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 cka4913/qimen-mcp --skill qimengit clone --depth 1 https://github.com/cka4913/qimen-mcpWrote 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/cka4913/qimen-mcp/qimen)<a href="https://agentmods.dev/skills/cka4913/qimen-mcp/qimen"><img src="https://agentmods.dev/badge/skills/cka4913/qimen-mcp/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/cka4913/qimen-mcp/qimen"><img src="https://agentmods.dev/badge/skills/cka4913/qimen-mcp/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 | $0.00062 | $0.03987 |
| Opus 5 | $0.00031 | $0.01994 |
| Sonnet 5 | $0.00012 | $0.00797 |
| Haiku 4.5 | $0.00006 | $0.00399 |
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 9d 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 — 219 lines — stays where its author put it; the contents beside it link to each section on GitHub.
奇門遁甲解讀
qimen-mcp 只回傳事實:哪一顆星落在哪個宮位、哪一道門配哪一個天干、值符值使在哪裡。判斷完全是你的工作。
本文件說明如何從事實推進到判斷,以及哪些事情不可以做。
草稿聲明:以下取用神與格局部分,係按《煙波釣叟歌》、《奇門遁甲統宗》一路的通用學理, 加上原 repo
data/system_prompts.json四個 persona 的取向整合而成,未經流派校訂。 各家取用神有出入(尤其求財、官非、疾病三類),使用前請按自己師承核對。
零、鐵律
- 每一句判語都要指得出是哪一個 tool result 的哪一欄。 講不出出處的話不要講。
- 不准補盤。 盤上沒有的東西(例如某顆星不在盤上)就是沒有,不准推一個出來。
- 時間要明文。 起「現在」的盤,先呼叫
resolve_time,再將其datetime傳下去。 引擎不會自己讀時鐘,你也不准假設。 - 拆補與置閏,未講明時預設拆補,但必須明確告知並提供改用置閏的選項。 兩派結論會不同,沒有哪一派是「正確」。 用戶已表明立場就用該派;用戶沒有表明,就用拆補法起盤,同時在輸出中註明「本盤用拆補法起局,如需置閏法結果可告知」—— 不准在完全不告知的情況下代用戶選擇。
- 不講死。 奇門是參考,不是判決。涉及健康、法律、財務的問題, 講完盤象之後要明確請用戶諮詢專業人士。
- 法術奇門(閉六戊)不主動提出。 用戶明確詢問才呼叫
get_closed_sixwu, 而且要問清楚對方要演義版還是寶鑑版——兩個傳承方向相反,沒有預設。 - 命主生年是補充參考點,不是必需輸入,也不會改變盤面本身。 見第二節「年命宮」;沒有生年資料時, 一切分析照常以值符、值使、日干、時干為中心進行。
一、起盤流程
用戶問事
↓
時間從何而來?
── 用戶已提供 → 直接使用
└ 未提供、問「現在」 → 呼叫 resolve_time:
自動偵測時區與當地時間後,向用戶覆述並請其確認;
用戶不同意該時區/時間,則請用戶自行提供
↓
命主生年(選填)?
── 用戶已提供 → 記下(例如「1984 年,甲子年」),作為年命宮的補充參考(見第二節)
└ 未提供 → 略過,不主動追問
↓
排局法用哪一派?
── 用戶已表明 → 使用該派
└ 未表明 → 使用拆補法,並在輸出中註明「本盤用拆補法起局,如需置閏法結果可告知」
↓
get_qimen_chart(時家為主)
↓
需要更精細 → get_qimen_chart_minute(刻家)
需要日課 → get_golden_mirror_chart(金函玉鏡)
需要擇時 → find_chart_times(由條件反查時辰,見下)
↓
check_patterns(格局)
↓
解讀
用戶如果追問「為何今日是這個局」,或想比較兩派差多遠而不想排成整盤,
可用 get_ju:它只回傳三個局名,加上置閏法的完整推導(距節氣日數、三元、四個候選局)。
擇時:反過來由條件找時辰
以上流程是「給定時間,排出盤面」。若用戶問的是擇時——「幾時動土好」、
「下次青龍返首帶生門是幾時」——方向相反,應改用 find_chart_times。
用法要點:
- 條件必須同宮成立。
doors:["生"] + skyStems:["丙"]是找「生門與丙同落一宮」, 不是「盤中有生門、另一處有丙」。每筆結果會標明中在哪一宮。 - 單一條件幾乎沒有篩選力。 每張盤必含全部八門、八神、八星,所以不限宮位而只給一個門, 會命中所有時辰。格局也不罕見(青龍返首約佔 18%)。至少夾兩個條件,或限定宮位。
- 不會回總數。 找夠就停,所以只能回已找到的。要繼續找,用回傳的
scannedThrough當作下次的start。 - 先想清楚用神,再把用神對應的符號放進條件——例如求財擇時就找生門配吉干, 而不是隨便湊一堆條件。找出來的時辰仍須逐一排盤解讀,不可只憑命中就下判斷。
時家 vs 刻家 vs 金函:
- 時家 — 主力。一個時辰一盤,占事、擇時、方位皆用它。沒有特別理由就用時家。
- 刻家 — 十分鐘一盤。用於需要分得很細的情況(同一個時辰內有幾件事、或詢問「現在這一刻」)。
- 金函玉鏡 — 一日一盤,日課性質。詢問「今日整體如何」、擇日時使用。
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.
- 9d ago First seen · 219 lines · 62 tokens per session scan A 6b1b58e6d5e2
qimen is a skill published in the GitHub repository cka4913/qimen-mcp (1 stars, last pushed 1mo ago), licensed MIT. It adds 62 tokens to every session and 3,987 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…