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 f09git 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/f09)<a href="https://agentmods.dev/skills/ace3000chao/book2startup/f09"><img src="https://agentmods.dev/badge/skills/ace3000chao/book2startup/f09/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/f09"><img src="https://agentmods.dev/badge/skills/ace3000chao/book2startup/f09.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 | $0.00125 | $0.02545 |
| Opus 5 | $0.00063 | $0.01273 |
| Sonnet 5 | $0.00025 | $0.00509 |
| Haiku 4.5 | $0.00013 | $0.00254 |
Grade A, and why
f09 tianli-renyu 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 — 139 lines — stays where its author put it; the contents beside it link to each section on GitHub.
天理人欲分判框架
R — 原文 (Reading)
"天理路上甚宽,稍游心,胸中便觉广大宏朗;人欲路上甚窄,才寄迹,眼前俱是荆棘泥涂。"
— 洪应明, 菜根谭·正义路广 欲情道狭
I — 方法论骨架 (Interpretation)
决策时问一句:这条路是"天理路"还是"人欲路"?
这个框架提供了一个方向性的判断工具:当你面对一个利益选择时,问自己"这是天理还是人欲"——天理是公利(对多数人有益),人欲是私利(只对我个人有利但可能损害他人或长期利益)。
两条路的特征:
- 天理路:走起来越走越宽("广大宏朗"),方向是开放的、坦荡的,你的选择不会让自己越走越窄。
- 人欲路:走起来越走越窄("荆棘泥涂"),每走一步都在缩小自己的选择空间,最终无路可走。
方法论本质:
- 当你面临选择时,先问"走这条路,我的选择空间会变大还是变小?"
- 如果这条路短期对我有利但长期会让我的选择空间变小,这是"人欲路"——即使短期有利,也要警惕。
- 如果这条路短期对我不利但长期会让我的选择空间变大,这是"天理路"——即使短期吃亏,也值得走。
一句话总结: 看一条路宽不宽,不是看它现在给你什么,而是看它未来让你能做什么。
A1 — 书中的应用 (Past Application)
案例 1: 秦桧和珅的"人欲路"
- 问题: 秦桧依附权势、卖国求荣,和珅贪腐弄权、聚敛财富——他们都是在短期利益(权力、金钱)上选择"人欲路"。
- 方法论的使用: 他们在做选择时,只看眼前的利益,没有问"走这条路,我的选择空间会越来越大还是越来越小?"。他们的权力越增越大,但每一步都在缩小自己的退路——最终身首异处,无路可走。
- 结论: "人欲路"短期甜、长期苦,每一步都在给自己挖坑。
- 结果: 秦桧跪像至今被人唾弃,和珅被嘉庆赐死。走人欲路的人,即使生前荣华,最终都是"荆棘泥涂",无路可退。
案例 2: 苏武、岳飞的"天理路"
- 问题: 苏武被扣押在匈奴19年坚贞不屈,岳飞精忠报国最终被冤杀——他们都是放弃了短期利益(投降、妥协可能获得更高地位),选择了"天理路"。
- 方法论的使用: 他们在做选择时,问的不是"这条路给我什么",而是"这条路让我成为什么样的人"。苏武选择坚守气节,岳飞选择精忠报国——他们的选择让自己的路越走越宽,最终成为千古楷模。
- 结论: "天理路"短期苦、长期宽,走这条路的人在当时可能"寂寞",但最终"天地尽属逍遥"。
- 结果: 苏武、岳飞千古流芳,他们的坚守成为后人效仿的榜样——走天理路的人,最终拥有的是"广大宏朗"的精神空间。
A2 — 触发场景 (Future Trigger) ★
用户会在什么情境下需要这个 skill?
- 面临利益选择时:在商业机会、人际关系、职业选择中遇到一个可能带来好处但涉及道德风险的选择,用户想确认"这条路该不该走"。
- 在诱惑面前犹豫:有一个看似很好的机会(快速获利、轻松赚钱、捷径),用户不确定是否应该接受。
- 做重大决策前的方向确认:用户面临一个需要付出较大代价的决定(投入时间、金钱、声誉),想确认自己选择的"大方向"是否正确。
- 评估"我现在走的路对不对":用户已经走在一条路上,但开始怀疑这条路的长期方向,想通过"天理/人欲"的框架来检验。
- 面对"灰色地带"的决策:有一个选择看起来不是非黑即白,用户想找一个原则来判断这个选择的性质。
语言信号 (用户的话里出现这些就应激活)
- "我不知道这样做对不对"
- "这个决定有没有问题"
- "这条路能不能走"
- "我面临一个选择,不知道该选哪个"
- "有一个机会看起来很好,但总觉得哪里不对"
- "我想确认我的方向是否正确"
- "这样做短期有利,但长期会怎样呢"
- "我该为了利益放弃原则吗"
与相邻 skill 的区分
- 与
f01(退让一步决策框架)的区别:f01 问的是"要不要退让"(策略问题);f09 问的是"这条路的方向对不对"(方向问题)。f01是战术,f09是战略。 - 与
f11(舍己勿疑 施恩勿报框架)的区别:f11 问的是"舍己/施恩时我的动机纯不纯";f09 问的是"这个选择的性质是公利还是私利"。f11是动机纯度,f09是方向判断。
E — 可执行步骤 (Execution)
当 skill 被激活后, agent应按以下步骤执行:
- 明确当前的选择选项
- 完成标准: 列出所有可选路径(至少2个),并用一句话描述每个选项的核心利益和潜在代价。
- 判停条件: 若用户无法列出选项(只有一个"不得不这样做"的想法),则进入步骤2的同时提醒用户"你可能忽略了其他选项"。
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 · 139 lines · 125 tokens per session scan A 0098a08f9a86
f09 tianli-renyu is a skill published in the GitHub repository ace3000chao/book2startup (80 stars, last pushed 4mo ago), licensed MIT. It adds 125 tokens to every session and 2,545 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 2026-09-03.
Other skills, from other repositories
ethics-review-checklist
Generate a story-specific editorial ethics checklist: consent verification, harm assessment, source protection, vulnerable-subject protocols, conflict-of-interest flags, and public interest justification — tailored to the story's specific risks.
s4h-ethics-empathy-circle
Applies Jaron Lanier's Circle of Empathy framework to determine which entities deserve moral consideration and rights. Use when questions arise about AI personhood, machine rights, robot citizenship, algorithmic agency, animal rights, or any decision about which entities belong inside or outside the circle of moral…
s4h-ethics-data-audit
Audit a data collection, retention, or sharing decision against ethical standards. Use when the user is making decisions about what data to collect, how long to keep it, who can access it, or who it's shared with. TRIGGERS: 'audit this data decision', 'is this data practice ok', 'data ethics check', any change to data…
s4h-ethics-vendor-review
Evaluate a third-party vendor, supplier, partner, or integration against ethical standards before signing a contract or shipping their code or service. Use when considering a new supplier, SaaS tool, data provider, API integration, outsourcing arrangement, or partnership. TRIGGERS: 'vet this vendor', 'is this supplier…
disclosure-assessment
Produces a disclosure requirements brief for a specific piece of content, identifying what must be disclosed, under which regulatory framework, and in what format — covering FTC, ASA, UCPD, and platform-specific rules across all common media formats.
AI Safety Auditor
Audit AI systems for safety, bias, and responsible deployment.