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 Haochenhust/ch-skills --skill intrinsic-value-analysisgit clone --depth 1 https://github.com/Haochenhust/ch-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/haochenhust/ch-skills/intrinsic-value-analysis)<a href="https://agentmods.dev/skills/haochenhust/ch-skills/intrinsic-value-analysis"><img src="https://agentmods.dev/badge/skills/haochenhust/ch-skills/intrinsic-value-analysis/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/haochenhust/ch-skills/intrinsic-value-analysis"><img src="https://agentmods.dev/badge/skills/haochenhust/ch-skills/intrinsic-value-analysis.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 | $0.00128 | $0.06131 |
| Opus 5.5 | $0.00051 | $0.02452 |
| Sonnet 5.5 | $0.00026 | $0.01226 |
| Haiku 4.5 | $0.00013 | $0.00613 |
Grade A, and why
intrinsic-value-analysis 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 2mo 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 — 310 lines — stays where its author put it; the contents beside it link to each section on GitHub.
如何分析一家企业的内在价值(老唐估值法)
何时使用
当你需要回答以下任一问题时,按本 skill 的流程走:
- 这家公司值多少钱?内在价值大概是多少?
- 现在的股价能买吗?什么价位算便宜?什么价位该卖?
- 帮我用价值投资的方法研究/估值某家公司。
重要前置判断:本方法只适用于符合三大前提的优质企业。银行、保险、地产、券商、航运、强周期、高资本开支、利润含金量低或有造假嫌疑的企业,不能硬套本公式。遇到这类企业,要么走"特殊企业变体",要么诚实地说"这家不在老唐估值法的能力范围内"。
核心理念(先理解,再动手)
1. 内在价值 = 企业未来全部自由现金流的折现值。 这是逻辑上唯一正确的估值法(DCF),但不可精算。
"自由现金流折现法是唯一能在逻辑上说得通的估值方法……一家企业值多少钱,要看从现在到它消失的全部时间段里,我能从中拿回多少钱,这些未来可以拿到的钱折合现在的钱是多少。"(老唐,2016)
2. DCF 是思维方式,不是计算公式。 不要去拉 Excel 做五阶段折现表。
"DCF是个思维模式,不是一个计算方法。如果用它去做计算,不管用哪个数据,得到的都是精确的错误。"(老唐,2022)
3. 把符合三大前提的好公司当成一份债券。 自由现金流是票息,无风险收益率决定它值多少钱。
"对于符合三大前提的企业,当年利润×25~30,是其当年的合理估值,其实也就是相当于将其直接视为一份债券。"(老唐,2021)
4. 模糊的正确,好过精确的错误。 先求方向(成长还是衰退)正确,再求数据接近。
"首先求方向的正确,其次求数据的接近。即便退而求其次,数量差异不是很大,得到模糊的正确亦可。"(老唐,2018)
5. 估值本质是"两种资产的比较",而不是预测股价。 合理估值只是一个"锚",用来跟等值现金比较,看持有哪个更划算。
"合理估值从来不是预测企业市值或股价会涨到这个数字去,它只是自己用来和等值现金做比较,比较持有哪个对我自己更划算的一个锚。"(老唐,2023)
第 0 步:圈定能力圈(只估你能看懂的)
估值的第一道闸门不是公式,而是"你看不看得懂这家企业"。A股 3500+ 家公司,真正敢下估值结论的最多几十家。
判断标准——你能否清楚回答这四个问题(看不懂就停,直接放弃):
- 它靠卖什么商品/服务获利?
- 客户为什么选它而不选别家?
- 同样逐利的资本,为什么没有抢走它的利润 / 压低它的利润率?
- 同行或巨头挟巨资进来竞争,它能否保住甚至扩张份额?
"有一尺高的栏,就别想着见栏就跳,这是所谓能力圈的核心要点。"(老唐,2016)
只有四个问题都能踏实回答,才进入下一步。 答不出来不代表公司不好,只代表它不在你的能力圈里。
第 1 步:三大前提排雷(不过关就不适用本方法)
这是整套方法的"排雷门槛"。不符合三大前提的企业,本简化估值法不适用——这是硬约束,不是建议。
"25倍的前提是企业必须符合三大前提:利润为真;利润可持续;维持当前盈利能力所需新增资本投入很少甚至无需新增资本投入。"(老唐,2020)
Checklist
-
前提一:利润为真 —— 赚的是真金白银,不是应收账款的欠条、关联交易或非主营偶然所得。
- 判断方法:看经营活动现金流净额是否长期≈或≥净利润;看应收账款占比与增速是否异常;多年持续真金白银分红本身就是利润为真的佐证。
-
"持续拿出真金白银来分红的行为本身,能够起到证明公司利润为真的作用。"(老唐,2016)
-
前提二:利润可持续 —— 未来利润能大体维持,至少能比当年高一点点;靠护城河支撑,不是昙花一现。
- 判断方法:能否大体预测三年后的利润水平?盈利的来源是否有核心竞争力(护城河)撑着?强周期、靠单一政策/补贴、技术易被颠覆的,判否。
-
"(利润可持续)至少能超过当年利润一点点。"(老唐,2021)
-
前提三:维持当前盈利能力不需要大量资本投入 —— 每年的折旧摊销足以维持现有盈利,赚到的钱大部分能分给股东而不伤元气。
- 判断方法:长期看资本性支出(购建固定资产/无形资产现金流出)是否长期≤折旧摊销。若公司必须不断砸钱才能维持现有产能/利润("吞金兽"),判否;像茅台这种"不需要投入更多资本就能成长的印钞机",判是。
-
"维持当前盈利能力不需要大量资本投入,可理解为每年的折旧摊销足够满足维持当前盈利能力所需的资本投入。"(老唐,2022)
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.
- 2mo ago First seen · 310 lines · 128 tokens per session scan A 42c053aca1f3
intrinsic-value-analysis is a skill published in the GitHub repository Haochenhust/ch-skills (9 stars, last pushed 3mo ago), licensed MIT. It adds 128 tokens to every session and 6,131 once invoked, about $0.0005 per session on Opus 5.5. 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.
intrinsic-value-analysis compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| intrinsic-value-analysisHaochenhust/ch-skills | Skill | 9 | 3mo ago | MIT | A | 128 | Claude Code, Codex |
| rugpull-detectorDjordjeMojsilovic/Djordjes-Claude-Setup | Skill | 4 | 3mo ago | none | A | 205 | Claude Code, Codex |
| ma-playbookalirezarezvani/claude-skills | Skill | 29k | yesterday | MIT | A | 29 | Claude Code |
| fiscalisteromainsimon/paperasse | Skill | 2.6k | yesterday | MIT | A | 320 | Claude Code, Codex |
| comptableromainsimon/paperasse | Skill | 2.6k | yesterday | MIT | A | 153 | Claude Code, Codex |
| syndicromainsimon/paperasse | Skill | 2.6k | yesterday | MIT | A | 204 | Claude Code, Codex |
| prompt-masternidhinjs/prompt-master | Skill | 16k | 15d ago | MIT | B | 78 | Claude Code, Codex |