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 R2h1/my-book-skills --skill v18-vsgit clone --depth 1 https://github.com/R2h1/my-book-skillsWrote 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/r2h1/my-book-skills/v18-vs)<a href="https://agentmods.dev/skills/r2h1/my-book-skills/v18-vs"><img src="https://agentmods.dev/badge/skills/r2h1/my-book-skills/v18-vs/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/r2h1/my-book-skills/v18-vs"><img src="https://agentmods.dev/badge/skills/r2h1/my-book-skills/v18-vs.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00114 | $0.01357 |
| Opus 5 | $0.00057 | $0.00678 |
| Sonnet 5 | $0.00023 | $0.00271 |
| Haiku 4.5 | $0.00011 | $0.00136 |
Grade A, and why
v18-新闻vs投资信息 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.
What it actually says
新闻 vs 投资信息：看比率不看总数
R — 原文 (Reading)
我关注的不是感染总数，而是感染比例。以感染比例为标准，当最高峰值过去之后，新冠肺炎疫情得到了控制。……人人清楚事实，但事实所指向的未来并不是每个人都能了解的。
— 金胜镐, 《通过新闻区分事实和投资信息的方法》
I — 方法论骨架 (Interpretation)
新闻擅长用"总量"制造情绪（恐惧/狂热），而判断趋势要用"比率/边际"。把"事实"与"投资信息"分开：
- 总量 vs 比率：感染人数创新高（总量）≠ 疫情恶化——要看"当天比前一天的增长率"（比率/边际）。作者在2020年3月恐惧最高峰买入，依据正是"感染比例在下降"。
- 消极报道自带偏见：美媒经济报道60%消极、韩媒80%消极——消极信息更吸睛，发挥监督功能，但也容易夸大；标题的论调不等于事实。
- 经济报道常被歪曲成政治报道：同一情况既可能被写成"惨淡"也可能写成"历史最低"；要把自己的政治理念与经济判断分开。
- 投资决策的落点：恐慌（或狂热）时，用数据/比率/内在价值（v14）判断，而不是被情绪标题裹挟。
A1 — 书中的应用
- 2020年疫情案例：作者在道琼斯暴跌、专家高喊"V/L/U/W形"、"巴菲特都割肉了"的恐惧中买入——他看的是各国"感染比例"的边际下降，而非感染总数。
- 作者指出：2020年3月媒体"大肆煽动恐惧"，恐慌滋生恐慌、几乎所有人抛售——这是"看总数被情绪绑架"的典型。
- 作者批评韩国媒体在1997年亚洲金融危机时"杜绝助长经济危机感"的社论——"这类报道统统不是经济报道，而是政治报道"。
A2 — 触发场景 ★
场景：你被新闻标题（暴跌/失业/恐慌/暴涨）刺激想操作时；你想判断一条经济数据的真实含义时；你发现同一事件有矛盾报道时；你想养成"看数据不看情绪"的习惯时。
语言信号：
- "新闻说经济崩了，我要不要清仓？"
- "这个失业率数据可怕吗？"
- "同一件事怎么两种说法？"
- "怎么判断一条新闻可不可信？"
相邻区分：与"风险与恐惧的逆向"（v09）配合——v18 是"如何读信息"，v09 是"读完后如何应对恐惧/贪婪"；与"独立判断"（v17）配合——v17 处理"专家意见"，本 skill 处理"媒体报道与数据"。
E — 执行步骤
-
把标题翻译成数据：看到情绪化标题（"崩了/完了/暴涨"），先找背后的原始数据，问"是总量还是比率？是绝对值还是边际变化？"
-
计算比率/边际：对关键数据（感染、失业、销量、价格），算出"相对前期的增速/占比"，用比率而非总数判断趋势。
-
多源核对 + 分离政治：读至少两家不同论调的媒体，注意区分"事实报道"与"政治化解读"；把个人政治立场与投资判断隔离。
-
情绪冷静再决策：若标题让你有强烈的"必须马上操作"的冲动（恐惧或贪婪），先暂停24小时，用 v14 的价值判断 + v09 的逆向框架再决定。
B — 边界 ★
- "看比率"是补充不是取代：总量本身有时也重要（如绝对需求、市场规模）；关键是"看清分子分母"，不机械套用。
- 数据也可能被操纵/滞后（v17 怀疑精神）；比率下降也可能只是统计口径问题。
- 不要为了"反情绪"而逆着合理事实操作：逆向要有价值依据（v09），不是为反而反。
- 本 skill 不提供具体宏观判断，只提供"如何读信息"的方法。
审计信息
V1 ✓ / V2 ✓ / V3 ✓
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 · 66 lines · 114 tokens per session scan A ac26806df990
v18-新闻vs投资信息 is a skill published in the GitHub repository R2h1/my-book-skills (2 stars, last pushed 27d ago), licensed MIT. It adds 114 tokens to every session and 1,357 once invoked, about $0.0006 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
bookkeeping-cn
A Chinese-language bookkeeping assistant that turns transaction records into organized income, spending, budgets, and reconciliation reports. Reconciliation means comparing records to find differences.
wps-budget
A spreadsheet generator for planning and tracking budgets, with categories, subtotals, totals, and comparison calculations. It supports department, project, event, household, and marketing budgets.
wps-salary
A Chinese payroll calculator and salary-slip generator. It calculates employee deductions for social insurance, housing funds, and personal income tax, then creates Excel salary slips.
wps-financial-report
A financial statement generator for the three standard company reports: the balance sheet, income statement, and cash flow statement.
rory-odriscoll
Rory O'Driscoll — Partner at Scale Venture Partners; recurring 20VC co-host. Triggers: enterpriseSaaS, growthinvesting, publicmarkets, SaaSeconomics.
dangjr
Dan G Jr — Venture capital theory & early-stage investing. Triggers: venturecapital, earlystageinvesting, fundeconomics, vcdiversification, dealflow, startupcapitalefficiency.