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 f02git 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/f02)<a href="https://agentmods.dev/skills/ace3000chao/book2startup/f02"><img src="https://agentmods.dev/badge/skills/ace3000chao/book2startup/f02/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/f02"><img src="https://agentmods.dev/badge/skills/ace3000chao/book2startup/f02.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 | $0.00112 | $0.02295 |
| Opus 5 | $0.00056 | $0.01148 |
| Sonnet 5 | $0.00022 | $0.00459 |
| Haiku 4.5 | $0.00011 | $0.00230 |
Grade A, and why
f02-self-sovereignty 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 — 136 lines — stays where its author put it; the contents beside it link to each section on GitHub.
以我转物思维模型
R — 原文 (Reading)
"以我转物者,得固不喜,失亦不忧,天地尽属逍遥;以物役我者,逆固生憎,顺亦生爱,一毛便生缠缚。"
— 洪应明, 菜根谭·以我转物 逍遥自在
I — 方法论骨架 (Interpretation)
主客颠倒,是一切痛苦的根源。
这个框架区分了两种立场:"以我转物"(我是主人,外物是工具)和**"以物役我"**(外物是主人,我是奴仆)。当你把名利、评价、得失当成主人,让它们指挥你的喜怒哀乐时,你就成了它们的奴仆——任何一个微小变动都能让你心生烦恼。反过来,如果你能确立"我是主人"的立场,让外物为你的目标服务,那么得到不狂喜,失去也不忧虑。
判断标准:问自己一个问题
- "此刻让我痛苦的,是事情本身,还是我对这件事的看法?"
- 如果是"看法"在控制你,那你正在被物役。
- 如果你能选择怎么看,那你就在"以我转物"。
一个简单测试:想象你失去了这个东西(一段关系、一笔钱、一个位置),一个月后你还会记得吗?如果会,说明它已经拥有了你。
A1 — 书中的应用 (Past Application)
案例 1: 秦桧和珅身首异处 vs 苏武岳飞千古流芳
- 问题: 南宋秦桧、清朝和珅面对权势的诱惑和压力,选择依附权贵、以权谋私。
- 方法论的使用: 他们以外物(权力、富贵)为主人,让这些外物驱动自己的行为,即使遗臭万年也在所不惜——典型的"以物役我"。
- 结论: 被外物奴役的人,最终失去了更重要的东西(名节、尊严)。
- 结果: 秦桧跪像至今被人唾弃,和珅被嘉庆赐死。与之对比,苏武、岳飞、文天祥宁守气节,被千古铭记。
案例 2: 飞蛾扑火自取灭亡
- 问题: 明明有晴空万里、皓月当空可以自由飞翔,飞蛾却偏要扑向灯火。
- 方法论的使用: 飞蛾把"灯火"当成主人,让那个光控制自己的方向,即使自取灭亡也在所不惜——最典型的"以物役我"。
- 结论: 被物欲奴役者,看不到更广阔的可能性,明明有更好的选择却执意走向毁灭。
- 结果: 飞蛾葬身灯火,警示人如果把追求对象当成主人,结局必然是失去自己。
A2 — 触发场景 (Future Trigger) ★
用户会在什么情境下需要这个 skill?
- 患得患失:已经做了一个决定,但事后反复纠结"如果当初选另一个会怎样",或为还没做的决定焦虑到失眠。
- 被人评价绑架:做一件事的主要动力是想让别人觉得自己好、怕别人说自己不好,甚至因为一句负面评价难受好几天。
- 失去某物后痛不欲生:失去一段关系、一份工作、一笔钱之后,觉得活不下去,或者情绪低落持续超过两周。
- 明明知道但做不到:理性上知道应该放下、应该不在乎,但情绪上就是过不去,知道但做不到。
- 决策时被"别人会怎么看"主导:在选择A还是B时,第一反应是"别人会不会觉得我做得不好",而不是"这个选择对我长期有什么价值"。
语言信号 (用户的话里出现这些就应激活)
- "我太在意别人的看法了"
- "这件事让我心里很乱"
- "我被这些事困住了"
- "我知道应该不在乎,但就是做不到"
- "因为这点事难受了好几天"
- "我做这个决定主要是怕别人说闲话"
- "失去了XX,我觉得天都塌了"
- "我控制不住一直想这件事"
与相邻 skill 的区分
- 与
f06(宠辱不惊情绪决策框架)的区别:f06 是"得意不失态、失意不失志"的具体操作;f02 是更底层的"主客立场转换",是 f06 的理论基础。 - 与
f03(动静皆静模型)的区别:f03 测试的是"内心是否安定";f02 测试的是"我是否在做主"。f03 偏向心理状态,f02 偏向主体性。 - 与
f01(退让一步决策框架)的区别:f01 解决"要不要退让"的策略问题;f02 解决"谁在控制我"的立场问题。
E — 可执行步骤 (Execution)
当 skill 被激活后,agent 应按以下步骤执行:
-
识别此刻谁在控制你
- 完成标准: 明确说出"此刻控制我的是外物(名利/评价/得失)还是我自己的判断"。
- 操作: 问自己"如果失去这个东西,我的核心价值会受损吗?"如果不会,它就不应该控制你。
-
做一次主客倒置
- 完成标准: 用"我是主人,这件事只是工具"的句式重新描述当前困境,格式:"我是___,这件事/这个东西是服务于我的___目标。"
- 判停条件: 若无法倒置(你觉得"没有这个东西我真的活不了"),则提示用户进入"逐步脱钩"流程。
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 · 136 lines · 112 tokens per session scan A 4e5918acf483
f02-self-sovereignty is a skill published in the GitHub repository ace3000chao/book2startup (80 stars, last pushed 4mo ago), licensed MIT. It adds 112 tokens to every session and 2,295 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
creative-flow-and-inspiration
Teaches the experiential practice of courting creative inspiration, sustaining openness, creating conditions for breakthrough ideas, staying in creative mode continuously, harnessing spontaneity, practising connected detachment, and using play as a serious creative method. Use when seeking breakthrough product ideas…
x-longtail-strategy
A strategy for understanding why most posts on X, formerly known as Twitter, receive ordinary engagement while a small number receive much more. It treats growth as improving the chance of producing posts in the top group rather than expecting every post to go viral.
x-four-saves
A checklist for judging whether a piece of content is worth publishing. It asks whether the content saves readers searching, understanding, trial and error, or rewriting work.
NorthwoodsMycelia
Optional cross-fleet help channel — post a question to other users' fleets, or respond to theirs. OFF BY DEFAULT. Must be explicitly opted into via header on every request. USE WHEN cross-fleet help, ask the network, second opinion from another user's AI, share what worked. NOT FOR private questions (this is public to…
NorthwoodsRhetoric
Output transformer — pipes any AI response through the deployed Northwoods Pack rhetoric module before showing it. Strips emoji-headed sections, splits long sentences on coordinating conjunctions, strips code blocks for chat context, collapses excessive blank lines. Preserves adult vocabulary. USE WHEN any AI response…
NorthwoodsSubstrate
Persistent memory store — second brain backed by D1 on user's own CF account. Save and retrieve entries across sessions and devices. USE WHEN need to remember, recall, search past notes, save a thought, look up what user said earlier, store a decision, find a breadcrumb. NOT FOR ephemeral session state (use…