与行动原样渲染REPORT_CONTRACT.evidenceRules和REPORT_CONTRACT.redlines，本文件不改写。
状态输入
明确值可直接转录为字符串。截图缺失或有疑义时使用 { "status": "missing|unreadable|uncertain|unknown", "raw": "外部盘原词" }。raw 只在审计 chart 保留原图文字；禁止为通过校验而把疑义字段改成确定值。确认无宫级标记时必须明确填写空数组，不能省略字段。
路由边界
只有出生资料且未提供外部奇门局盘时转 bazi；明确婚恋问题转 love-marriage，明确事业财运问题转 wealth-career，其中奇门只作为可选外部增强。同时明确询问事业与婚恋时转 bazi 输出概览，并说明可再分别进入两个领域技能深入。手掌照片转 palm。住宅风水与占卜能力均为 future / 未交付，当前不支持且不得调用不存在的技能。
用户显式点名技能时覆盖自动路由，但仍须遵守本技能不自研起局的边界。信息不足时一次性追问全部缺失项并停止；用户要求本技能起局时说明当前不实现起局，并请其提供可信外部 APP 局盘。
安全唯一来源
从 lib/chart.js 读取 REPORT_CONTRACT。其 disclaimer 由共享 disclaimerFor('奇门') 生成，evidenceRules 与 redlines 也是共享安全快照。报告必须逐条原样输出这些字段，不在技能内另写或改写同义安全措辞。
What ships with it
4 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.
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.
- 12d ago First seen · 33 lines · 59 tokens per session scan A edb67e589b53
qimen is a skill published in the GitHub repository konglong87/xuanxue-skills (3 stars, last pushed 2d ago), licensed MIT. It adds 59 tokens to every session and 942 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
liki-bazi
A Chinese traditional fortune-reading tool using BaZi, a birth-chart system based on birth details, and Zi Wei Dou Shu, another Chinese astrology system. It can examine life areas and yearly trends, but its conclusions are for cultural reference, not professional advice.
liki-divination
A traditional Chinese divination skill covering Liuyao readings, Qimen decisions, and selecting auspicious dates. It interprets an automatically generated chart using defined rules and presents the result as cultural guidance, not professional advice.
liki-fengshui
A tool for analysing home layouts and directions through traditional Chinese feng shui methods, including Eight Mansions and Flying Stars. Feng shui is a traditional system for interpreting how spaces, directions, and time relate to one another.
liki-naming
A Chinese naming tool that combines BaZi, a birth-chart system based on birth details, with traditional name analysis called Sancai-Wuge. It can also assess existing names and help create Chinese names from English names.
liki-hepan
A traditional Chinese relationship reading that combines Bazi, a birth-chart system, with Zi Wei Dou Shu, another Chinese astrology system. It uses both people's birth information to produce a detailed compatibility report.
liki-mingshu
An AI workflow for producing a Chinese traditional-culture fortune-telling report as JSON. It generates a report, reviews it, and revises it when the review fails; the results are for reference, not professional advice.