concentrated-investing

concentrated-investing is a skill for Claude Code, Codex from kangarooking/duan-yongping-skill. It costs 194 tokens per session (2,937 once invoked), scanned A, original, MIT.

An investing framework about putting a larger share of money into a small number of companies you understand well. It distinguishes concentrated investing from broad diversification used for general wealth management.

In plain words
What is it for?
Thinking through whether to concentrate or diversify a portfolio, how many companies to hold, and how understanding should affect position size.
Why use it?
It provides a way to think about position size based on understanding of a company rather than simply spreading money across many holdings.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Thinking through whether to concentrate or diversify a portfolio, how many companies to hold, and how understanding should affect position size.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/kangarooking/duan-yongping-skill/concentrated-investing
Install

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.

Any agent
npx skills add kangarooking/duan-yongping-skill --skill concentrated-investing
Clone the repo
git clone --depth 1 https://github.com/kangarooking/duan-yongping-skill

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for concentrated-investing

README.md
[![agentmods](https://agentmods.dev/badge/skills/kangarooking/duan-yongping-skill/concentrated-investing/github.svg)](https://agentmods.dev/skills/kangarooking/duan-yongping-skill/concentrated-investing)
Your own site
<a href="https://agentmods.dev/skills/kangarooking/duan-yongping-skill/concentrated-investing"><img src="https://agentmods.dev/badge/skills/kangarooking/duan-yongping-skill/concentrated-investing/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.

agentmods 80×15 button for concentrated-investing

Your own site · 80×15
<a href="https://agentmods.dev/skills/kangarooking/duan-yongping-skill/concentrated-investing"><img src="https://agentmods.dev/badge/skills/kangarooking/duan-yongping-skill/concentrated-investing.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 194 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,937 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00194 $0.02937
Opus 5 $0.00097 $0.01469
Sonnet 5 $0.00039 $0.00587
Haiku 4.5 $0.00019 $0.00294

Measured 12d ago against content hash 51ad0ac16057, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

concentrated-investing 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.

investment-logic/concentrated-investing/SKILL.md · 137 lines

How it starts

The opening of the file, as written. The whole thing — 137 lines — stays where its author put it; the contents beside it link to each section on GitHub.

集中投资框架

R — 原文 (Reading)

我从头到尾真正投资过的公司最多五六家,卖掉了一些,我持有的公司一般在三家左右。巴菲特的哈撒韦一千多亿美元市值,也才投十来家。我不怕集中,我不是一般的集中,我是绝对的集中。

投资多元化是个伪命题。所谓投资多元化指的是理财,它和投资是两种不同的游戏。……既然你认为他最好你只投了一小部分,然后把剩下的钱投到你认为不够好的公司里头,这逻辑上就是错的。

— 段永平,第三章第4节「分散还是集中」/ 《会见财经界》专访


I — 方法论骨架 (Interpretation)

集中投资的底层逻辑是一个简单推导:如果你真正看懂了一家公司(在能力圈内),你应该把钱投到最好的机会上;如果你同时持有很多只股票,说明你对每只都不够懂。

  1. 分散 = 对无知的保护:如果你需要买10只股票来分散风险,恰恰说明你对每只都不够了解。真正的理解带来的是确定性,而不是分散需求。
  2. 仓位反映理解度:一只股票的仓位比例应该由你的理解深度决定,而不是由"风险管理"公式决定。"一般的比例是0%-100%,取决于你自己懂多少"。
  3. 投的企业越多赚的越少:超出能力圈范围的持股,每增加一只都在稀释你对每只的注意力,增加犯错概率。
  4. 一辈子20个决策:如果一生只能投资20次(打孔卡片比喻),你会极其慎重地对待每一次出手。少决策、决策重。
  5. 集中是简单但非常难的事:难的不是集中本身,而是"真正看懂一家公司"这件事本身就极难。了解一只股票都很难,十只几乎是"mission impossible"。
  6. 钱少尤其要focus:资金量小的时候更没有资本分散,应该集中到最好的2-3个机会上。
  7. 分散叫理财不叫投资:撒胡椒面式的分散是理财(跟上大盘),不是投资(找到好公司重仓)。

A1 — 书中的应用 (Past Application)

案例 1: 段永平的极端集中持仓

  • 问题: 段永平如何管理自己的投资组合?
  • 方法论的使用: 他从始至终只真正投资过最多五六家公司,持有的公司一般在三家左右(苹果、茅台为核心)。买网易时把当时能动用的钱全部投进去。苹果仓位逐步加到60-70%。
  • 结论: "好容易找到一个好价格的好股票,不集中是不明白的表现。"
  • 结果: 网易约100倍回报,苹果和茅台均为长期重仓大牛股。芒格评价伯克希尔"除去10个投资就是个笑话"——57年历史,集中投资的收益几乎全部来自少数几个决策。

案例 2: 卡片打孔与决策频率

  • 问题: 投资者应该以什么频率做出投资决策?
  • 方法论的使用: 段永平引用巴菲特的打孔卡片比喻——一张只有20个孔的卡片,每次投资打一个孔,一生只有20次机会。他自己反省"大道这4年里只真正出手了一次,就是苹果,上一次出手是GE",平均约两年一家。在10年里大致看懂了不到10家企业,重手投了5家。
  • 结论: "看准了出手就要狠。似懂非懂很难下手狠。"
  • 结果: 极少的出手次数带来极高的单次决策质量和回报集中度。

A2 — 触发场景 (Future Trigger) ★

用户会在什么情境下需要这个 skill?

  1. 构建投资组合时犹豫持仓数量 — 用户有了一笔资金,正在纠结"买几只股票合适",是分散到8-10只还是集中到2-3只
  2. 已有持仓但仓位过轻想加仓时犹豫 — 用户看好某只股票但只敢放5%-10%仓位,想"平衡一下风险",在问仓位该怎么定
  3. 手中持股过多、精力分散导致每只都研究不深 — 用户持有10只以上股票,发现自己对每只都是"似懂非懂",频繁焦虑,想精简组合

语言信号 (用户的话里出现这些就应激活)

  • "我买了10只股票分散风险" / "要不要多买几只平衡一下"
  • "这只股票我只敢放5%仓位" / "不敢买太多比例"
  • "投的企业越多赚的越少是怎么回事" / "为什么我持股越多反而越焦虑"

与相邻 skill 的区分

  • circle-of-competence (能力圈决策框架) 的区别: 能力圈解决"这只股票我懂不懂",本skill解决"懂了以后应该投多少钱"。能力圈是前提,集中投资是能力圈的仓位推论。
  • opportunity-cost (机会成本决策框架) 的区别: 机会成本解决"持有A还是换B"的比较问题,本skill解决"总共应该持几只"的数量问题。但两者在逻辑上互联——集中投资的理由之一是机会成本:每一块钱都应该投到最好的机会上。

Read the full file on GitHub · 137 lines

Files

What ships with it

1 file 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.

Changes

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.

  1. 12d ago First seen · 137 lines · 194 tokens per session scan A 51ad0ac16057

Subscribe to this mod's changes

concentrated-investing is a skill published in the GitHub repository kangarooking/duan-yongping-skill (48 stars, last pushed 4mo ago), licensed MIT. It adds 194 tokens to every session and 2,937 once invoked, about $0.0010 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.

Related

Other skills, from other repositories