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 agentmods add skills/mxm-sys/opencode-tianji/zhanbunpx skills add Mxm-sys/opencode-tianji --skill zhanbugit clone --depth 1 https://github.com/Mxm-sys/opencode-tianjiWhat 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 | $0.00146 | $0.01930 |
| Opus 5 | $0.00073 | $0.00965 |
| Sonnet 5 | $0.00029 | $0.00386 |
| Haiku 4.5 | $0.00015 | $0.00193 |
Grade A, and why
zhanbu 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.
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 — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.
六爻占卜工作流(先问后算)
本技能在用户请求占卜类服务时生效。核心铁律:未收集齐必问信息前,禁止调用 qigua/paipan/duangua 工具。
第 0 步:心诚与预告
开始前用一两句话告知用户占卜须知:一事一占(一次只问一件事,不可一卦兼断),心诚则灵(心中默念所问之事)。若用户想同时问多事,提醒其分别起卦。
第 1 步:必问信息(用 question 工具)
在调用任何占卜工具之前,必须调用 question 工具一次性收集以下 5 项(其中第 1、2、3 项为硬性必问):
- 占卜事项(最重要):用户具体想问什么?
- 分类可参考:求财、事业功名、婚姻感情、健康疾病、出行/行人、词讼官非、失物寻找、家宅风水、考试文书、子嗣、终身运势、其他。
- 必须问清具体情境:例如"求财"要问清是投资/生意/工作收入;"婚姻"要问清单身寻缘还是已婚问感情。
- 求测人性别(占婚姻/感情必用,影响用神与部分断法,如女占以官鬼为用、男占以妻财为用)。
- 是否本人求测、为谁而占:自占以世爻为己;代占他人须问清与被测人关系(父母/子女/配偶/朋友/领导…),以定用神。
- 地理位置/所在方位:问清求测人当前所在城市或方位。方位影响出行/行人/失物/家宅类断卦,以及梅花易数时间起卦的地支与五行取象。如"人在北京""人已动身去南方"。
- 起卦时间:默认用当前时间;若用户指定(如"昨晚发生的""想算明天的事"),按用户指定的时间起卦。
若用户对某必问项沉默,可合理推断但须在输出中注明"此处按 XX 推断"。
第 2 步:据事项补充情境(question 工具)
针对占卜事项追问关键细节(可选,但能显著提升断卦质量):
- 求财:资金大小、求财周期(短期/长期)、是守是求。
- 婚姻感情:现状(单身/恋爱/已婚/离异)、问结合还是问现状。
- 疾病:是否就医、近病久病(近病逢冲即愈,久病逢冲则危)。
- 出行/行人:去往何方位、何时去、预期归期。
- 失物:何时何地丢失、物品种类。
- 官非词讼:是原告/被告、是否已立案。
- 家宅:是买房/动土/迁居还是查运势。
第 3 步:确认后起卦(qigua)
将收集的信息与用户确认(可简略复述),然后:
- 若用户未自己摇卦 → 用
qigua起卦(method=time时间起卦,或coins铜钱随机;时间传入第 1 步确认的时间)。 - 若用户已摇出卦 → 用
qiguamethod=manual,请用户提供卦名/动爻(或六次掷币结果)。
第 4 步:排盘(paipan)
调用 paipan,传入:卦名、动爻、起卦时间、占事。核对世应、六亲、用神、旬空、月破、六神、卦身。
第 5 步:断卦(duangua + cha)
- 用
duangua按占事分类取用神断吉凶倾向。 - 用
cha查卦辞、爻辞、变卦、焦氏易林变诗,用于佐证。 - 断卦要结合第 1、2 步的用户情境(性别、方位、关系)落地成具体人话,避免空泛。
第 6 步:输出规范
铁律:每个术语性结论后必须紧跟一段白话文翻译,让完全不懂卦的用户也能看懂。 禁止只给卦学术语。
输出格式建议:
【求测】占事 | 性别 | 为谁而占 | 所在方位 | 起卦时间
【卦象】本卦·变卦·动爻
【排盘】世应/用神/旬空/月破等关键点
【断卦】分条给出: 结论 + 依据(数据/卦辞/爻辞)+ 白话文解释 + 针对用户情境的具体化建议
【应期】时间上的提示(据卦理,不强断)
【总结】一段纯白话全文总结(像跟朋友讲话一样,概括此卦吉凶走向与要做的事)
白话文写法要求:
-
把术语"翻译成人话":如"官鬼持世偏弱"→"代表你自身状态的那股气目前不太旺,考试要下硬功夫";"子孙剥官"→"有让你分心、发挥受限的因素在";"旬空"→"眼下还虚着/还没落实";"应爻生世"→"有人会帮你,但要主动去争取"。
-
每条断语先给一句大白话结论(吉/凶/中平/谨慎),再讲为什么(可以带术语,但必须翻译)。
-
结尾【总结】必须是纯白话,不出现卦学术语,说明:此卦总体如何、最需要注意什么、建议怎么做。
-
每条结论须有依据,不能只给结论。
-
断卦为传统文化参考,结尾可加一句"仅供参考,现实决策请结合实际情况"。
-
全程中文,语气专业平和、像一位懂行的朋友,不迷信夸张。
参考资料
- 工具来源:opencode-tianji 插件(npm 包),安装后自动提供 13 个工具 qigua/paipan/duangua/cha/meihua/bazi/liuren/almanac/dayan/yilin/jingshi/huozhulin/chazhu
- 梅花体用断卦:meihua 工具(十八类占断辞据包内 data/meihua.json)
- 八字四柱:bazi 工具(十神/藏干/纳音/大运据包内 data/bazi.json、data/ganzhi.json)
- 小六壬:liuren 工具(六宫断辞据包内 data/liuren.json)
- 农历黄历:almanac 工具(农历/干支/宜忌/冲煞,基于 lunar-javascript)
- 断卦法则:paipan/duangua 工具输出(用神/旬空/月破/六冲六合/旺相休囚)
- 卦例参考:duangua 输出自带相似卦例(据包内 data/guaili.json 381 则占验卦例)
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.
- yesterday First seen · 90 lines · 146 tokens per session scan A 8db224bf06f3
zhanbu is a skill published in the GitHub repository Mxm-sys/opencode-tianji (0 stars, last pushed 24d ago), licensed MIT. It adds 146 tokens to every session and 1,930 once invoked, about $0.0007 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.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
agent-host-chat-contributions
Build and review cross-cutting agent-host chat behavior through lifecycle contributions. Use when adding turn lifecycle side effects, prompt or context injection, restored-history transformation, protocol-action observation, or when reviewing changes that add code to AgentSideEffects or AgentService.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.