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 ml8s/liki --skill liki-fengshuigit clone --depth 1 https://github.com/ml8s/likiWrote 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/ml8s/liki/liki-fengshui)<a href="https://agentmods.dev/skills/ml8s/liki/liki-fengshui"><img src="https://agentmods.dev/badge/skills/ml8s/liki/liki-fengshui/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/ml8s/liki/liki-fengshui"><img src="https://agentmods.dev/badge/skills/ml8s/liki/liki-fengshui.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium MCP Rug Pull · line 15 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
- medium Data Exfiltration · line 104 Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
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 | $0.00073 | $0.01264 |
| Opus 5 | $0.00036 | $0.00632 |
| Sonnet 5 | $0.00015 | $0.00253 |
| Haiku 4.5 | $0.00007 | $0.00126 |
Grade A, and why
liki-fengshui 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 today.
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
Liki 风水 — 八宅 / 玄空
覆盖八宅命卦、门主灶与方位吉凶，以及玄空飞星、元运和流年盘。引擎负责排盘，LLM 负责解读返回因子。
启动与 RPC
- 外部安装副本先读本地
VERSION与远程VERSION；不一致时提示更新命令并等待确认，远程 10 秒不可达时标注后继续。托管环境跳过检查。 - POST JSON-RPC：默认
https://liki.hk/jsonrpc，设置LIKI_RPC_URL时使用该端点；Content-Type 为application/json。 - 用
rpc.discover读取bazhai,xuankong,time.now的最终 schema。 - 完成上述检查后进入路由。
路由
所有风水 / 家宅 / 布局 / 流年飞星问题读取 app/fengshui.md，卡内再分八宅与玄空分支。
核心流程
| 步骤 | 条件 | 动作 | 产物 |
|---|---|---|---|
| 1 | 流年或元运问题 | time.now |
当前年基准 |
| 2 | 八宅问题 | bazhai.chart → bazhai.layout |
命卦、吉凶方、门主灶 |
| 2 | 玄空问题 | xuankong.chart，按需 xuankong.liunian |
山向盘、元运、流年飞星 |
| 3 | 已有数据 | 读取 app/fengshui.md 与 domain 文档 |
解读规则 |
| 4 | 输出 | 按模板综合 | 结论 + 方位建议 |
硬边界
-
xuankong.chart返回带chart_digest的完整宅盘；传给xuankong.liunian时 digest 必须匹配，不得手工拼装或修改。 -
命卦、飞星、元运与流年盘全部来自 RPC；LLM 只解释返回字段。
-
八宅只需要出生年份和性别；玄空不需要命主出生日期，需要宅运起盘日期与房屋坐向。
-
玄空坐山与向山必须相对 180°（二十四山相隔 12 位）；同山或任意两山组合不是合法坐向。
-
二十四山 index 以 engine schema 为准：
0=子,1=癸,2=丑,3=艮,4=寅,5=甲,6=卯,7=乙,8=辰,9=巽,10=巳,11=丙,12=午,13=丁,14=未,15=坤,16=申,17=庚,18=酉,19=辛,20=戌,21=乾,22=亥,23=壬。优先复述zuo_shan_name/xiang_shan_name让用户确认。 -
缺房屋坐向 / 宅运日期时先询问；缺出生年份或性别时先询问命卦所需参数。
-
布局建议表述为传统文化视角；建筑、安全、法律与医疗问题引导专业人员。
输出契约
- 首句给布局判断，随后列命卦 / 飞星 / 元运依据。
- 专断因子优先；冲突因子并列解释，三个以上同向因子才形成综合判断。
- 八宅与玄空冲突按
app/fengshui.md和domains/fengshui/caijue.md分层裁决；不得只引用有利体系。 - 每个建议绑定具体方位和引擎因子；冲煞或凶方同时给可行动调整。
- 涉及健康、睡眠、安全、重大装修或年龄敏感布局时，附现实专业确认提示；不得让命理结论替代建筑、医疗或安全评估。
- 输出语言跟随用户；英文首次出现核心术语时括注英文。
JSON-RPC 参数错误按 schema 修正后重试；网络超时告知用户可重试；HTTP 403 更换 HTTP 客户端或请求头。反馈提交到 https://liki.hk/api/feedback，请求体使用 UTF-8。
交互与安全
- 流程表中标记 ⛔ 的步骤为阻塞确认：LLM 必须展示当前结果和编号选项，等待用户回复后才能继续。禁止跳过 ⛔ 节点直接排盘或展开布局建议。
- 流程表中标记 💬 的步骤为参数收集：LLM 一次列出所有待收集项和默认值，用户可一次回复或说“都用默认”。
- 每个交互步骤只输出该步骤的内容，禁止提前输出后续步骤的结果。
- 阳台、大门与主要采光面朝向可能不同；排盘前必须确认以哪一项作为坐向依据。
- 仅服务风水话题；建筑、安全、法律与医疗问题引导专业人员，避免宿命化表述。
What ships with it
6 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.
- today Changed · +9 lines 2b75f7f4dbfe
- yesterday Changed · +1 lines c2f3fdfda7cb
- 2d ago Changed · -60 lines scan B → A 2e00ef62efd7
- 7d ago Changed 83ebea772790
- 11d ago First seen · 110 lines · 73 tokens per session scan B cd317469c8eb
liki-fengshui is a skill published in the GitHub repository ml8s/liki (60 stars, last pushed today), licensed MIT. It adds 73 tokens to every session and 1,264 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 2026-08-30.
Other skills, from other repositories
yueyuan
A specialised BaZi analysis system, where BaZi is a Chinese birth-chart method based on birth date and time. It is designed for structured analysis with explicit uncertainty and requires the user to check the chart before deeper interpretation.
horosa-agent
Use this skill when an AI agent is connected to Horosa Skill through MCP, CLI, Cursor, Claude, Codex, OpenClaw, Open WebUI, or another local-first client and needs to call Horosa metaphysics tools, generate reports, store memory, or debug user-facing results.
bazi-skill-gaoxin492-main
A Chinese Four Pillars astrology skill that uses local Python scripts to calculate and store birth charts, while the agent interprets the results. Four Pillars is a traditional Chinese system based on birth date and time.
fengshui-master
A guide to traditional Chinese feng shui, the practice of assessing places through their layout, surroundings, direction, and timing. It covers approaches including Flying Stars, Eight Houses, landform analysis, date selection, and links with Four Pillars astrology.
aov-mingyu-api
An interface to the aov.cc public API for Chinese astrology, divination, tarot, calendars, and related prompt generation.
yinyuan
A structured Chinese fortune-telling skill focused on relationships, compatibility, and romantic timing. It covers methods such as birth-chart matching, zodiac pairing, marriage charts, fortune sticks, and “peach blossom” luck.