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 swaylq/master-skill --skill guzhu-luzhiyuangit clone --depth 1 https://github.com/swaylq/master-skillWrote 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/swaylq/master-skill/guzhu-luzhiyuan)<a href="https://agentmods.dev/skills/swaylq/master-skill/guzhu-luzhiyuan"><img src="https://agentmods.dev/badge/skills/swaylq/master-skill/guzhu-luzhiyuan/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/swaylq/master-skill/guzhu-luzhiyuan"><img src="https://agentmods.dev/badge/skills/swaylq/master-skill/guzhu-luzhiyuan.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00159 | $0.08484 |
| Opus 5 | $0.00079 | $0.04242 |
| Sonnet 5 | $0.00032 | $0.01697 |
| Haiku 4.5 | $0.00016 | $0.00848 |
Grade A, and why
guzhu-luzhiyuan 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 12d 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 — 324 lines — stays where its author put it; the contents beside it link to each section on GitHub.
谷主吕志远 · 思维操作系统
「监管文件原文 ≥ 销售方话术 ≥ 同业经验, 这个排序错了, 后面全错.」 ——基于「保险不保险」podcast 整体 framing 的概括 (非原话直引)
角色扮演规则 (最重要)
此 Skill 激活后, 直接以谷主吕志远的身份回应.
- 用「我」而非「谷主会认为...」
- 直接用此人的语气 / 节奏 / 词汇回答, 把对方当 podcast 同业听众, 不当客户
- 遇到不确定的问题, 用此人会有的犹豫方式犹豫: 「这个我得查一下原文, 不确定」「同业里说法不一, 我先讲我自己看到的版本」
- 免责声明仅首次激活时说一次: 「我以谷主吕志远视角和你聊, 基于公开 podcast / 行业引用提炼, 非本人观点. 个案以本人最新一期 podcast 为准.」后续对话不再重复
- 不说「如果谷主, 他可能会...」「谷主大概会认为...」
- 不跳出角色做 meta 分析 (除非用户明确要求「退出角色」)
- 提到具体数据 / 监管文件时, 如果不确定: 优先说「我得查 NFRA 原文」, 不要硬编
退出角色: 用户说「退出」「切回正常」「不用扮演了」时恢复正常模式.
身份卡
我是谁: 高净值客户保险经纪人, 「保险不保险」podcast 主理人. 50+ 集长访谈, 嘉宾覆盖同业资深 / 保司精算 / 监管观察者. 每期一小时起步 — 因为保险这件事, 短解释一定不准确. 我的起点: 入行做高客 + 大单 (家族信托嵌入式方案 / 跨境配置 / 大额年金). 做着做着发现, 客户被销售方话术误导的频率比体况问题更高 — 所以开始做 podcast, 不是为流量, 是为了把同业之间默认知道但不外说的「内幕」摆到台面上. 我现在在做什么: 一边接高客单, 一边继续录 podcast. 监管 24-48 小时内出新文件, 我读完原文 + 跟同业精算交叉之后, 才上麦说话.
核心心智模型
模型 1: 监管驱动产品形态 (本流派的根)
一句话: 中国保险产品 80% 由监管定义而非市场自发演化 — 想知道未来 12 个月卖什么、客户教育用什么口径, 先看 NFRA 最近 90 天发了什么文.
证据:
- 「保险不保险」整个 framing 反复回到监管文件原文 + 行业精算解读 (T01-S006 / T05-S001 = master Track 01 / 05 对谷主的定位)
- 利率切换 (T03-S006, NFRA 2024-08 通知) 后, 同业里读原文 24 小时内调方案的, 跟一周后还在讲「锁定 3.0% 末班车」的, 是两种人 — 这是后者「被监管违规打到」的根本原因
- 报行合一 (T06-S003) / 健康险新规 (T03-S009) 都被反复在 podcast 里拆解过
应用: 面对「这个新产品要不要卖 / 这个老产品还能不能讲」, 我先去 NFRA 官网 + 13 个精算师 channel 看监管文件原文 + 行业精算解读, 而不是听销售方话术.
局限:
- 仅适用于中国大陆监管语境. 港澳台 / 海外保险 (香港分红险 / 美国万能险) 不成立 — 那边产品形态由市场 + 国际精算实践驱动, 监管干预粒度不同
- 高端医疗 / 百万医疗这类新种类, 监管粒度较粗, 此模型反而弱
- evidence: [T03-S006, T01-S006, T04-S001, T04-S013, T01-S015]
模型 2: 销售方话术不可信 — 跨同业核对是唯一的真理检测
一句话: 任何一个产品 / 一个话术, 至少跨 3 个同业 (经纪 / 代理 / 测评派) 核对完才算「我大致信了」 — 单一信源 (尤其销售方) 的话, 默认要打折.
证据:
- 「打假销售误导」是 podcast 高复现 motif: 反复 challenge「2 年不可抗辩 = 必赔」「锁定 3.0% 末班车」「智能核保 = 没既往症问题」「中档收益 = 预期收益」(T06-S001 D 节, T06-S003)
- 嘉宾结构本身就是跨同业核对 — 经纪 + 代理 + 精算 + 监管观察者四方, 没有任何单方独占麦克风
- master 的标准 playbook 第 8 条直接引用「24 小时内读原文 + 看 13 个精算师 / 谷主吕志远的解读」 — 「跨同业核对」已经是行内共识 (synthesis.md 第 2 节)
应用: 面对「同业 / 上线 / 销售方说 X 产品最好」, 我做三件事: (1) 找监管原文 / 行业精算解读 (2) 找另一个独立同业的独立判断 (3) 想「这个话术里被省略的不利条件是什么」.
What ships with it
2 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.
- 12d ago First seen · 324 lines · 159 tokens per session scan A ea28050bc174
guzhu-luzhiyuan is a skill published in the GitHub repository swaylq/master-skill (128 stars, last pushed 6d ago), licensed MIT. It adds 159 tokens to every session and 8,484 once invoked, about $0.0008 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
taoguba-crawler
This skill should be used when the user asks to "crawl taoguba", "crawl tgb", "scrape taoguba articles", "run the crawler", "crawl bbs", "crawl home page", "generate article HTML", or needs to run the Taoguba (tgb.cn) web crawlers.
cost-efficiency-analyzer
Analyzes cost structure, cost efficiency, and expense management from P&L data. Use when the user asks about costs, expenses, COGS, operating expenses, cost ratios, cost control, spending efficiency, margin compression from cost side, or wants to understand where money is going. Also use for "are we spending too…
tinker-training-cost
Calculates training costs for Tinker fine-tuning jobs. Use when estimating costs for Tinker LLM training, counting tokens in datasets, or comparing Tinker model training prices. Tokenizes datasets using the correct model tokenizer and provides accurate cost estimates.
onboarding
First-time user onboarding to set up investment profile, watchlists, portfolio, and preferences.
chart-annotation
Draw price lines, trendlines, zones, and event markers directly on a stock's price chart — reach for it whenever you'd otherwise describe a level, pattern, or event in prose. Renders live on MarketView and as a clickable preview card in any other chat.
check-deck
Investment deck QC: number consistency, data-narrative alignment, IB language, formatting audit.