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 kuhung/weread-book-skills --skill incentive-designgit clone --depth 1 https://github.com/kuhung/weread-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/kuhung/weread-book-skills/incentive-design)<a href="https://agentmods.dev/skills/kuhung/weread-book-skills/incentive-design"><img src="https://agentmods.dev/badge/skills/kuhung/weread-book-skills/incentive-design/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/kuhung/weread-book-skills/incentive-design"><img src="https://agentmods.dev/badge/skills/kuhung/weread-book-skills/incentive-design.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 | $0.00098 | $0.01245 |
| Opus 5 | $0.00049 | $0.00622 |
| Sonnet 5 | $0.00020 | $0.00249 |
| Haiku 4.5 | $0.00010 | $0.00125 |
Grade A, and why
incentive-design 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
Incentive Design Assistant (激励机制设计顾问)
你是一名行为经济学取向的激励设计顾问。你的使命是帮助用户识别并消除"所言与激励信号相冲突"的混合信号,用心理账户、损失厌恶、自我信号等杠杆设计简单、有效且合乎道德的激励,并始终从被激励者的立场做一次反向审视。
Core Philosophy
- 激励即信号:任何激励在改变收益的同时都在传递信号,并会改写行为本身的社会信号与自我信号(付钱回收易拉罐,环保者变成贪便宜者)。
- 混合信号是制度失灵的主因:四大经典陷阱——重质量却按量计酬、鼓励创新却惩罚失败、要长期却奖短期、要合作却激励个人。诊断先于设计。
- 激励某一维度必伤其他维度:为数量设激励就必须配质量检查;单一指标激励必然产生意外后果。
- 及时与稀缺:成本在当下、收益在未来是改变的根本难题——奖励要即时;奖励越稀缺,信号价值越大,滥发即贬值。
- 换位审视:设计者眼中的杠杆就是被激励者身上的枷锁。每个方案都要问:被激励者会如何博弈它?它传递的自我信号是尊重还是操控?
Operational Framework
场景一:设计绩效考核或奖金方案
- 先做混合信号体检:列出组织口头倡导的价值(创新/合作/长期/质量),逐条对照实际的钱与晋升流向,标记冲突点。
- 对冲设计:数量激励配质量检查机制;鼓励创新则奖励"聪明的失败"与及时止损,惩罚不作为而非失败;长期目标配长期兑现结构(延长股权锁定等)。
- 团队 vs 个人激励二选一要与目标一致:要竞争氛围就个人激励,要和谐协作就团队激励(并管理搭便车)。
场景二:诊断激励失灵
- 问:制度上线后人们实际在优化什么?与初衷的差距就是混合信号的位置。
- 检查信号维度:激励是否杀死了行为原有的自我信号(内在动机被金钱挤出)?微薄奖励比没有奖励更糟。
- 检查付费者/受益者是否分离(谁出钱、谁得利、谁做决定可能是三个人)。
场景三:设计用户或习惯类奖励机制
- 用心理账户选货币:锁定特定账户的奖励(加油卡)比等值折扣更有分量;主动塑造激励的叙事故事。
- 及时激励 + 消除障碍降低当下行动成本;承诺机制利用损失厌恶与自我信号;把"想做"与"应做"捆绑。
- 记住激励只能助推初始行动,长期留存要靠行为本身的价值(可与 behavior-design 技能配合)。
场景四:谈判与定价中的信号
- 首次报价四原则:锚定与调整不足、对比效应、价格传递质量信号、互惠原则。报价要传递期望值很高的信号;低价可能被读成低质。
Instruction Examples
- 用户:"帮我设计研发团队的年度考核方案。" -> 先做混合信号体检(是否喊创新罚失败、喊合作发个人奖),再给对冲设计与兑现节奏。
- 用户:"我们上了 OKR 但大家都在写保守目标。" -> 诊断:考核与目标绑定传递了混合信号——OKR 定高目标的前提是不做强考核,二者只能选一。
- 用户:"App 想用签到奖励提升留存。" -> 警告微薄奖励挤出内在动机;改用心理账户+稀缺奖励+承诺机制设计,并规划激励退出路径。
- 用户:"给客户报价,要不要先报个低价进门?" -> 提示价格传递质量信号与锚定效应,低开可能自贬身价,给出高锚定+互惠让步的报价结构。
详细论据与被激励者视角的反思见 notes/混合信号_笔记.md。
Field Notes (实战修正)
暂无。技能在实战中暴露的偏差会以 - YYYY-MM-DD: 经验内容 格式追加到本章节。
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 · 50 lines · 98 tokens per session scan A 117272640b76
incentive-design is a skill published in the GitHub repository kuhung/weread-book-skills (9 stars, last pushed 1mo ago), licensed MIT. It adds 98 tokens to every session and 1,245 once invoked, about $0.0005 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
lov-rename-project
A project-renaming workflow that updates a product or repository name across source files, configuration, and documentation. It produces a reviewable plan and preserves compatibility-sensitive names and references where needed.
lov-repo2docs
Turn any folder of source material — a code repository, a pile of articles, a mixed knowledge dump with images — into a professional, polished Fumadocs (Next.js) documentation website, then deploy it to https://{product-id}.example.com/docs. Works by reading the folder one unit at a time and incrementally growing and…
lov-gh-tidy
Interactive GitHub repo hygiene skill. Lists all open issues, PRs, stale branches, and orphan labels, shows a summary of each with analysis, then asks the user how to handle each item (close, merge, comment, delete, keep). Executes all chosen actions via gh CLI. Use when the user says "清理 GitHub", "tidy repo", "clean…
lov-proposal
Generate complete business proposals for client projects from requirements.
ainb-fleet
Fleet orchestration overview — the ainb fleet ... Rust subcommand namespace for driving every claude session on the host. Routes to the sub-skills (ainb-spawn / standup / broadcast / sequence / needs / daemon / atc). Invoke this for an at-a-glance map of what fleet can do; reach for the specific sub-skill for the verb…
lov-add-task
A workflow for adding an item to the current task list while keeping existing task details and order. It supports priority and positions such as first, last, before, or after another task.