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 ace3000chao/book2startup --skill dont-copy-compensationgit clone --depth 1 https://github.com/ace3000chao/book2startupWrote 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/ace3000chao/book2startup/dont-copy-compensation)<a href="https://agentmods.dev/skills/ace3000chao/book2startup/dont-copy-compensation"><img src="https://agentmods.dev/badge/skills/ace3000chao/book2startup/dont-copy-compensation/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/ace3000chao/book2startup/dont-copy-compensation"><img src="https://agentmods.dev/badge/skills/ace3000chao/book2startup/dont-copy-compensation.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 | $0.00159 | $0.03842 |
| Opus 5 | $0.00079 | $0.01921 |
| Sonnet 5 | $0.00032 | $0.00768 |
| Haiku 4.5 | $0.00016 | $0.00384 |
Grade A, and why
dont-copy-compensation 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 9d 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 — 168 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Don't Copy Someone Else's Compensation System(不要复制别人的薪酬体系)
R — 原文 (Reading)
"Don't copy somebody else's compensation system. Look to your Core Values, your business model, and your Brand Promise, and let them instruct you in the design of your compensation plan."
— Verne Harnish, Scaling Up, 第5章
I — 方法论骨架 (Interpretation)
核心原则:薪酬是文化的表达,不是竞争的工具
Scaling Up最反直觉的建议之一:不要去看"市场行情"和"行业标准薪酬报告"来设计你的薪酬体系。Verne Harnish认为,行业标准薪酬报告告诉你的是"别人怎么做",而不是"你应该怎么做"。复制别人的薪酬体系,本质上是用别人的价值观来解决你自己的问题。
为什么薪酬体系必须从内而非从外设计?
薪酬体系是组织行为的控制器。如果你按照外部标准设定薪酬,你就在告诉团队:"你们的行为应该符合行业惯例。"但Scaling Up认为,优秀的组织之所以优秀,是因为他们不按行业惯例行事。
薪酬设计的三个内部北极星(North Stars):
-
Core Values(核心价值观)
- 薪酬必须体现你真正奖励什么。如果"协作"是你的Core Values,但你的薪酬只奖励个人业绩,那你嘴上说的Core Values是假的。
- 例如:Patagonia的Core Values是环保和员工自主,其薪酬特点是"没有差旅预算限制"(信任驱动)和"允许员工随时离开去冲浪"(自主驱动)——这些都由其Core Values推导,而非行业惯例。
-
Business Model(商业模式)
- 商业模式决定了你用什么指标衡量成功,也就决定了什么样的薪酬结构最有效。
- 例如:SaaS公司用ARR(年度经常性收入)衡量成功,薪酬结构应该奖励续约率和客户成功指标;电商公司用GMV,薪酬结构应该奖励转化率和复购率。用错误的指标奖励团队,是薪酬设计的最大陷阱之一。
-
Brand Promise(品牌承诺)
- 你的品牌承诺是什么?如果你的品牌承诺是"最优秀的客户服务",你的薪酬应该大力奖励NPS(客户满意度)和客户留存,而不是只奖励销售额。
- 例如:Zappos以卓越客户服务闻名,其薪酬设计中超过10%的绩效奖金与客户满意度直接挂钩,而不仅仅是销售额。
从这三个内部北极星推导薪酬设计的流程:
Core Values → 什么行为应该被奖励(软性)
Business Model → 什么结果应该被奖励(硬性)
Brand Promise → 什么客户价值应该被奖励(外部感知)
↓
三者结合 → 薪酬结构的权重分配
A1 — 书中的应用 (Past Application)
案例 1: 星巴克的"超越行业标准"薪酬
- 问题: 星巴克在90年代面临的挑战是——零售业服务员的行业平均离职率约为150%(每年替换整个人员池一次半),而星巴克要在店里卖咖啡和浓缩饮料(高度依赖员工培训和门店文化)。
- 方法论的使用: 星巴克没有参考"零售业标准薪酬",而是追问:我们的Core Values是什么?(第三空间、伙伴文化)我们的Business Model是什么?(高顾客复购率、门店体验驱动)我们的Brand Promise是什么?(不是"最便宜的咖啡",而是"第三空间的体验")。从这三个内部北极星,星巴克推导出了当时震惊行业的决策:全职和兼职员工都享受完整的医疗福利和股票期权。
- 结论: 星巴克的薪酬不是"零售业标准",而是"让我们能够兑现品牌承诺的薪酬"。他们用内部北极星而非外部基准来设计。
- 结果: 星巴克的员工流失率在90年代末降至行业平均的一半以下,顾客满意度显著提升,成为服务行业的标杆。
案例 2: 某创业公司的"薪酬倒挂"危机
- 问题: 某A轮创业公司,因为抢人压力大,从市场上招聘了3名高级工程师,薪酬均高于公司老员工30-50%,形成了严重的"薪酬倒挂"。老员工发现后,2个月内4名核心技术骨干提出离职。
- 方法论的使用: CEO开始审视薪酬体系,发现他们的薪酬设计完全是"市场驱动"(看别人给多少我就给多少),完全没有内部逻辑。他重新从Core Values("我们是一个重视信任和透明的家庭型团队")出发,设计了一套新的薪酬调整方案——不是简单的全员涨薪,而是增加了"资历系数"(在公司越久,基本工资中由资历贡献的部分越高)和"文化贡献奖金"(对帮助新人、跨团队协作的行为进行奖励)。
- 结论: 薪酬倒挂的根源是外部驱动(market-based)的薪酬设计,而解决的根本是从内部价值观出发设计薪酬的内在逻辑。
- 结果: 2名提出离职的核心骨干撤回离职申请,薪酬倒挂的心理影响("被不公平对待")通过透明的新薪酬逻辑得到缓解。
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.
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.
- 9d ago First seen · 168 lines · 159 tokens per session scan A 1cffacdbc8cc
dont-copy-compensation is a skill published in the GitHub repository ace3000chao/book2startup (80 stars, last pushed 4mo ago), licensed MIT. It adds 159 tokens to every session and 3,842 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
strategy-generate
Create, modify, and optimize quantitative trading strategies, then backtest and evaluate them.
bottleneck-hunter
Supply-chain bottleneck arbitrage. Given a super-trend (AI infra, energy transition, defense, semiconductor reshoring, space economy), decompose its physical supply chain down to Layer 2/3 choke points (optics, lasers, InP/SOI substrates, IC substrates, probe cards, specialty fiberglass...) and surface under-the-radar…
execution-model
Trade execution modeling (backtest only) — slippage formulas (linear / square-root impact), VWAP/TWAP execution logic, market-impact cost estimation, and execution-assumption configuration.
ml-strategy
Machine-learning predictive strategy based on sklearn walk-forward training, feature engineering, and signal generation. Suitable for any OHLCV data.
event-driven
Event-driven strategy based on sentiment-scored signals from news, announcements, and macro events. The LLM acts as the NLP engine, and event data follows a CSV schema.
thesis-tracker
Buy-side discipline system. For each holding, maintain a written investment thesis — core thesis in 5 sentences, falsifiable assumptions, red lines, valuation anchors — and re-check it each quarter against new earnings/events. Scores thesis health 1-10 from assumption breakage and red-line triggers, and recommends…