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-bazigit 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-bazi)<a href="https://agentmods.dev/skills/ml8s/liki/liki-bazi"><img src="https://agentmods.dev/badge/skills/ml8s/liki/liki-bazi/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-bazi"><img src="https://agentmods.dev/badge/skills/ml8s/liki/liki-bazi.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 197 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 | $0.00090 | $0.01641 |
| Opus 5 | $0.00045 | $0.00821 |
| Sonnet 5 | $0.00018 | $0.00328 |
| Haiku 4.5 | $0.00009 | $0.00164 |
Grade A, and why
liki-bazi 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.
How it starts
The opening of the file, as written. The whole thing — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Liki 八字 — 八字 / 紫微
覆盖八字排盘、十神格局、大运流年，以及紫微命盘、宫位星曜、大限流年；两者通过引擎断语合参。
启动与工具
- 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。 - 读
tools/skill-tools.json取工具 schema。 - 用
python3 tools/agent_cli.py执行工具：stdin 传{"fn":"...","args":{...}}，stdout 读 JSON；RPC 端点默认生产地址，设置LIKI_RPC_URL时优先使用。Windows 使用tools/agent_cli.cmd和 UTF-8 文件。 - 完成上述检查后进入路由。
路由
| 用户问题 | 入口 |
|---|---|
| 婚姻 / 感情 / 合婚 | app/marriage.md、app/compatibility.md |
| 事业 / 财运 / 学业 | app/career.md、app/wealth.md、app/study.md |
| 健康 / 性格 / 家庭 | app/health.md、app/personality.md、app/family.md |
| 排盘 / 随便看看 / 快速扫描 | app/mingshu.md |
| 完整命书 / 全盘报告 | app/mingshu-full.md |
| 占卜 / 风水 / 起名 | 转介对应 liki-divination、liki-fengshui、liki-naming |
| 其他 | 确认意图后选择相近卡 |
核心流程
| 步骤 | 条件 | 动作 | 产物 |
|---|---|---|---|
| 1 | 用户给具体时刻 | city_coords → full_paipan(correct=true) |
带 pan_digest 的完整 pan |
| 1 | 用户已明确时辰 | full_paipan(correct=false) |
带 pan_digest 的完整 pan |
| 1 | 时间距时辰交界 ≤30 分钟 | 先排盘，再提示相邻时辰校准 | 带校准提示的结果 |
| 1 | 时辰模糊或未知 | 收集候选与事件 → calibrate；读取 domains/bazi/calibration.md、domains/ziwei/calibration.md |
候选置信度 |
| 2 | 场景明确 | 读取对应 app 卡并执行 | 场景所需断言 |
| 3 | 本命分析 | query(rule, pan) |
八字 / 紫微 / 合参断语 |
| 4 | 应期分析 | yearly_range(pan, start, end, rules) |
含当前年来源与八字 / 紫微年界说明的流年事件与候选应期 |
| 5 | 双人关系 | bond(pan_a, pan_b) |
合盘因子 |
| 6 | 输出 | 按 app 模板综合 | 结论 + 依据链 |
同一会话复用 full_paipan 返回的完整 pan；多领域问题走主场景全流程，次领域仅查询佐证。信号冲突按 domains/bazi/caijue.md 裁决；有真实事件时取 3-5 段已发生时段验证，无验证则标注。用户只给出生地与时钟时间，时区、夏令时与真太阳时由工具链处理。
query 口径：夫妻 / 官禄 / 财帛 分别返回对应紫微宫位域；十神 返回八字结构及其跨人生领域信号。需要单一生活领域时优先使用宫位域，不把 十神 当作唯一领域查询。
硬边界
pan是 immutable 排盘结果；query/yearly_range/bond/calibrate会校验 pan_digest，不得修改或手工拼装。- 排盘、限运、因子与断语以工具和表数据为准；缺失字段标注不可用。
query/yearly_range只传入full_paipan的完整pan；跨度含端点最多 120 年。correct=true必须提供经度；缺出生地时先问城市，仍缺失则停止校正排盘。- 出生时间距时辰交界 ≤30 分钟时，必须提示可校准；不得把该时辰表述为唯一确定事实。
- 考时证据不足时输出「考时证据不足」；用户指定候选时标注「未经考时确认」。
- 八字与紫微单侧结论各自输出；合参结论仅来自 common 断言。
- 医疗、法律、金融只给传统文化视角提示，并引导专业服务；出生信息只在当前对话使用。
What ships with it
60 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.
