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/ml8s/liki/hepannpx skills add ml8s/liki --skill hepangit 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/hepan)<a href="https://agentmods.dev/skills/ml8s/liki/hepan"><img src="https://agentmods.dev/badge/skills/ml8s/liki/hepan.svg" alt="Measured on agentmods" 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 | $0.00033 | $0.00116 |
| Opus 5 | $0.00016 | $0.00058 |
| Sonnet 5 | $0.00007 | $0.00023 |
| Haiku 4.5 | $0.00003 | $0.00012 |
Grade A, and why
liki-hepan 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 5d 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
你是一个合盘命理分析师，擅长八字和紫微斗数感情合盘。
你的任务是输出 JSON 格式的合盘报告（参考 generate.md）。 如果需要审查质量，调用 review.md 中定义的审查流程。
注意：命理结论为传统文化视角，仅供参考，不构成专业建议。
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.
- 5d ago First seen · 12 lines · 33 tokens per session scan A 17c714e3799f
liki-hepan is a skill published in the GitHub repository ml8s/liki (51 stars, last pushed yesterday), licensed MIT. It adds 33 tokens to every session and 116 once invoked, about $0.0002 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
zhanshi-jixiong
占事吉凶 · 测吉凶：针对某一件具体事、某一天、某一刻的吉凶研判与择吉建议。 运用「黄历择日 + 四柱命理本命喜忌 + 阴阳五行天时地利 + 天人感应/梅花心易」四层独立推演， 再交叉汇聚成【吉 / 平·宜谨慎 / 凶·宜改期】的整体倾向与可执行建议。 当用户问：测吉凶、占吉凶、这事能不能做、今天适不适合出门/旅行/搬家/开业/签约/求医、 出行吉凶、看日子、择日、挑个好日子、黄历、老黄历、今天宜不宜、宜忌、冲煞、起一卦、 算算这件事顺不顺、"临出发前忽然心悸/心慌，是不是预兆"、"我有种不好的预感" 时使用。 English triggers: "is today auspicious", "is it a good day…
tarot-astrology
塔罗牌占星：把「抽三张塔罗牌」与「西方占星本命盘」合为一次解读。 用户带着一个具体问题来 → 抽三张牌（可复现的 seed）→ 若愿意提供生日，则用脚本 确定性地排出星座与星盘 → 用黄金黎明的塔罗↔占星对应把两者接起来（牌落在黄道哪一旬， 你的哪颗行星正站在那里）→ 给出一张交叉对照表、对所问之事的审慎取向与可执行建议。 塔罗层：牌阵位置语义、牌与牌的组合叙事、元素尊贵、正逆位、直觉对话、治疗性解读。 占星层：本命盘、相位与宫位、必然尊贵、行运盘推运、比较盘/组合盘（合盘）、太阳弧推运。 当用户说：塔罗、塔罗牌、抽牌、抽三张牌、占卜、算一卦（西洋）、牌阵、正逆位、…
fengshui-kanyu
风水堪舆 · 阳宅/阴宅选址与布局建议。用户提供地点（最好是准确经纬度）、周边环境描述或图片、 以及阳宅或阴宅（可选朝向/坐向、建造或入住年、居者生辰性别、所求何事）→ 先用脚本确定性地 定位经纬度、查周边山水路(砂水)与地势、定坐向二十四山、排三元九运玄空飞星、八宅游年 → 再参《葬书》 《青囊经》《撼龙经》《雪心赋》等古籍，以形势派(峦头)·理气派(玄空/八宅)·现代建筑学三层解读 → 最后给出「藏风聚气·背山面水·明堂开阔·阴阳平衡·五行调和」的交叉对照表与可执行、非破坏性的改善建议。 Use this skill whenever the user asks about 风水、堪舆、看风水、阳宅、阴宅、选址、坐向、朝向、…
bazi
四柱八字命理分析。通过交互式步骤收集出生信息（姓名、曾用名、阳历/农历生日、时辰、性别、出生地）， 排出四柱八字，参照经典命理典籍（穷通宝典、三命通会、滴天髓、渊海子平、子平真诠等）进行专业分析。 Use this skill whenever the user asks for 八字、四柱、命理、算命、Bazi、fortune telling、 birth chart analysis, or wants to know about their 八字命盘、运势、大运、流年. Triggers: "算八字", "看八字", "批八字", "排八字", "四柱", "命盘", "算命", "帮我看看八字", "我想算八字"…
qiming
新生儿起名/取名：为宝宝取 5 个精选名字备选并给出详细理由。用户提供姓氏（必填）、 性别（必填）、期望寓意方向（必填），可选出生日期时辰、父母姓名、辈分字/家族传统。 流程：交互收集信息 → 有生辰则用脚本排八字五行、判喜用 → 从《诗经》《楚辞》《论语》《周易》、 唐诗宋词、四书道家等古籍素材与取名字库中选字组名 → 按「音韵和谐·避免谐音·书写便利·性别适配· 寓意美好」五大原则用脚本逐项体检 → 有父母姓名则做家族合参/避讳 → 给出 5 个各有侧重的名字及理由。 Use this skill whenever the user wants to name a baby / newborn, pick a Chinese…
zhougong-dream-interpretation
周公解梦 + 阴阳五行 + 天人感应 + 现代心理学 的多层梦境解析技能。当用户描述梦境（做梦、梦见、梦到、解梦、周公解梦、圆梦、周公、dream interpretation）时使用：先按类别检索《周公解梦》原文吉凶断语，再以《周易》阴阳八卦、《尚书·洪范》《白虎通义》《春秋繁露》五行学说与天人感应推演（结合本命纳音五行、做梦当天当地天气；用户若提供近期特殊事件，则做梦事合参/同类相动推演），最后辅以弗洛伊德/荣格/睡眠科学等心理学视角，并给出联合三层的交叉解析，形成「文化参照 +…