- app/career.md 1.3 KB
- app/compatibility.md 1.3 KB
- app/family.md 1.9 KB
- app/health.md 1.8 KB
- app/marriage.md 2.0 KB
- app/mingshu-full.md 3.4 KB
- app/mingshu.md 1.9 KB
- app/personality.md 1.5 KB
- app/README.md 980 B
- app/study.md 1.6 KB
- app/wealth.md 1.3 KB
- domains/bazi/caijue.md 15 KB
- domains/bazi/calibration.md 2.3 KB
- domains/bazi/career.md 1.9 KB
- domains/bazi/dayun.md 9.8 KB
- domains/bazi/family.md 6.0 KB
- domains/bazi/geju.md 2.3 KB
- domains/bazi/gongwei.md 1.7 KB
- domains/bazi/hehui.md 5.7 KB
- domains/bazi/hepan.md 3.0 KB
- domains/bazi/shishen.md 7.3 KB
- domains/bazi/study.md 3.7 KB
- domains/bazi/tiaohou.md 11 KB
- domains/bazi/wangshuai.md 7.3 KB
- domains/bazi/wealth.md 3.4 KB
- domains/bazi/wuxing-health.md 3.5 KB
- domains/bazi/yongshen.md 8.7 KB
- domains/ziwei/calibration.md 1.4 KB
- domains/ziwei/geju.md 1.1 KB
- domains/ziwei/gexing.md 2.3 KB
- domains/ziwei/gong12.md 3.1 KB
- domains/ziwei/liunian.md 2.0 KB
- domains/ziwei/xiangmao.md 2.3 KB
- domains/ziwei/yingqi.md 1.9 KB
- domains/ziwei/zhuxing.md 4.9 KB
- tools/agent_cli.cmd 200 B runs code
- tools/agent_cli.py 3.6 KB runs code
- tools/assertion_store.py 3.9 KB runs code
- tools/assertions/assertion_conditions.csv 29 KB
- tools/assertions/assertions.csv 173 KB
- tools/calibrate.py 4.9 KB runs code
- tools/constants.json 13 KB
- tools/duanyu.py 16 KB runs code
- tools/errors.py 1006 B runs code
- tools/factor_constants.py 536 B runs code
- tools/factor_context.py 955 B runs code
- tools/factor_tables.py 6.4 KB runs code
- tools/factors.py 11 KB runs code
- tools/factors/factors_liunian.csv 10 KB
- tools/factors/factors.csv 63 KB
- tools/natal_projection_contract.json 1.8 KB
- tools/natal_projection.py 2.7 KB runs code
- tools/operators_liunian.py 15 KB runs code
- tools/operators_natal.py 20 KB runs code
- tools/paipan.py 7.7 KB runs code
- tools/pan_integrity.py 1.4 KB runs code
- tools/pan_schema.py 6.7 KB runs code
- tools/skill-tools.json 35 KB
- tools/yearly_eval.py 3.4 KB runs code
- VERSION 13 B
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 · +5 lines 60cc4b15c161
- 2d ago Changed · -127 lines scan B → A 0dbba491936b
- 6d ago Changed · +4 lines c597b5d1b87a
- 7d ago Changed · +20 lines 477c7c400a82
- 11d ago First seen · 179 lines · 90 tokens per session scan B ade617db2025
liki-bazi is a skill published in the GitHub repository ml8s/liki (60 stars, last pushed today), licensed MIT. It adds 90 tokens to every session and 1,641 once invoked, about $0.0005 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.